JP2018072337A - Method of predicting recurrence risk of major adverse cardiac event - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow for predicting recurrence risk of a major adverse cardiac event within a predetermined period by means of a simple test.SOLUTION: First data, which is either based on measurements taken from a test sample collected from a subject or on predetermined index parameters obtained from the subject, is processed using a learning model that has been built on the basis of predetermined second data to predict recurrence risk of a major adverse cardiac event.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a method for predicting recurrence risk of major adverse cardiac events (MACE), a program for prediction and a prediction device.

  Predicting the risk of recurrence of major adverse events is extremely important because the recurrence of major adverse events can result in serious consequences.

  For example, Patent Document 1 below discloses a method for determining the risk of recurrent major adverse cardiac events within one year after the onset of at least one symptom of acute coronary syndrome.

U.S. Pat. No. 8,658,384

In Patent Document 1, in determining the risk of recurrence of major adverse cardiac events, so-called myocardial markers, cardiac troponin I (cTnI), pro-B-type natriuretic peptide (pro-BNP) or a cleavage product thereof, high sensitivity C-reactive protein (hsCRP), myeloperoxidase (MPO), placental growth factor (PIGF), estimated glomerular filtration rate (eGFR), homocysteine (HCY), choline, ischemia modified albumin (IMA), soluble CD40 ligand ( The amount of at least three kinds of biomarkers selected from the group consisting of sCD40L) and lipoprotein-related phospholipase A ₂ (LpPLA2) in the test sample is used as an indicator.

  However, since the determination method according to Patent Document 1 uses the amount of the myocardial marker in the test sample as an index, for example, a special and expensive cost is required separately from, for example, a test generally performed in a hospitalization test or a health checkup. It was necessary to carry out a proper inspection, and as a result, the burden for the implementation became large.

  The present invention has been made in view of the above problems. The present inventors have found that the above-described problems can be solved only by a simple and inexpensive test that is generally performed in a hospitalization test or a health checkup without separately performing a high-load test or the like. The invention has been completed.

That is, the present invention provides the following [1] to [14].
[1] An index parameter measured using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the amount of LDL-cholesterol , Prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level, glycohemoglobin level, crawl Amount, triglyceride amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct biliruby Quantity, lactate dehydrogenase (LDH) quantity, uric acid quantity, pH, potassium quantity, calcium quantity, sodium quantity, red blood cell count, hematocrit value, hemoglobin quantity, lymphocyte count, platelet count, basophil count, eosinophil count , Neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking habits, presence of anemia, history of acute myocardial infarction, narrowness requiring coronary angioplasty (PCI) History of heart disease, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, weight Acquiring first data based on two or more index parameters selected from the group consisting of: heart rate, urine protein (qualitative), urine sugar (qualitative), reason for hospitalization, and on-hospital disease When,
Processing the first data with a learning model constructed based on the second data to predict a recurrence risk, a prediction method for a recurrence risk of a major adverse cardiac event within a predetermined period.
[2] The second data is data including a history of recurrence of major adverse cardiac events within a predetermined period as an index parameter, and the second data includes the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, LDL-cholesterol amount, prothrombin time (international standard ratio (INR)), γ-glutamyltransferase peptidase amount, aspartate aminotransferase amount, amylase amount, alanine aminotransferase amount, alkaline phosphatase amount, albumin amount, antithrombin amount, glyco Hemoglobin level, chlor level, triglyceride level, fibrinogen level, fibrin / fibrinogen degradation product level, activated partial thromboplastin time, serum creatinine level, blood urea nitrogen level, blood glucose level, total cholesterol level, total bilbilin level, Number of spheres, direct bilirubin content, lactate dehydrogenase (LDH) content, uric acid content, pH, potassium content, calcium content, sodium content, red blood cell count, hematocrit value, hemoglobin content, lymphocyte count, platelet count, basophil count , Eosinophil count, neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, smoking habit, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) A history of angina pectoris, a history of heart failure, a history of atrial fibrillation requiring ablation treatment, a history of cerebral infarction, a history of peripheral arterial disease, a history of aortic dissection, dialysis, Data based on one or more index parameters further selected from the group consisting of age, height, weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and symptoms at the time of hospitalization, [1 ] In the specified period Method for predicting the risk of recurrence of major adverse cardiac events in the inner.
[3] The predetermined data according to [1] or [2], wherein the first data and the second data are data based on an index parameter selected from a group further including an index parameter derived from a myocardial marker. Of predicting the risk of recurrence of major adverse cardiac events in Japan.
[4] The myocardial marker is creatine kinase MB, human cardiac fatty acid binding protein, cardiac troponin I, cardiac troponin T, brain natriuretic peptide, pro-brain natriuretic peptide or its cleavage product, myeloperoxidase, placental growth factor, estimation [3], which is one or more selected from the group consisting of glomerular filtration rate, homocysteine, ischemia-modified albumin, soluble CD40 ligand, lipoprotein-related phospholipase A2, choline, and highly sensitive C-reactive protein. Of predicting the risk of recurrence of major adverse cardiac events within a given period of time.
[5] The method for predicting the risk of recurrence of a major adverse cardiac event within a predetermined period according to any one of [1] to [4], wherein the test sample is blood or a blood-derived sample.
[6] The main adverse cardiac event is acute myocardial infarction, angina pectoris with coronary revascularization, heart failure requiring hospitalization, atrial fibrillation, stroke, or death due to cardiovascular disease. [1] The prediction method for the risk of recurrence of major adverse cardiac events within a predetermined period as described in any one of [5].
[7] The learning model divides the second data into a plurality of data groups, uses each of the data groups as teacher data, and performs machine learning performed under a plurality of parameter conditions different for each of the plurality of data groups. A plurality of first learning models constructed to predict whether there is a recurrence of a major adverse heart event or unknown, and a plurality of second models for predicting whether there is no or unknown recurrence of a major adverse cardiac event Learning model,
The step of predicting the recurrence risk of the major adverse cardiac event is a step of processing the first data by the first learning model and the second learning model to predict a recurrence risk [1] to [ 6] The method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period of any one of [6]
[8] The learning model includes a plurality of first selection learning models selected based on sensitivity and positive predictive value for each of the plurality of first learning models and the plurality of second learning models, and a plurality of first learning models. 2 selection learning model,
The step of predicting the recurrence risk of the major adverse cardiac event is a step of processing the first data by the first selective learning model and the second selective learning model to predict a recurrence risk [7] A method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period as described in.
[9] The step of predicting the recurrence risk of the major adverse heart event processes the first data by the first selection learning model and the second selection learning model, and the first selection learning model and the second Obtaining a first determination result for each selection learning model, voting on the first determination result, obtaining a second determination result based on a vote rate for each of the first selection learning model and the second selection learning model; The second determination result of the first selective learning model and the second determination result of the second selective learning model are integrated to obtain a third determination result. Based on the third determination result, a major adverse event The method for predicting the risk of recurrence of major adverse cardiac events within the predetermined period according to [8], wherein the risk of recurrence is predicted.
[10] A program for predicting a risk of recurrence of a major adverse cardiac event within a predetermined period, including the following steps executed by a computer including a calculation unit,
The calculation unit is an index parameter measured by using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the LDL-cholesterol Amount, prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase amount, aspartate aminotransferase amount, amylase amount, alanine aminotransferase amount, alkaline phosphatase amount, albumin amount, antithrombin amount, glycohemoglobin amount, Amount of crawl, amount of triglyceride, amount of fibrinogen, amount of fibrin / fibrinogen degradation product, activated partial thromboplastin time, amount of serum creatinine, amount of blood urea nitrogen, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct biliary count Bin volume, lactate dehydrogenase (LDH) volume, uric acid volume, pH, potassium volume, calcium volume, sodium volume, red blood cell count, hematocrit level, hemoglobin volume, lymphocyte count, platelet count, basophil count, eosinophil Number, neutrophil count, sex, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of angina pectoris, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, Obtain first data based on two or more index parameters selected from the group consisting of weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and on-hospital disease, based on selection frequency Steps,
The calculation unit includes a step of processing the first data with a learning model constructed based on the second data to predict a recurrence risk of a major adverse cardiac event within a predetermined period.
[11] The learning model divides the second data into a plurality of data groups, uses each of the data groups as teacher data, and performs machine learning performed under a plurality of parameter conditions different for each of the plurality of data groups. A plurality of first learning models constructed to predict whether there is a recurrence of a major adverse heart event or unknown, and a plurality of second models for predicting whether there is no or unknown recurrence of a major adverse cardiac event Learning model,
The step of predicting the risk of recurrence of the major adverse event is that the calculation unit processes the first data by the first learning model and the second learning model to determine the major adverse event within a predetermined period. The program according to [10], which is a step of predicting a recurrence risk.
[12] The learning model includes a plurality of first selection learning models selected based on sensitivity and positive predictive value for each of the plurality of first learning models and the plurality of second learning models, and a plurality of first learning models. 2 selection learning model,
The step of predicting the risk of recurrence of the major adverse heart event is such that the calculation unit processes the first data by the first selective learning model and the second selective learning model, and the major adverse heart in a predetermined period. The program according to [11], which is a step of predicting a risk of recurrence of an event.
[13] The step of predicting the recurrence risk of the major adverse cardiac event is such that the calculation unit processes the first data by the first selection learning model and the second selection learning model, and the first selection learning A first determination result is obtained for each model and the second selection learning model, voting is performed on the first determination result, and a second determination based on a vote rate is obtained for each of the first selection learning model and the second selection learning model. Obtaining a result, integrating the second determination result of the first selective learning model and the second determination result of the second selective learning model, obtaining a third determination result, and based on the third determination result The program according to [12], which is a step of predicting a recurrence risk of a major adverse cardiac event within a predetermined period.
[14] An index parameter measured using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the amount of LDL-cholesterol , Prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level, glycohemoglobin level, crawl Amount, triglyceride amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct biliyl Level, lactate dehydrogenase (LDH) level, uric acid level, pH, potassium level, calcium level, sodium level, red blood cell count, hematocrit level, hemoglobin level, lymphocyte count, platelet count, basophil count, eosinophil Number, neutrophil count, sex, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of angina pectoris, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, Generate first data based on two or more index parameters selected from the group consisting of body weight, heart rate, urine protein (qualitative), urine sugar (qualitative), reason for hospitalization, and on-hospital disease First data raw An acquisition unit,
A prediction unit that processes the first data acquired by the first data generation acquisition unit with a learning model constructed based on the second data, and predicts a recurrence risk of a major adverse cardiac event within a predetermined period. , A prediction device for the risk of recurrence of major adverse cardiac events within a given period.

  According to the method for predicting the risk of recurrence of major adverse cardiac events according to the present invention, it is possible to determine the risk of recurrence with higher accuracy in simpler steps. As a result, it is possible to provide more accurate consulting on the treatment policy, the frequency of hospital visits, and the like. In addition, it is possible to carry out only simpler and cheaper examinations without carrying out high-load examinations such as measurement of biomarkers that require special and expensive costs, so the burden for implementation can be further reduced. .

FIG. 1 is a flowchart showing a method for predicting the risk of recurrence of major adverse cardiac events. FIG. 2 is a flowchart for explaining step (S1). FIG. 3 is a flowchart for explaining the step (S0). FIG. 4 is a table showing an example of index parameters according to the second data. FIG. 5 is a schematic diagram illustrating a configuration of complete data for generating the second data. FIG. 6 is a schematic diagram of the second data. FIG. 7 is a flowchart for explaining step (S2). FIG. 8 is a table for explaining the evaluation result of the cutoff value. FIG. 9 is a table for explaining the evaluation result of the cutoff value. FIG. 10 is a schematic block diagram for explaining the configuration of the computer. FIG. 11 is a schematic block diagram for explaining the configuration of the calculation unit. FIG. 12 is a graph showing the results of stratifying the evaluation data group into a MACE high risk group and a low risk group. FIG. 13 is a graph showing the prediction performance. FIG. 14 is a graph showing the selection frequency based on the ratio of selection learning models in which a certain index parameter is used in the entire selection learning model.

  Embodiments of the present invention will be described below with reference to the drawings. In addition, each drawing has shown only the shape of the component, the magnitude | size, and arrangement | positioning to such an extent that an invention can be understood. The present invention is not limited to the following description, and each component can be appropriately changed without departing from the gist of the present invention. In the drawings used for the following description, the same components are denoted by the same reference numerals, and overlapping descriptions may be omitted. Moreover, the component concerning embodiment of this invention is not necessarily manufactured or used by arrangement | positioning shown by drawing.

  The present invention relates to a method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period. Such a prediction method is an index parameter that is measured using a test sample collected from a subject or obtained from a subject, and includes C-reactive protein amount, D-dimer amount, HDL-cholesterol amount, LDL- Cholesterol content, prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase content, aspartate aminotransferase content, amylase content, alanine aminotransferase content, alkaline phosphatase content, albumin content, antithrombin content, glycohemoglobin content , Crawl amount, triglyceride amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, Contacted bilirubin, lactate dehydrogenase (LDH), uric acid, pH, potassium, calcium, sodium, red blood cell count, hematocrit, hemoglobin content, lymphocyte count, platelet count, basophil count, eosinic acid Requires sphere count, neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, smoking habit, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of angina pectoris, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height Obtaining first data based on two or more index parameters selected from the group consisting of body weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and oncology at the time of hospitalization; 1 data is duplicated Processing with a learning model constructed based on a data group including a number of second data to predict a recurrence risk.

[Explanation of terms]
As used herein, “major adverse cardiac event” refers to acute myocardial infarction, angina pectoris with coronary revascularization, heart failure requiring hospitalization, atrial fibrillation, stroke (transient ischemic attack (TIA) ), Or death due to cardiovascular reasons.

  As used herein, “prediction of recurrence risk” means within a predetermined period (eg, 3 months, 6 months, 1 year, 1 year, 6 months, 2 years, 3 years or longer) after the onset of major adverse cardiac events. It means predicting the recurrence (or unknown) or the likelihood (or unknown) of further major adverse cardiac events.

  In the present specification, the “subject” means a living body that is a prediction target of recurrence risk, and specifically includes, for example, a patient.

  In the present specification, the “test sample” means an arbitrary sample capable of obtaining an index parameter described later. Examples of such test samples include liquid samples (eg, blood (whole blood) or blood-derived samples (eg, serum, plasma), urine, saliva, ascites, tissue extract, cell extract), non-liquid samples. (For example, a tissue sample, a cell sample) is mentioned, but a liquid sample is preferable, blood or a blood-derived sample is more preferable, and blood is more preferable. The test sample may be processed in advance before measurement. Examples of such treatment include centrifugation, extraction, concentration, fractionation, cell fixation, tissue fixation, tissue freezing, and tissue thinning.

  In this specification, the “index parameter” refers to the results of various tests performed on the above-described test sample, for example, the results of so-called blood tests (such as biochemical tests, blood glucose tests, general blood tests, and coagulation tests). Content, quantity, characteristics, etc.) and other parameters based on biological information.

  Examples of “index parameters” include C-reactive protein (CRP), D-dimer, HDL-cholesterol (HDL-C), LDL-cholesterol (LDL-C), prothrombin time (international standard ratio (INR)) (PT -INR), γ-glutamyl transpeptidase (γ-GTP), aspartate aminotransferase (AST (GOT)), amylase (AMY), alanine aminotransferase (ALT (GPT)), alkaline phosphatase (ALP), albumin ( ALB), antithrombin (AT), glycated hemoglobin (HbA1c), chlor (Cl), triglyceride (TG), fibrinogen (Fbg), fibrin / fibrinogen degradation product (FDP), activated partial thromboplastin time (APTT) ), Serum creatinine (CRE), blood urea nitrogen (BUN), blood glucose (Glu), total cholesterol (CHO), total bibilin (T · Bil), monocyte count (Mono), direct bilirubin (D · Bil), Lactate dehydrogenase (LD (LDH)), urine protein (qualitative) (UP), uric acid (UA), urine sugar (qualitative) (US), pH, potassium (K), calcium (Ca), sodium (Na) , Red blood cell count (RBC), hematocrit value (Ht), hemoglobin (Hb), lymphocyte count (Lym), platelet count (PL), basophil count (Baso), eosinophil count (Eos), and neutrophil One example is the number of balls (Neut). Information on these measured values in the test sample can be obtained by a conventional method.

  Examples of “index parameters” include the history of recurrence of major adverse cardiac events within a given period, gender, reason for hospitalization, current onset symptoms, history of diabetes, history of hypertension, history of dyslipidemia, smoking habits, History of anemia, history of acute myocardial infarction, history of angina requiring coronary angioplasty (PCI), history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction Further examples include binarized or digitized parameters for biometric information (attributes, qualitative data) such as history, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, weight, heart rate. Among these, the “reason for hospitalization” can be determined based on, for example, a doctor's diagnosis and treatment when the patient (subject) is hospitalized.

  Specifically, for example, when the subject is a patient who has been diagnosed with acute myocardial infarction (AMI) and is hospitalized, the index parameter may be set to 1, and an angina pectoris in which the subject has undergone coronary revascularization. If the patient is hospitalized for the reason, the index parameter may be 2, and if the subject is a patient who has been diagnosed with heart failure (HF) and is hospitalized, the index parameter may be 3. If the patient is hospitalized because of atrial fibrillation (required myocardial ablation (ablation)), the index parameter may be 4, and the patient is diagnosed with cerebral infarction (CI) and hospitalized. In some cases, the index parameter may be 5, and when the subject is a patient diagnosed with a transient ischemic attack (TIA) and hospitalized, the index parameter may be 6.

  As for “oncology at admission”, for example, the pathological findings based on the electrocardiogram waveform indicate that the index parameter is 0 in the case of “no atrial fibrillation” (sinus rhythm: normal), and there is atrial fibrillation. In this case, the index parameter is 1.

  In the present specification, the “myocardial marker” means an index related to the heart (myocardium) in particular, among the results of examinations performed on test samples. Examples of “myocardial markers” include creatine kinase MB (CKMB), human cardiac fatty acid binding protein, cardiac troponin I, cardiac troponin T, brain natriuretic peptide (BNP), pro-brain natriuretic peptide or its cleavage product, myel Examples include peroxidase, placental growth factor, estimated glomerular filtration rate, homocysteine, ischemia-modified albumin, soluble CD40 ligand, lipoprotein-related phospholipase A2, choline, and highly sensitive C-reactive protein.

[Method of predicting the risk of recurrence of major adverse cardiac events within a specified period]
Hereinafter, each of the steps included in the method for predicting the risk of recurrence of major adverse heart events according to the present embodiment will be described in detail. In this embodiment, unless otherwise specified, “steps” are executed by a computer (details will be described later).

  With reference to FIG. 1, the prediction method of the recurrence risk of the main adverse cardiac event within the predetermined period of this embodiment is demonstrated. FIG. 1 is a flowchart showing a prediction method.

(1) An index parameter measured using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the amount of LDL-cholesterol , Prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level, glycohemoglobin level, crawl Amount, triglyceride amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct biliruby Quantity, lactate dehydrogenase (LDH) quantity, uric acid quantity, pH, potassium quantity, calcium quantity, sodium quantity, red blood cell count, hematocrit value, hemoglobin quantity, lymphocyte count, platelet count, basophil count, eosinophil count , Neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking habits, presence of anemia, history of acute myocardial infarction, narrowness requiring coronary angioplasty (PCI) History of heart disease, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, weight Acquiring first data based on two or more index parameters selected from the group consisting of: heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and on-hospital disease (S1)
As shown in FIG. 1, the method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period of the present embodiment includes the step (S1).

  Hereinafter, step (S1) will be specifically described with reference to FIG. FIG. 2 is a flowchart for explaining step (S1).

  Prior to step (S1), it is preferable to construct a learning model to be described later.

  As shown in FIG. 2, in step (S1), first, a step (S1-1) of collecting a test sample is performed. The method of selecting the test sample and collecting the test sample in step (S1-1) is not particularly limited on condition that the index parameter can be acquired.

  For example, when the test sample is a sample particularly related to blood, the test sample can be obtained by a normal blood collection method.

  In the present embodiment, an examination result and / or biological information based on a test sample collected from a subject is used as the index parameter.

  In the method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period of the present embodiment, it is preferable to use an index parameter that is not derived from a myocardial marker because it can improve convenience and reduce the load. .

  Therefore, in this embodiment, it is preferable to next perform the step (S1-2) of acquiring the first data based on the index parameter not derived from the myocardial marker measured using the obtained test sample.

  This step (S1-2) can be performed by analyzing (measuring) the obtained test sample using any conventionally known suitable inspection means (measurement means) and inspection method (measurement method).

  Examples of index parameters not derived from myocardial markers that can be applied to the present embodiment include C-reactive protein amount, D-dimer amount, HDL-cholesterol amount, LDL-cholesterol amount, prothrombin time (international standard ratio (INR)). )), Γ-glutamyl transpeptidase amount, aspartate aminotransferase amount, amylase amount, alanine aminotransferase amount, alkaline phosphatase amount, albumin amount, antithrombin amount, glycohemoglobin amount, chlorine amount, triglyceride amount, fibrinogen amount, fibrin / Fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct bilirubin level, lactate dehydrogenase LDH), uric acid, pH, potassium, calcium, sodium, red blood cell count, hematocrit value, hemoglobin content, lymphocyte count, platelet count, basophil count, eosinophil count, and neutrophil count Can be mentioned.

  The format of the first data is not particularly limited on condition that it can be applied to the prediction method of the present invention (step (S2) described later).

  Further, in the step (S1-2) of acquiring the first data, examples of the index parameter not derived from the myocardial marker used in addition to the already described “group of index parameters not derived from the myocardial marker” , Sex, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking, presence of anemia, history of acute myocardial infarction, history of angina requiring coronary angioplasty (PCI) History of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, weight, heart rate, urine Examples thereof include biological information obtained from a subject such as protein (qualitative) and urine sugar (qualitative).

  In addition, as an example of the index parameter not derived from the myocardial marker, which is used in addition to the group of index parameters not derived from the myocardial marker already described, it was obtained from a subject such as the reason for hospitalization and on-hospital disease. Biological information can be mentioned.

  In the present embodiment, the first data (and second data described later) further includes an index parameter derived from the already explained myocardial marker, in addition to a group of index parameters not derived from the already described myocardial marker. It is good also as data based on the index parameter selected from.

  Thus, if the index parameter derived from the myocardial marker is further used, for example, the prediction accuracy of the recurrence risk in a relatively short period such as “within 3 months” after the onset of the major adverse cardiac event can be further improved.

  The first data (and second data described later) is data based on an index parameter selected from the group further including an index parameter derived from an electrocardiogram in addition to the index parameter group not derived from the myocardial marker already described. It can be.

  Examples of index parameters derived from such an electrocardiogram include P wave height, R wave interval (RR interval), PQ time, R wave height, QRS width, ST portion change amount (S wave The sum of the height and the height of the T wave), the height of the T wave, and the power spectrum obtained by Fourier transforming the electrocardiogram.

  If the index parameters derived from the electrocardiogram are further used in this way, the number of index parameters can be further increased, so that the effect of improving the prediction accuracy of the recurrence risk of the main adverse cardiac event can be obtained. .

  The first data can be generated based on two or more types of index parameters selected from the group of index parameters already described. Such an index parameter is preferably selected based on a selection frequency described later.

  In the method for predicting the risk of recurrence of a major adverse event within a predetermined period of the present embodiment, the number of index parameters that can be used can be arbitrarily set in consideration of the time required for prediction. The number of index parameters that can be used can be determined, for example, by appropriately selecting an index parameter having a higher selection frequency in consideration of prediction accuracy.

  In the method for predicting the risk of recurrence of a major adverse event within a predetermined period of the present embodiment, two or more types of index parameters are used as the first data (and second data described later) among the index parameters already described. . However, the number of indicator parameters that can be used is not particularly limited. Examples of the index parameter include not only two types but also 5 types or more, 10 types or more, 15 types or more, 20 types or more, 25 types or more, 30 types or more, 35 types or more, 40 types or more, 45 types or more or already All described can be used.

  When two or more types of index parameters are used, an appropriate combination of the two or more types of index parameters can be selected by processing such as correlation rule analysis or clustering.

(2) A step of processing the first data with a learning model constructed based on the second data to predict a recurrence risk (S2)
As shown in FIG. 1, the method for predicting major adverse event within a predetermined period of the present embodiment includes the above step (S2).

  Here, first, with reference to FIG. 3, the step (S0) for constructing the learning model used in the step (S2) will be described. FIG. 3 is a flowchart for explaining the step (S0).

  Note that the step (S0) of building the learning model can be performed prior to the step (S1) already described.

  As shown in FIG. 3, first, a step of preparing second data including a plurality of bit strings (S0-1) is performed.

  Specifically, the bit string is based on two or more index parameters selected based on the selection frequency from the group added to the “group consisting of a plurality of index parameters not derived from the myocardial marker” already described. 2 Generate and prepare data.

  The second data is teacher data for constructing a learning model. Here, the second data and generation thereof will be described.

  First, a case data group collected in advance is prepared. The case data group of the present embodiment is a data group configured by collecting case data including numerical data on a plurality of index parameters related to a patient who has developed a major adverse cardiac event, and corresponds to the first data. ing.

  Case data group consists of multiple case data for which the presence or absence of recurrence of major adverse events within a prescribed period of 1 year or more after hospitalization, that is, “with recurrence”, which has recurred major adverse events within a prescribed period. Includes “relapsed” case data classified and “no relapse” case data classified as “no recurrence” that did not recur major adverse cardiac events within a predetermined period.

  Therefore, the case data group includes a “relapsed” case data group composed of a plurality of “relapsed” case data and a “no relapsed” case data group composed of a plurality of “no relapsed” case data.

  Next, each of the case data groups, that is, the “relapsed” case data group and the “no relapse” case data group of the main adverse cardiac event, are (i) a case data group for constructing a learning model and (ii) an evaluation Divide into case data group. Among these, the second data is generated using the divided “case data for constructing a learning model”.

  If the number of “recurring” case data included in the “case data group for learning model construction” and the number of “no recurrence” case data are not equal and biased, learning is performed when constructing the learning model. There is a risk of bias.

  Therefore, if there is a bias in this way, an equalization process is performed to equalize the number of “recurrent” case data and the number of “non-recurrent” case data to the same level. “Case data group” is prepared. Specifically, for example, if the number of “relapsed” case data is less than the number of “no recurrence” case data, the same number of “no recurrence” case data as the number of “recurring” case data is extracted. Thus, it is preferable to perform equalization processing to make both numbers uniform.

  Next, the equalized case data group is further divided into a plurality of groups. The number of case data included in each of the divided groups may be approximately the same, and is preferably the same. The total number of groups after division is not particularly limited, but is preferably about 4, for example.

  Next, “partial data” is generated using a part of the divided plurality of equalized case data groups. For example, when the data is divided into four equalized case data groups, “partial data” may be generated using three groups (75%) of them. In this case, the remaining one group (25%) is set as “evaluation data”.

  And a learning model is constructed | assembled using the 2nd data which is the data group containing the complete data (case data) which is the original data used for the production | generation of this some partial data and partial data (for details, see FIG. (It will be described later.)

Here, with reference to FIG. 4, the example of the parameter | index parameter concerning 2nd data is demonstrated. FIG. 4 is a table showing an example of index parameters according to the second data.
In FIG. 4, in addition to the index parameter name and the index parameter, the definition and unit of the index parameter, and the type of the index parameter are shown. The index parameters are assigned serial numbers (1 to 24) as ID numbers.

  For the second data, refer to “Indicator parameter about whether major adverse events recurred within the prescribed period after the occurrence of major adverse events, or did not recur (history of major adverse events within the prescribed period)” Selection is mandatory. In the first data, such an index parameter cannot be selected because it cannot exist in the first place.

  The group of index parameters according to the second data has already been included, except that “index parameters regarding whether or not a major adverse event has recurred within a predetermined period after the occurrence of a major adverse event” has been included. It can be the same as the group of index parameters according to the first data described.

  In the selection of the index parameter in the second data, it is preferable to select the index parameter selected from the group consisting of the same index parameters as the first data based on the selection frequency (details will be described later).

  The second data will be described with reference to FIGS. FIG. 5 is a schematic diagram for explaining the configuration of complete data for generating partial data. FIG. 6 is a schematic diagram of second data that is partial data.

As shown in FIG. 5 and FIG. 6, the second data including complete data and partial data generated from the complete data is a bit string (bit string) for selecting an index parameter and selecting case data used during machine learning. It is data expressed as
In the example shown in FIG. 5, 10 index parameters and 10 case data are used in the complete data for generating partial data.

  Here, the “case data” is data (parameters) for specifying a case (patient) corresponding to the selected index parameter. Note that a plurality of cases for a single patient may exist as separate case data.

  As shown in FIG. 5 and FIG. 6, the bit string for the second data including the complete data and the partial data includes the first partial BSP1 in which the selection or non-selection of the index parameter is described and the selection or non-selection of the case data. It consists of a second part BSP2 in which the selection is described. In this example, the second part BSP2 is described continuously after the first part BSP1. In this example, ten index parameters (ID: 1 to 10) are described in the first part BSP1, and case data (ID: PT1 to PT10) of ten cases used are described in the second part BSP2. Yes.

  That is, in FIG. 5 and FIG. 6, the uppermost number sequence indicates the ID number, and the numerical values on the lower level indicate selection or non-selection of the index parameter and selection or non-selection of the case data.

  The bit string shown in FIG. 5 is complete data showing an example using all 10 kinds of index parameters and case data of 10 cases. Therefore, the numerical values constituting the bit string are all composed of “1”. ing. Here, if considered in association with the index parameter shown in FIG. 4, this bit string specifically means that the index parameter related to (ID: 1 to 10) is used in contrast.

  As shown in FIG. 4, when the obtained test result and / or biological information is acquired as quantitative data (numerical data) such as the content, age, and height of a predetermined component, for example, it is used as an index parameter as it is. Can be used.

  In addition, such quantitative data (numerical data) should be converted into an ordinal scale, interval scale, proportional scale, etc., taking into account the age (elderly, middle-aged, adolescent, boy, young), for example, and used as an index parameter. Can do.

  For attribute data relating to biological information such as a history of diabetes, a history of hypertension, a history of dyslipidemia, and qualitative data such as positive (level) and negative, for example, “Yes = 1, No = 0” and 2 It can be used as an index parameter by converting it into a value.

  Next, generation of second data including complete data and partial data based on the complete data will be described. Specifically, multiple index parameters (data group columns) and case data (data group rows) included in complete data are selected, and multiple partial data different from the original complete data are generated. Thus, the second data which is a data group including the complete data and a plurality of partial data based on the complete data is prepared.

  As described above, the second data includes complete data including all index parameters and all case data in addition to a plurality of partial data, provided that the prediction performance of the corresponding learning model is sufficient. It may be.

Here, the generation of partial data and partial data will be described with reference to FIG.
Here, partial data (bit string) based on complete data (bit string) that can constitute the second data already described with reference to FIG. 5 and generation steps thereof will be described.

  As shown in FIG. 6, in this example, 6 types (ID = 1, 3, 4, 6, 7, and 9) are selected from 10 types of index parameters, and 4 types (ID = 2, 5, 8, and 8) are selected. 10) is not selected, and 4 cases (ID = PT1, PT4, PT7 and PT10) are selected from the case data of 10 cases, and 6 cases (ID = PT2, PT3, PT5, PT6, PT8 and PT9) are selected. ) Is not selected.

  Specifically, for example, the partial data is obtained by generating a plurality of partial data by randomly selecting the selection results so as not to overlap without particularly considering the combination of the selected index parameter and the learning model. be able to. Then, a process of including the obtained partial data in the second data is performed.

  A learning model having a larger variance is obtained by performing the step of obtaining second data that is a data set incorporating a plurality of partial data obtained by re-sampling the index parameter (feature value) in this way. Can be obtained.

  As shown in FIG. 6, in the present embodiment, the second data including partial data is managed and stored as a data set including a plurality of bit strings. FIG. 6 shows bit strings (BS1, BS2, and BS3) of partial data having three patterns included in the data set that is the second data. Details of the processing relating to a data set (second data) including a plurality of bit strings will be described later.

  Next, a step (S0-2) of constructing a learning model by machine learning is performed using the obtained second data.

  The learning model constructed in the present embodiment includes a plurality of types of learning models, that is, a first learning model and a second learning model.

  In the present embodiment, the first learning model is a learning model that predicts “there is a major adverse cardiac event reoccurring within a predetermined period” or “unknown”. The second learning model is a learning model that predicts “no recurrence of major adverse cardiac events within a predetermined period” or “unknown”.

Hereinafter, step (S0-2) will be specifically described.
Here, complete data that can be included in the second data and each of the plurality of partial data are used as teacher data, and a plurality of learning models, that is, a plurality of first learning models and a plurality of second learning models are constructed by machine learning. .

  In the present embodiment, the first learning model and the second learning model are preferably support vector machines (SVM). Also, as means other than the support vector machine, other means such as a neural network can be used.

  In this embodiment, an example of a support vector machine that can be used for machine learning to construct a learning model is obtained from a website (https://cran.r-project.org/web/packages/e1071). A support vector machine based on the "e1071 package of R language (https://www.R-project.org)" is possible.

  Here, the learning model is constructed by machine learning performed by dividing the second data into a plurality of data groups, using each of the data groups as teacher data, and performing a plurality of parameter conditions different for each of the plurality of data groups. It is preferable.

  In the method for predicting major adverse event according to this embodiment, a support vector machine using an RBF kernel (Gauss kernel) as a kernel function can be used for machine learning.

  Specifically, the machine learning is performed under a plurality of different parameter conditions. The “different parameter conditions” can be set by adjusting an optimum adjustment coefficient (hyper parameter) by, for example, random sampling.

  For example, when using a support vector machine employing a Gaussian kernel as described above, a plurality of different learning models can be constructed from the same partial data by adjusting the γ parameter and the C parameter, which are adjustment coefficients. .

  In this case, for example, five parameters, γ = 0.01, γ = 0.02, γ = 0.03, γ = 0.04, and γ = 0.05, are used as γ parameters for adjusting the complexity of the identification boundary line. , And the allowable parameter C of the soft margin is replaced by a discriminant function (described later) used in performance evaluation during machine learning, so that the learning model can be constructed with C = 100. it can.

  For example, by setting the adjustment coefficient as described above, a learning model having a larger variance can be obtained.

  The support vector machine is a learning model that is originally constructed so that the variance is small. However, in the present embodiment, a support vector machine having a large dispersion is constructed, and the processing described later is further performed.

  According to the present embodiment, as a result, prediction accuracy can be further improved by constructing a support vector machine having a large variance. In the following description, processing using a support vector machine as a learning model will be described unless otherwise specified.

  Next, a step (S0-3) of processing the evaluation data with the learning model and evaluating the prediction result based on the Pareto rank is performed.

  In this step (S0-3), the performance of the first learning model and the second learning model is evaluated based on the Pareto rank using the sensitivity and the positive predictive value as indices. Hereinafter, this evaluation step will be specifically described.

  1) First, prediction results are obtained for all learning models using the constructed learning models (first learning model and second learning model) and the evaluation data already described.

2) When dealing with an identification problem that assumes a predictable area and an impossible area, it is important to reduce the degree of misidentification as much as possible and to increase the number of objects that can be correctly predicted as much as possible. Therefore, it is obtained using the objective function O ₁ (function for measuring a prediction error in a predictable region) and the objective function O ₂ (function for counting the number of data that can be correctly predicted in the data space). Evaluate the predicted results.

Here, the objective function O ₁ and the objective function O ₂ will be described. Here, a case will be described in which a support vector machine is used as the discriminant function to evaluate the first learning model whose prediction target is “with recurrence”.

  As a premise, in the evaluation data (x, y), x is a set of values measured for a certain case, y is a correct answer label, and signs “with recurrence = + 1” and “without recurrence = −1”. Any value is assumed as data.

  If the discriminating function of the first learning model constructed by learning using predetermined second data is f, x corresponding to the discriminating function f is input based on “there is a recurrence” that is the discriminating target of this learning model. Based on the predicted value f (x) calculated at this time, if f (x)> 0, it is predicted as “recurring”, and if f (x) <0, it is determined as “unknown”. Conversely, in the second learning model whose identification target is “no recurrence”, “no recurrence” is predicted if the predicted value of the discrimination function is f (x) <0, and f (x)> 0. “Unknown”.

  The first learning model for predicting “with or without recurrence” according to the present embodiment always predicts “with recurrence” for data existing in the predictable region, and “unknown” for data existing outside the predictable region. "

  Therefore, when data that should be determined as “no recurrence” exists in the predictable region of the first learning model, the prediction always fails.

The evaluation by the objective function O ₁ and the objective function O ₂ in the predictable region of “there is recurrence” in the first learning model will be described.

Note that the evaluation by the objective function O ₁ can be generalized for the learning model using the two-group discriminant function even when a learning model other than the support vector machine is used. Specifically, for example, when a linear discriminant function, a quadratic discriminant function, or a logistic discriminant function is used, evaluation is performed using the distance from the mispredicted data to the identification line as in the case of the support vector machine. be able to.

In the objective function O ₁ , the minimization of the sum total of the distance (SVM Confidence Margin) from the mispredicted data to the identification line is considered.

  The SVM Confidence Margin is defined as the product yf (x) of the predicted value f (x) and the correct answer label y using the predicted value f (x) calculated by the identification function f of the evaluation data (x, y). The

  Here, when the evaluation data is correctly predicted to be “with recurrence”, the SVM Confidence Margin is a product of the predicted value f (x)> 0 and the correct answer label “with recurrence = + 1”. Takes a value. On the other hand, if the correct label y is “no recurrence = −1” even though it is predicted to be mispredicted in the predictable region, that is, f (x)> 0 and “recurring”, the predicted value is The product with the correct answer label takes a negative value.

  Similarly, in the second learning model, when the evaluation data is correctly predicted as “no recurrence”, the SVM Confidence Margin indicates that the predicted value f (x) <0 and the correct label “no recurrence = −1”. Therefore, it takes a positive value and takes a negative value if it is mispredicted.

The minimization of the objective function O ₁ by SVM Confidence Margin is expressed by the following equation (1).

In formula (1), for m (y, f (x))
And abs [x] represents the absolute value of x. That is, the expression (1) has a function for counting only the degree of misidentification in the predictable region in the SVM Confidence Margin.

When evaluating the first learning model whose prediction target is “with recurrence”, “with recurrence” data is predicted as a negative example (f (x _i ) <0) for the distance from the identification line of each evaluation data. Only the estimated distance of the evaluation data.

Next, with regard to the objective function O ₂ , let us consider maximizing the number of “recurring” evaluation data that is correctly predicted while allowing a certain degree of erroneous prediction.

When the correctness of the prediction of the discrimination function f is expressed using the correct answer label y and the predicted value f (x), it is expressed by the following formula (2).

Here, maximization of the objective function O ₂ when prediction is performed for k pieces of evaluation data is expressed by the following equation (3).

  In Expression (3), the second term on the right side represents regularization based on the total number of “no recurrence” in the predictable region.

  In equation (3), α (1> α> 0), which is a variable for adjusting the tolerance of misprediction, is preferably set to α = 0.3.

  Thus, the prediction result of the learning model is evaluated by the Pareto rank.

  Next, a step (S0-4) of selecting a learning model having a high evaluation and a bit string for which a learning model having a high evaluation can be constructed is performed.

Specifically, a learning model (first learning model and second learning model) in which the evaluation values (O ₁ , 1 / O ₂ ) by the objective functions O ₁ and O ₂ already described are smaller and such a learning model are constructed. The bit string (second data) that can be selected is selected.

  Here, step (S0-4) will be specifically described.

  First, a plurality of evaluation data is prepared which has the same index parameter configuration as that of the first data described above and whose index parameter values do not match the first data.

  The evaluation data used for selecting the learning model belongs to, for example, an equalized case data group that has not been used to generate second data (partial data) among a plurality of divided equalized case data groups Case data can be used.

  Then, the evaluation data is processed by a plurality of first learning models and a plurality of second learning models, respectively, to predict a risk of recurrence of a major adverse cardiac event within a predetermined period.

Next, with respect to the obtained prediction results, the first learning model and the second learning model are evaluated by the Pareto rank using the sensitivity and positive predictive value as indices using the objective functions O ₁ and O ₂ already described.

  Based on the obtained evaluation results, both the sensitivity and the positive predictive value are high, that is, the learning model (the first learning model and the second learning model) having a high evaluation and such a learning model can be constructed. Two data (bit strings) are selected and stored.

  The number of learning models to be selected and the number of corresponding bit strings can be arbitrarily set in consideration of the time required, the implementation scale, and the like. In the case of this embodiment which has already been described, it is preferable that the number is about 40.

  The step (S0-4) of selecting a highly evaluated learning model (first learning model and second learning model) and a corresponding bit string (second data) has a sensitivity of 1 or less and 0.95 or more. 0.7 or more, preferably 0.6 or more, and the false positive rate is 0 or more, preferably 0.4 or less, 0.3 or less, or 0.05 or less.

  The analysis result of analyzing the selection frequency of the index parameter concerning the learning model selected by the step of selecting the first learning model and the second learning model having a high evaluation is used to construct the first data and the second data. Can be used to select the index parameter.

  Specifically, when the first learning model and the second learning model are constructed, if an index parameter having a high selection frequency is selected in advance when the first data and the second data are generated, it is necessary to implement the prediction method. Time can be shortened and prediction accuracy can be further improved.

  In addition, a plurality of indices that can further improve the prediction accuracy by analyzing a combination of the adopted index parameters using the bit strings that have been able to build the first learning model and the second learning model that are highly evaluated. A combination of parameters can be found.

  If a combination of a plurality of index parameters found in this way is selected in advance when generating the first data and the second data, the time required to implement the prediction method can be shortened, and the prediction accuracy can be improved. It can be improved further.

Next, a step (S0-5) of determining whether the learning model satisfies a predetermined requirement is performed.
Specifically, a step (S0-5) for determining whether or not the learning models (the first learning model and the second learning model) selected by performing the step (S0-4) satisfy a predetermined requirement. Is done.

  Specifically, in step (S0-5), the first learning model and the second learning model have predetermined requirements, for example, the performance of bit strings, that is, the prediction accuracy of the selected first learning model and second learning model. Is a predetermined prediction accuracy, for example, whether the improvement rate of the prediction accuracy is less than 0.1%, or the number of generations required to update the first learning model and the second learning model (bit string) is an arbitrarily set number of generations A determination is made as to whether an upper limit (eg, 100 generations) is satisfied.

  First, in the step (S0-5), when the selected first learning model and second learning model do not satisfy the predetermined requirements due to the execution of the step (S0-4) (step (S0-5)). In the case of “No” in FIG.

  When the selected first learning model and second learning model (learning model) do not satisfy the predetermined requirements (“No” in step (S0-5)), for example, as a result of the determination in the example, the first When the prediction accuracy of the learning model and the second learning model is less than 0.1% and / or when the number of generations of the first learning model and the second learning model (bit string) does not reach 100 generations), A step (S0-6) of generating a new bit string by performing evolutionary processing on the selected bit string corresponding to the learning model using a genetic algorithm is performed.

  Note that the bit string generation (optimization) step can be performed not only by a genetic algorithm but also by, for example, a search for a combination of all patterns, a random search, or the like.

  Here, the step of optimizing a bit string using a genetic algorithm will be described.

  In the step of optimizing the bit string using the genetic algorithm, the selection of the bit string and the second data including the plurality of selected bit strings (data set) that can construct the learning model having better prediction performance ) Is updated and saved.

(1) First, as already described, based on the evaluation of the learning model by the objective functions O ₁ and O _2, the bit string that can construct the learning model having a higher evaluation, that is, the Pareto rank is higher. Ranking so that

  Specifically, for the bit strings that have already been ranked, for example, rearrange the higher-order bit strings to the upper level, and consider the number of bit strings included in the data set. Edit by excluding from the dataset. Then, the data set (second data) including the updated plurality of bit strings is stored in a state where the bit strings included in the data set can be read.

  Taking the bit string shown in FIG. 6 as an example, bit string BS1 is the most significant bit string, bit string BS2 is the second most significant bit string, and bit string BS3 is the third most significant bit string. .

  (2) Next, the genetic algorithm is used to perform evolutionary processing such as selection, crossover, mutation introduction, and bit string evaluation on the ranked bit strings.

  In the present embodiment, the processing using such a genetic algorithm can be performed using, for example, NSGA-II (Elitist Non-Dominated Sorting Genetic Algorithm). Here, NSGA-II is a non-dominant sort genetic algorithm.

  The processing by such a genetic algorithm is not particularly limited. For example, the number of models per generation is set to 500, the archive size is set to 125, the mutation rate per bit string is set to 10%, and one point crossover is performed up to 80 generations. This can be done as a condition for updating.

  Then, the bit string newly generated by the processing by the genetic algorithm is incorporated into the original second data, updated to the latest second data (data set), and the bit string included in the data set can be read. A process of saving as a state is performed (S0-7).

  Next, using the updated second data, the process returns to the step (S0-1) for preparing the second data including the plurality of bit strings already described, and the steps up to step (S0-5) are performed again. If the step is repeated and the determination result in step (S0-5) is “No”, step (S0-1) to step (S0-1) are repeated until the determination result in step (S0-5) is “Yes”. Steps S0-7) are repeated.

  In this way, a bit string capable of constructing a better learning model is selected, and a data set related to better second data can be held.

  In the process of optimizing a bit string by such a genetic algorithm, selection of variables (index data) is performed simultaneously. Specifically, for example, by comparing the variable used in the second data (bit string) with better results (prediction accuracy) and the variable not used, for example, by comparing the selection frequency of the variables. Evaluate the importance of and select variables that are judged to be highly important.

  By such variable selection, it is possible to effectively extract variables considered to contribute to prediction or narrow down combinations of variables.

  If the determination result in step (S0-5) satisfies the predetermined requirement already described and is “Yes” (the determination accuracy in the above example, the prediction accuracy of the first learning model and the second learning model) Is 0.1% or more and / or the number of generations of the first learning model and the second learning model (bit string) reaches 100 generations), the bit string (second data) The update is completed, and a learning model based on the final bit string is selected as a selection learning model (a first selection learning model and a second selection learning model).

Finally, the first selection learning model and the second selection learning model are stored (S0-8). More specifically, the first selection learning model and the second selection learning model that are finally selected are stored in a readable state. Here, the second data (bit string) that has been updated is stored in a state where it can be read out.
By executing step (S0-8), step (S0) is completed.

  Next, step (S2) will be described with reference to FIG. FIG. 7 is a flowchart for explaining step (S2).

  First, the first data is processed by the first selection learning model and the second selection learning model, and the step of obtaining the first determination result for each of the first selection learning model and the second selection learning model (S2-1) is performed. Is called.

  By this step (S2-1), a plurality of first determination results of each of the plurality of first selection learning models and a plurality of first determination results of the plurality of second selection learning models can be acquired.

  Next, voting is performed for each of the plurality of first determination results of the plurality of first selection learning models and the plurality of first determination results of the plurality of second selection learning models, and the first selection learning model and the second selection learning model. A step of acquiring a second determination result based on the vote rate is performed every time. Hereinafter, this step will be specifically described.

  First, voting is performed for each of the plurality of first determination results of the plurality of first selection learning models and the plurality of first determination results of the plurality of second selection learning models (S2-2).

  Specifically, based on the obtained first determination result, the plurality of first selection learning models vote for “recurring” or “unknown”. The plurality of second selection learning models vote for “no recurrence” or “unknown”. Each voting result is totaled for each of the first selection learning model and the second selection learning model.

  Next, a vote rate is calculated for each of the first selection learning model and the second selection learning model. Next, the vote rate is compared with the cut-off value, and it is determined whether the vote rate is equal to or exceeds the cut-off value (cut-off value ≦ voting rate) (S2-3). Details of the cutoff value will be described later.

  As a result, when the vote rate is equal to or exceeds the set cut-off value (in the case of “Yes” in step (S2-3)), the primary adverse event within a predetermined period for the first selection learning model The second determination result for determining the recurrence of “Yes” is acquired, and for the second selective learning model, the second determination result for determining the recurrence of the main adverse cardiac event within the predetermined period as “No” is acquired. (S2-4).

  When the vote rate is smaller than the set cut-off value (in the case of “No” in step (S2-3)), both the first selection learning model and the second selection learning model are main within a predetermined period. A second determination result with “unknown” as the risk of recurrence of an adverse heart event is acquired (S2-5).

  Here, an example of voting results based on a plurality of first determination results for a plurality of first selection learning models will be described with reference to Table 1.

  Table 1 is a table showing an example of the vote rate and the second determination result according to the first selection learning model. Here, an example in which the second determination result is obtained using four first selection learning models for each of the three first data will be described. In this example, in order to obtain the second determination result, the vote rate when determining that there is a recurrence of the major adverse event within one year as “Yes” is 75% (3/4), that is, the cut-off value is This is an example of 0.75.

  As shown in Table 1, in this example, for the first data (1), since any of the first learning models (1) to (4) determined that the recurrence of the major adverse cardiac event was “Yes”, “Yes” "" Is 100% (4/4) and, as a result, exceeds the set cut-off value (cut-off value≤voting rate), the second determination result is "Yes".

  For the first data (2), the first learning models (1) to (3) are determined to be “present”, and the first learning model (4) is determined to be “unknown”. 75% (3/4), and as a result, the second determination result is “present”.

  For the first data (3), the first learning models (1) to (3) are determined to be “unknown”, and the first learning model (4) is determined to be “present”. Since it is 25% (1/4) and smaller than the set cut-off value (cut-off value> voting rate), the second determination result is “unknown” as a result.

  The example shown in Table 1 is an example related to the first learning model that predicts “Yes” or “Unknown”, and the second determination result related to the second learning model that predicts “None” or “Unknown”. In Table 1, the first learning models (1) to (4) in Table 1 are replaced with the second learning models (1) to (4), and the second determination result is included and “Yes” is inverted to “No”. This can be explained similarly.

  In the prediction method of the present embodiment, voting is performed on the first determination result, and a step of acquiring the second determination result based on the vote rate is performed. In the present embodiment, the prediction accuracy tends to improve as compared to the prediction performance when a single learning model is used as the number of learning models used increases. Further, when the number of learning models reaches a predetermined number, the number of prediction errors tends to increase as the number of learning models increases thereafter.

  This suggests that there is an optimal value for the number of learning models used. Therefore, to improve prediction accuracy (to reduce the number of prediction errors), for example, by observing fluctuations in the number of learning errors and the number of occurrences of prediction errors as the number of learning models increases, By reducing the number of learning models used rather than the number of learning models that have fluctuated in the direction of increasing the number of occurrences, it is possible to improve prediction accuracy (reduce the number of prediction errors). In the present embodiment, in addition to the increase in the number of occurrences of prediction errors, taking into account the equal number of votes for the prediction of “with recurrence” and the prediction of “without recurrence”, the first model of about 40 models at most. It is preferable to use the selective learning model and the second selective learning model, respectively.

  In the present embodiment, the cut-off value can be appropriately adjusted in order to perform prediction more suitable for the purpose. Here, the cut-off value of the vote rate of the first selection learning model and the cut-off value of the vote rate of the second selection learning model can be set to different values.

  In the present embodiment, since the main adverse cardiac event is a target, it is necessary to exclude as many false negatives as possible, that is, cases in which recurrence has occurred despite prediction of no recurrence. Therefore, the cutoff value of the first learning model is made smaller than the cutoff value of the second learning model, that is, the cutoff value of the second learning model is made larger than the cutoff value of the first learning model. By setting to, the false negative rate can be further reduced. In this way, a prediction method more suitable for “exclusion diagnosis” can be achieved.

  Further, by setting the cutoff value of the first learning model to be larger than the cutoff value of the second learning model, the false positive rate can be further reduced. As a result, a prediction method more suitable for “definite diagnosis” can be obtained.

  The cut-off value is appropriately adjusted in view of the seriousness when the prediction result is incorrect.

  In the present embodiment, both of the prediction of the first learning model (with recurrence) and the prediction of the second learning model (without recurrence) are determined by voting. Even if the data is applied, all of them are predicted as “unknown”, and if the cut-off value is too low, there is a possibility that all of them are predicted as “recurring”. In view of the above, in the present embodiment, the cutoff value is preferably set in the range of 0.3 to 0.7.

  In the present embodiment, specifically, the cutoff value of the first learning model is in the range of 0.3 to 0.6, and the cutoff value of the second learning model is in the range of 0.4 to 0.7. This is preferable from the viewpoint of providing a gradient in the acceptance rate of the voting results of the first learning model and the second learning model.

  The evaluation of the cutoff value will be described with reference to FIGS. 8 and 9 are tables for explaining the evaluation result of the cutoff value.

  Here, out of a total of 1231 cases, the number of positive cases (the number of patients who recurred major adverse events within one year) was 100, and the number of negative cases (the major adverse events recurred within one year). An example of using a model in which the number of patients who did not exist is 1131 is shown.

  When the optimum value of the cutoff value of the second learning model was searched for when the cutoff value of the first learning model was set to 0.35, the optimum cutoff value of the second learning model was 0.45. .

  As is apparent from FIGS. 8 and 9, when the cutoff value of the first learning model is set to 0.35 and the cutoff value of the second learning model is set to 0.45 (in FIG. 9, P35_N45). The sensitivity was 0.77, and the specificity was 0.45.

  In FIG. 8, the calculated value in which the case where the prediction result is “unknown” is not counted is shown in the upper part, and the calculated value according to the conventional method is shown in the lower part.

  In FIG. 8, “YY” indicates the number of cases where “the first learning model is determined to be“ recurring ”(Y) and the second learning model is determined to be“ no recurrence ”(Y). , “UU” represents the number of cases where the first learning model is determined as “unknown” (U) and the second learning model is determined as “unknown” (U).

  Next, a step (S2-6) of acquiring a third determination result by integrating the second determination result of the first selection learning model and the second determination result of the second selection learning model is performed.

  By this step (S2-6), the second determination result of the classification problem relating to “there is a major adverse cardiac event reoccurring or unknown within a predetermined period” of the first selection learning model (first learning model), and the second The second determination result concerning the classification problem of “no recurrence of major adverse cardiac events within a predetermined period or unknown” in the selective learning model (second learning model) is integrated. As a result, a third determination result obtained by integrating the second determination result of the first selective learning model and the second determination result of the second selective learning model is acquired.

  Specifically, for example, (1) the second determination result relating to the first selection learning model is “there is a major adverse cardiac event reoccurring”, and the second determination result relating to the second selection learning model is “unknown” In some cases, the third determination result is “reoccurrence of major adverse cardiac event”. (2) When the second determination result concerning the first selective learning model is “unknown” and the second determination result concerning the second selective learning model is “no recurrence of major adverse cardiac events” The third determination result is “no major recurrence of adverse cardiac events”.

  The second determination result related to the first selective learning model is “there is a major adverse heart event recurrence”, and the second determination result related to the second selective learning model is “there is no major adverse heart event recurrence”. And the second determination result concerning the first selection learning model is “unknown” and the second determination result concerning the second selection learning model is also “unknown”, the third determination result is “unknown” "

Next, based on the third determination result, a step (S2-7) of predicting the recurrence risk of the main adverse cardiac event is performed.
Specifically, based on the third determination result obtained in step (S2-6) already described, in the case of (1) above, “the risk of recurrence of a major adverse cardiac event is high within a predetermined period. In the case of (2) above, it is determined that “the risk of recurrence of major adverse cardiac events is low within a predetermined period”, and in cases other than (1) and (2) above, Determination of the risk of recurrence of major adverse cardiac events within the period is pending.

  As already described, this step (S2-7) is usually performed by a computer. However, the prediction of recurrence risk based on the third determination result, the determination of the frequency of visit based on the prediction of recurrence risk, etc., for example, may be processing according to a rule definition file or algorithm based on knowledge of doctors, consultants, etc. it can.

  The step (S2-8) of calculating the reliability of the predicted relapse risk can be performed based on the second determination result already described.

  Specifically, first, in acquiring the second determination result, for example, when a plurality of learning models determines that “there is recurrence”, “+1” points, and when “no recurrence” is determined, “−” If it is determined as “1” or “unknown”, “0” is given, and the sum of scores for all models for the same subject is calculated. The ratio of the total score of “no recurrence” is calculated as the reliability (%).

  The calculated reliability (%) values range from -100 (%) (the risk of recurrence of major adverse events is low) to 100 (%) (the risk of recurrence of major adverse events is high). Can take a value.

  As described above based on past cases, the reliability (%) is calculated by associating the analysis by machine learning and the recurrence frequency in the data used for learning, so it is suitable as an index of reliability. It is.

[Prediction device]
The prediction method of the present embodiment, that is, the steps (S1) and (S2) are usually executed by a computer including a calculation unit. Hereinafter, with reference to FIG. 10 and FIG. 11, a configuration of the computer 10 that is a prediction device that can be suitably used in the present embodiment will be described.

  FIG. 10 is a schematic block diagram for explaining the configuration of the computer. FIG. 11 is a schematic block diagram for explaining the configuration of the calculation unit.

  As shown in FIG. 10, the computer 10 includes an arithmetic unit 12 that processes instructions such as generating data based on the acquired parameters and storing the data.

  The calculation unit 12 is a functional unit corresponding to, for example, a microprocessor (CPU), a graphic processor (GPU), or the like.

  The computer 10 further includes a storage unit 14 that can store input data, generated data, and the like temporarily or for a predetermined period and store them in a readable state.

  The storage unit 14 corresponds to, for example, a memory (RAM) device, a hard disk drive, an SSD, and the like, and is a functional unit configured to cooperate with the calculation unit 12.

  Examples of data that can be stored and stored in the storage unit 14 in a readable state include first data, second data (complete data, partial data, updated bit string data set), evaluation data, Examples include a support vector machine, a first learning model, a second learning model, a first selection learning model, and a second selection learning model.

  The computer 10 further includes external functional units and functional units such as an input / output unit 16 that is an interface such as serial connection and parallel connection for exchanging data with the device.

  In addition, the computer 10 outputs data generated on an input device 22 such as a keyboard and a mouse, a display device capable of visually displaying data, a paper medium, and the like, which functions when connected to the input / output unit 16. The computer 10 includes a so-called computer hardware resource such as a printer capable of reading and writing, a large-capacity external storage device 32 that can read and write, or a dedicated hardware resource corresponding to each of these components. It can also be set as the structure connected so that it may cooperate with a function part.

  Specifically, for example, the external storage device that stores the database for the first data and the database for the second data that have already been described, or the hardware resource that stores the first data as the database and the second data as the database The hardware resources to be stored are configured as separate external storage devices, installed in remote locations that are physically separated from the computer installation locations described above, and can cooperate with each other by electric communication lines. You may comprise so that it may connect to.

  Here, “connected by telecommunication line” means connected by connecting data, control signals, etc. via a wired or wireless information line using a medium such as electricity or light. This means that the devices are configured to work together.

  Even if the prediction device for carrying out the prediction method of the present embodiment is composed of a single computer, a plurality of computers (including servers, operation terminals, etc.) and other peripheral devices are integrated by an electric communication line. It may be configured as a system connected to.

  In addition, among the processes described in the above-described embodiments, all or part of the processes described as being automatically performed can be manually performed, or all of the processes described as being performed manually are performed. Alternatively, a part can be automatically performed by a known method. In addition, the processing procedures, control procedures, specific names, various data, information including parameters, screen examples, and database configurations shown in the above description and drawings may be arbitrarily changed unless otherwise specified. it can.

  The prediction device of this embodiment is a prediction device that predicts the recurrence risk of a major adverse cardiac event within a predetermined period.

  More specifically, the prediction apparatus is an index parameter measured using a test sample collected from a subject or obtained from a subject, and includes C-reactive protein amount, D-dimer amount, HDL- Cholesterol level, LDL-cholesterol level, prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level Amount, glycohemoglobin amount, crawl amount, triglyceride amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level Monocyte count, direct bilirubin level, lactate dehydrogenase (LDH) level, uric acid level, pH, potassium level, calcium level, sodium level, red blood cell count, hematocrit level, hemoglobin level, lymphocyte count, platelet count, basophil Count, eosinophil count, neutrophil count, sex, history of diabetes, history of hypertension, history of dyslipidemia, smoking habits, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) ) History of angina pectoris, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis Based on two or more index parameters selected based on the selection frequency from the group consisting of age, height, weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and oncology Generate 1 data A first data generation / acquisition unit to be obtained and the first data acquired by the first data generation / acquisition unit are processed by a learning model constructed based on a data group including a plurality of second data, and within a predetermined period A predictor for predicting the risk of recurrence of major adverse cardiac events.

  As illustrated in FIG. 11, the prediction device 100 of the present embodiment includes a plurality of functional units that function in cooperation with each other in the arithmetic unit 12 that has already been described. The prediction device 100 of the present embodiment includes a first data generation acquisition unit 12a, a second data generation acquisition unit 12b, a learning model construction unit 12d, a learning model selection unit 12e, a first determination result generation acquisition unit 12f, and a second determination result. A generation acquisition unit 12g, a third determination result generation acquisition unit 12h, and a prediction unit 12i are provided.

  The prediction apparatus 100 according to an embodiment of the present invention acquires two or more index parameters measured using a test sample collected from a subject or obtained from a subject, and performs a first measurement based on the index parameter. The first data generation / acquisition unit 12a that generates and acquires one data and the first data acquired by the first data generation / acquisition unit 12a are processed by the first selection learning model and the second selection learning model, and the first data A first determination result generation acquisition unit 12f that generates and acquires a first determination result for each of the selection learning model and the second selection learning model, and a plurality of first selection learning models acquired by the first determination result generation acquisition unit 12f. Based on a plurality of first determination results and a plurality of first determination results of a plurality of second selection learning models, a second determination result generation acquisition unit 12g that generates and acquires a second determination result, and a second determination result generation Acquisition department A third determination result generation acquisition unit 12h that generates and acquires a third determination result by integrating the second determination result of the first selection learning model acquired by 2g and the second determination result of the second selection learning model; And a prediction unit 12i that predicts the recurrence risk of the main adverse heart event based on the third determination result acquired by the third determination result generation acquisition unit 12h.

  The prediction apparatus 100 according to another embodiment includes two or more types selected from the group consisting of a plurality of index parameters for a plurality of subjects who have recurred or did not recur a major adverse cardiac event within a predetermined period. Based on the second data acquired from the second data generation / acquisition unit 12b that generates and acquires the second data based on the index parameter, the presence or absence of the recurrence of the major adverse heart event is determined. A plurality of first learning models to be predicted and a plurality of second learning models to predict whether there is no recurrence or unknown of the major adverse heart event, and a plurality of first models constructed by the learning model building unit 12d A learning model selection unit 12e that selects a plurality of first selection learning models and a plurality of second selection learning models for each learning model and a plurality of second learning models. It is preferable to include in La.

  In the prediction device 100 of yet another embodiment, the second data generation / acquisition unit 12b selects a plurality of index parameters and generates partial data, thereby generating a plurality of partial data and partial data. It is preferable that it is a function part which produces | generates the 2nd data which may contain the used complete data (case data).

  In the prediction apparatus 100 according to yet another embodiment, the learning model construction unit 12d divides the second data acquired from the second data generation acquisition unit 12b into a plurality of data groups, and each of the data groups is teacher data. And a functional unit that constructs a plurality of first learning models and a plurality of second learning models by machine learning performed under a plurality of parameter conditions that differ for each of the plurality of data groups.

  In the prediction apparatus 100 according to another embodiment, the second determination result generation acquisition unit 12g includes a plurality of first determination results of the plurality of first selection learning models and a plurality of first of the plurality of second selection learning models. It is preferable that the function unit performs voting on the determination result, and generates and acquires the second determination result based on the vote rate for each of the first selection learning model and the second selection learning model.

[Program and storage medium on which the program is recorded]
The present invention also relates to a program for executing the prediction method of the present embodiment described above and a storage medium on which the program is recorded.

  Here, the “program” is a data processing method described in an arbitrary language or description method, and may be in any format such as source code or binary code. The “program” is not necessarily limited to a single configuration, and may be distributed as a plurality of modules and libraries, and cooperates with a separate program represented by an OS (Operating System). Including those that achieve their functions.

  Note that the program is normally recorded on a recording medium according to the storage unit 14 already described, and is read by a computer that performs the prediction method as necessary. As a specific configuration for reading a program recorded in a recording medium by each device, a reading procedure, an installation procedure after reading, and the like, a well-known configuration and procedure can be used.

  The “recording medium” includes any “portable physical medium”, any “fixed physical medium”, and “communication medium”. The “portable physical medium” is a flexible disk, a magneto-optical disk, a ROM, an EPROM, an EEPROM, a CD-ROM, an MO, a DVD, or the like. The “fixed physical medium” is a ROM, a RAM, a hard disk drive or the like built in various computer systems. The “communication medium” holds the program for a short period of time like a communication line or a carrier wave in the case of transmitting the program via a network such as a LAN, WAN, or the Internet.

  A program according to an embodiment of the present invention is a program for predicting a recurrence risk of a major adverse cardiac event within a predetermined period, including the following steps executed by a computer 10 including a calculation unit 12. 12 is an index parameter measured using a test sample collected from the subject or obtained from the subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the amount of LDL-cholesterol , Prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level, glycohemoglobin level, crawl Amount, triglyceres Level, fibrinogen level, fibrin / fibrinogen degradation product level, activated partial thromboplastin time, serum creatinine level, blood urea nitrogen level, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct bilirubin level, lactate dehydration Elementary enzyme (LDH) level, uric acid level, pH, potassium level, calcium level, sodium level, red blood cell count, hematocrit level, hemoglobin level, lymphocyte count, platelet count, basophil count, eosinophil count, neutrophil Number, sex, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking, presence of anemia, history of acute myocardial infarction, history of angina requiring coronary angioplasty (PCI) History, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, year First based on two or more index parameters selected from the group consisting of age, height, weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and oncology at the time of hospitalization The step of acquiring data, and the calculating part 12 process the 1st data with the learning model constructed | assembled based on the data group containing several 2nd data, and the step which estimates a recurrence risk.

  In the program according to another embodiment of the present invention, the second data is data including a history of recurrence of major adverse cardiac events within a predetermined period as an index parameter, and the second data is C-reactive protein amount, D Dimer amount, HDL-cholesterol amount, LDL-cholesterol amount, prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase amount, aspartate aminotransferase amount, amylase amount, alanine aminotransferase amount, alkaline phosphatase amount, Albumin level, antithrombin level, glycohemoglobin level, chlor level, triglyceride level, fibrinogen level, fibrin / fibrinogen degradation product level, activated partial thromboplastin time, serum creatinine level, blood urea nitrogen level, blood glucose level Total cholesterol level, total bilbilin level, monocyte count, direct bilirubin level, lactate dehydrogenase (LDH) level, uric acid level, pH, potassium level, calcium level, sodium level, red blood cell count, hematocrit level, hemoglobin level, lymphocytes Count, platelet count, basophil count, eosinophil count, neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, smoking habit, presence of anemia, acute myocardial infarction Medical history, history of angina pectoris requiring coronary angioplasty (PCI), history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease One or more indicators selected from the group consisting of: history of aortic dissection, dialysis, age, height, weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), hospitalization reason and on-hospital disease Based on parameters It is preferable that the data.

  In a program according to another embodiment of the present invention, it is preferable that the first data and the second data are data based on an index parameter selected from a group further including an index parameter derived from a myocardial marker.

  In another embodiment of the present invention, the myocardial marker is creatine kinase MB, human cardiac fatty acid binding protein, cardiac troponin I, cardiac troponin T, brain natriuretic peptide, pro-brain natriuretic peptide or its cleavage. 1 selected from the group consisting of product, myeloperoxidase, placental growth factor, estimated glomerular filtration rate, homocysteine, ischemia modified albumin, soluble CD40 ligand, lipoprotein-related phospholipase A2, choline, and sensitive C-reactive protein It is preferable that it is a seed or more.

  In a program according to still another embodiment of the present invention, the first data and the second data are preferably data based on an index parameter selected from a group further including an index parameter derived from an electrocardiogram.

  In the program according to still another embodiment of the present invention, the index parameter derived from the electrocardiogram includes P wave height, R wave interval, PQ time, R wave height, QRS width, and ST portion change amount. The height of the T wave and the power spectrum obtained by Fourier transforming the electrocardiogram are preferably selected.

  In a program according to still another embodiment of the present invention, the test sample is preferably blood or a blood-derived sample.

  In a program of yet another embodiment of the invention, the major adverse cardiac event is acute myocardial infarction, angina with coronary revascularization, heart failure requiring hospitalization, atrial fibrillation, stroke, or circulation Preferably, the death is due to a vessel.

  In a program according to still another embodiment of the present invention, the step of predicting the recurrence risk of a major adverse cardiac event divides the second data into a plurality of data groups, and each of the data groups is used as teacher data. And a plurality of first learning models for predicting whether a major adverse cardiac event is recurring or unknown by machine learning performed under a plurality of different parameter conditions for each of the plurality of data groups, and Further comprising the step of constructing a plurality of second learning models for predicting whether there is no recurrence or unknown, wherein the first data is processed by the first learning model and the second learning model and within a predetermined period Preferably, the step is predicting the risk of recurrence of a major adverse cardiac event.

  In a program according to another embodiment of the present invention, the step of predicting the risk of recurrence of a major adverse cardiac event is performed with sensitivity and positive predictive value for each of a plurality of first learning models and a plurality of second learning models. A step of selecting a plurality of first selection learning models and a plurality of second selection learning models based on the first data, and processing the first data by the first selection learning model and the second selection learning model within a predetermined period Preferably, the step is predicting the recurrence risk of major adverse heart events in

  In a program according to still another embodiment of the present invention, the step of predicting the risk of recurrence of a major adverse cardiac event processes the first data using a first selection learning model and a second selection learning model, The first determination result is acquired for each of the selection learning model and the second selection learning model, the first determination result is voted, and the second determination result based on the vote rate for each of the first selection learning model and the second selection learning model. , The second determination result of the first selection learning model and the second determination result of the second selection learning model are integrated to acquire a third determination result, and within a predetermined period based on the third determination result Preferably, the step is predicting the recurrence risk of major adverse heart events in

〔Example〕
Examples are given below to explain the present invention in detail. The present invention is not limited to the following examples.

<Example 1> (Data preparation and learning model construction)
(1) Collection of subjects and index parameters During the period from September 20, 2012 to November 28, 2014, acute myocardial infarction (AMI) and coronary angioplasty (PCI) within 48 hours of onset were required. 2273 patients hospitalized because of angina pectoris (AP), heart failure (HF), atrial fibrillation (AF) requiring ablation treatment, or cerebral infarction (CI) did.

  Predictive goal by defining any occurrence of cardiovascular disease, cardiovascular infarction (mi), stroke (stroke), or heart failure (hf) as a recurrence of MACE until 365 days after admission Was the presence or absence of recurrence of MACE.

  For the subject, index parameters were collected to construct first data. The index parameters used are shown in Tables 2-1 and 2-2 below.

  The subject group (corresponding first data group) was divided into two groups before and after October 1, 2013 on the basis of the hospitalization date of the subject. Specifically, 1659 cases whose hospital admission date is before September 30, 2013 are taken as a data group for development of a learning model (development cohort), and 614 patients whose hospital admission date is after October 1, 2013 are used for evaluation. Data group (validation cohort).

  As a result, 102 cases in the learning model construction data group and 56 cases in the evaluation data group corresponded to “with recurrence”.

(2) Generation of partial data First, the data group for constructing the learning model in (1) was further divided into two data groups, a first divided data group and a second divided data group. Here, the division is performed so that the ratio of the number of data included in the first divided data group and the second divided data group (evaluation data group) is first divided data group: second divided data group = 6: 4. did.

  Next, partial data of 400 patterns was randomly generated using the first divided data group.

The generation of partial data was performed as follows.
(I) A part (column) of the index parameter is deleted from the data (complete data) belonging to the first divided data group. Note that the index parameters for the ID and the presence or absence of recurrence of MACE within the period were maintained in all partial data.
(Ii) Next, a part (row) of the case data was further deleted from the data from which a part of the index parameter was deleted.
(Iii) A plurality of different partial data were generated by repeating the process (i) and the process (ii). The combination of index parameters and the combination of case data in the partial data were described as bit strings and managed as one-dimensional information. The obtained partial data was included in the original first divided data group to obtain second data.

(3) Construction of learning model by machine learning A plurality of learning models were constructed by performing machine learning using the obtained second data as teacher data. SVM (e1071 package) was used for machine learning, and an RBF kernel was used as a kernel function. The parameter γ for adjusting the complexity of the identification boundary line was set to 0.01. The soft margin allowable parameter C in the SVM is fixed at 100. As a result, a total of 400 learning models were constructed.

(4) Evaluation of prediction performance by constructed learning model Using the second divided data group of (2) above, the prediction results of all learning models were evaluated. The prediction results of each learning model were evaluated by Pareto rank. Specifically, the evaluation values (O ₁ , 1 / O ₂ ) based on the objective functions O ₁ and O ₂ described above are obtained, and based on the evaluation values, the Pareto rank with the sensitivity and the positive median as indexes. The learning model was evaluated.

(5) Selection of learning model (selected learning model) Based on the obtained evaluation results, a learning model having a smaller evaluation value (O ₁ , 1 / O ₂ ), that is, a higher sensitivity and a positive predictive value. Selected as a selection learning model. Specifically, a learning model having a sensitivity of 0.7 or more and a positive predictive value of 0.7 or more was selected as a selection learning model. As a result, a total of 40 selection learning models were selected.

  In addition, a total of 40 second data (bit strings) for which a selection learning model could be constructed was selected.

(6) Optimization of the second data using the genetic algorithm The second data was optimized and updated by the method already described using a non-dominant sort genetic algorithm (NSGA). Specifically, the bit string (group) selected in (5) above is the first generation, the number of models per generation is 400, the archive size is 40, and the mutation rate per bit string is 10%. The mutation was introduced by crossing at one point. This was repeated over 5 generations, and a learning model with better prediction accuracy could be constructed, that is, a bit string (second data) with good results was obtained.

<Example 2> (Prediction of recurrence of MACE)
As described above, recurrence of MACE was predicted using the selective learning model constructed in Example 1 and the evaluation data group.
Based on the obtained prediction results, the risk of recurrence for one year was stratified. The results are shown in FIG. FIG. 12 is a graph showing the results of stratification of the evaluation data group (Original: dotted line) into a MACE high risk group (High: black line) and a low risk group (Low: gray line).

  As a result, the evaluation data group (original) (n = 614 with 56 observations, 9.1%) was replaced with the high risk group (High) (51 out of n = 247, 20.6%) and the low risk group. It was possible to divide into two groups of groups (Low) (5 out of n = 367, 1.4%).

  As shown in FIG. 12, in these two groups, the rate of recurrence of MACE (a) and the cumulative survival rate (b) up to 1 year later, the rate of recurrence of MACE in the data group for evaluation and 1 year There was a significant difference compared to the cumulative survival rate until later.

<Example 3> (Evaluation of prediction performance)
Predictive performance when an evaluation data group was used was evaluated by AUC analysis. The results are shown in FIG. FIG. 13A is a graph showing the prediction performance.
As shown in FIG. 13A, the prediction performance was AUC = 0.653 (95% CI = 0.816−0.890).
The sensitivity under the condition where the specificity was fixed at 0.9 was 0.672 (95% CI = 0.595-0.762).

<Comparative example 1> (Evaluation of prediction performance)
The prediction performance in the case of using a data group for evaluation was evaluated by regression analysis using a conventionally used Cox proportional hazard model. It shows to FIG.13 (b), (c) and (d). FIGS. 13B, 13C, and 13D are graphs showing prediction performance by a conventionally used method.

As shown in FIG. 13B, the prediction performance was AUC = 0.919 (95% CI = 0.768-0.869).
Further, as shown in FIG. 13C, in GRACE score, AUC = 0.609 (95% CI = 0.562-0.656).
Furthermore, as shown in FIG. 13 (d), AUC = 0.535 (95% CI = 0.488-0.582) in the Framingham risk score.
Thus, the above results according to Comparative Example 1 were all inferior to the results of Example 3.

In addition, when the conventional Cox proportional hazard model was used, the sensitivity under the condition where the specificity was fixed at 0.9 was 0.393 (95% CI = 0.250−0.536).
Thus, the sensitivity according to Comparative Example 1 was inferior to the sensitivity of Example 3.

<Example 4> (Evaluation of importance of index parameter)
The importance of the index data was evaluated by comparing the selection frequency of the index parameters adopted by the good bit string (second data) obtained by (6) above.
The results are shown in FIG. FIG. 14 is a graph showing the selection frequency based on the ratio of selection learning models in which a certain index parameter is used in the entire selection learning model. The vertical axis indicates the index parameter, and the horizontal axis indicates the selection frequency. A variable with a higher selection frequency is considered more important for prediction.

DESCRIPTION OF SYMBOLS 10 Computer 12 Calculation part 12a 1st data generation acquisition part 12b 2nd data generation acquisition part 12d Learning model construction part 12e Learning model selection part 12f 1st determination result generation acquisition part 12g 2nd determination result generation acquisition part 12h 3rd determination result Generation acquisition unit 12i Prediction unit 14 Storage unit 16 Input / output unit 22 Input device 32 External storage device 100 Prediction device

Claims (14)

An index parameter measured using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the amount of LDL-cholesterol, the prothrombin time (International standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level, glycohemoglobin level, crawl level, triglyceride level Amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct bilirubin level, Acid dehydrogenase (LDH) level, uric acid level, pH, potassium level, calcium level, sodium level, red blood cell count, hematocrit level, hemoglobin level, lymphocyte count, platelet count, basophil count, eosinophil count, favorable Anemia requiring neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, smoking habit, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of heart failure, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, weight, heart rate Obtaining first data based on two or more index parameters selected based on the frequency of selection from the group consisting of number, urinary protein (qualitative), urine sugar (qualitative), hospitalization reason and on-hospital manifestation; and
Processing the first data with a learning model constructed based on the second data to predict a recurrence risk, a prediction method for a recurrence risk of a major adverse cardiac event within a predetermined period.   The second data is data including the history of recurrence of major adverse cardiac events within a predetermined period as an index parameter, and the second data includes C-reactive protein amount, D-dimer amount, HDL-cholesterol amount, LDL-cholesterol. Amount, prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase amount, aspartate aminotransferase amount, amylase amount, alanine aminotransferase amount, alkaline phosphatase amount, albumin amount, antithrombin amount, glycohemoglobin amount, Amount of crawl, amount of triglyceride, amount of fibrinogen, amount of fibrin / fibrinogen degradation product, activated partial thromboplastin time, amount of serum creatinine, amount of blood urea nitrogen, blood glucose level, total cholesterol level, total bilbilin level, monocyte count Direct bilirubin content, lactate dehydrogenase (LDH) content, uric acid content, pH, potassium content, calcium content, sodium content, red blood cell count, hematocrit value, hemoglobin content, lymphocyte count, platelet count, basophil count, eosinic acid Requires sphere count, neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, smoking habit, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of angina pectoris, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height The data based on one or more index parameters further selected from the group consisting of: body weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and on-hospital disease. Within the prescribed period of Of predicting the risk of recurrence of major adverse cardiac events in Japan.   The major adverse cardiac event within a predetermined period according to claim 1 or 2, wherein the first data and the second data are data based on an index parameter selected from a group further including an index parameter derived from a myocardial marker. Of predicting the risk of recurrence.   The myocardial marker is creatine kinase MB, human cardiac fatty acid binding protein, cardiac troponin I, cardiac troponin T, brain natriuretic peptide, pro-brain natriuretic peptide or its cleavage product, myeloperoxidase, placental growth factor, estimated glomerular filtration 4. The predetermined period according to claim 3, which is at least one selected from the group consisting of an amount, homocysteine, ischemic modified albumin, soluble CD40 ligand, lipoprotein-related phospholipase A2, choline, and high-sensitivity C-reactive protein. For predicting the risk of recurrence of major adverse cardiac events   The method for predicting the risk of recurrence of a major adverse cardiac event within a predetermined period according to any one of claims 1 to 4, wherein the test sample is blood or a blood-derived sample.   The major adverse cardiac event is acute myocardial infarction, angina with coronary revascularization, heart failure requiring hospitalization, atrial fibrillation, stroke, or death due to cardiovascular disease. 6. The method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period according to any one of 5 above. The learning model is constructed by machine learning performed by dividing the second data into a plurality of data groups, using each of the data groups as teacher data, and performing a plurality of parameter conditions different for each of the plurality of data groups. A plurality of first learning models for predicting whether a major adverse cardiac event is recurring or unknown, and a plurality of second learning models for predicting whether a major adverse cardiac event is recurrent or unknown. Yes,
The step of predicting the recurrence risk of the major adverse cardiac event is a step of processing the first data by the first learning model and the second learning model to predict a recurrence risk. The prediction method of the recurrence risk of the main adverse heart event within the predetermined period of any one of 1. A plurality of first selection learning models, and a plurality of second selection learning, wherein the learning model is selected based on sensitivity and positive predictive value for each of the plurality of first learning models and the plurality of second learning models. Model
The step of predicting the recurrence risk of the major adverse event is a step of processing the first data by the first selective learning model and the second selective learning model to predict a recurrence risk. A method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period as described in.   The step of predicting the recurrence risk of the major adverse cardiac event includes processing the first data by the first selective learning model and the second selective learning model, and the first selective learning model and the second selective learning model. A first determination result is obtained for each, a vote is performed on the first determination result, a second determination result based on a vote rate is obtained for each of the first selection learning model and the second selection learning model, and the first The second determination result of the selective learning model and the second determination result of the second selective learning model are integrated to obtain a third determination result. Based on the third determination result, the risk of recurrence of major adverse cardiac events The method for predicting the risk of recurrence of major adverse cardiac events within a predetermined period according to claim 8, wherein A program for predicting the risk of recurrence of major adverse cardiac events within a predetermined period, including the following steps executed by a computer having a calculation unit,
The calculation unit is an index parameter measured by using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the LDL-cholesterol Amount, prothrombin time (international standard ratio (INR)), γ-glutamyl transpeptidase amount, aspartate aminotransferase amount, amylase amount, alanine aminotransferase amount, alkaline phosphatase amount, albumin amount, antithrombin amount, glycohemoglobin amount, Amount of crawl, amount of triglyceride, amount of fibrinogen, amount of fibrin / fibrinogen degradation product, activated partial thromboplastin time, amount of serum creatinine, amount of blood urea nitrogen, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct biliary count Bin volume, lactate dehydrogenase (LDH) volume, uric acid volume, pH, potassium volume, calcium volume, sodium volume, red blood cell count, hematocrit level, hemoglobin volume, lymphocyte count, platelet count, basophil count, eosinophil Number, neutrophil count, sex, history of diabetes, history of hypertension, history of dyslipidemia, presence of smoking, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of angina pectoris, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, Obtain first data based on two or more index parameters selected from the group consisting of weight, heart rate, urinary protein (qualitative), urine sugar (qualitative), reason for hospitalization, and on-hospital disease, based on selection frequency Steps,
The calculation unit includes a step of processing the first data with a learning model constructed based on the second data to predict a recurrence risk of a major adverse cardiac event within a predetermined period. The learning model is constructed by machine learning performed by dividing the second data into a plurality of data groups, using each of the data groups as teacher data, and performing a plurality of parameter conditions different for each of the plurality of data groups. A plurality of first learning models for predicting whether a major adverse cardiac event is recurring or unknown, and a plurality of second learning models for predicting whether a major adverse cardiac event is recurrent or unknown. Yes,
The step of predicting the risk of recurrence of the major adverse event is that the calculation unit processes the first data by the first learning model and the second learning model to determine the major adverse event within a predetermined period. The program according to claim 10, which is a step of predicting a recurrence risk. A plurality of first selection learning models, and a plurality of second selection learning, wherein the learning model is selected based on sensitivity and positive predictive value for each of the plurality of first learning models and the plurality of second learning models. Model
The step of predicting the risk of recurrence of the major adverse heart event is such that the calculation unit processes the first data by the first selective learning model and the second selective learning model, and the major adverse heart in a predetermined period. The program according to claim 11, which is a step of predicting a recurrence risk of an event.   The step of predicting the recurrence risk of the major adverse cardiac event is such that the calculation unit processes the first data by the first selection learning model and the second selection learning model, and the first selection learning model and the The first determination result is acquired for each second selection learning model, the first determination result is voted, and the second determination result based on the vote rate is acquired for each of the first selection learning model and the second selection learning model. Then, the second determination result of the first selection learning model and the second determination result of the second selection learning model are integrated to obtain a third determination result, and based on the third determination result, a predetermined period of time is obtained. The program according to claim 12, which is a step of predicting a risk of recurrence of a major adverse cardiac event in the brain. An index parameter measured using a test sample collected from a subject or obtained from a subject, the amount of C-reactive protein, the amount of D-dimer, the amount of HDL-cholesterol, the amount of LDL-cholesterol, the prothrombin time (International standard ratio (INR)), γ-glutamyl transpeptidase level, aspartate aminotransferase level, amylase level, alanine aminotransferase level, alkaline phosphatase level, albumin level, antithrombin level, glycohemoglobin level, crawl level, triglyceride level Amount, fibrinogen amount, fibrin / fibrinogen degradation product amount, activated partial thromboplastin time, serum creatinine amount, blood urea nitrogen amount, blood glucose level, total cholesterol level, total bilbilin level, monocyte count, direct bilirubin level, Acid dehydrogenase (LDH) level, uric acid level, pH, potassium level, calcium level, sodium level, red blood cell count, hematocrit level, hemoglobin level, lymphocyte count, platelet count, basophil count, eosinophil count, favorable Anemia requiring neutrophil count, gender, history of diabetes, history of hypertension, history of dyslipidemia, smoking habit, presence of anemia, history of acute myocardial infarction, coronary angioplasty (PCI) History of heart failure, history of heart failure, history of atrial fibrillation requiring ablation treatment, history of cerebral infarction, history of peripheral arterial disease, history of aortic dissection, dialysis, age, height, weight, heart rate Generate and obtain first data based on two or more index parameters selected based on the frequency of selection from the group consisting of number, urine protein (qualitative), urine sugar (qualitative), reason for hospitalization, and oncology A first data generation and acquisition unit; ,
A prediction unit that processes the first data acquired by the first data generation acquisition unit with a learning model constructed based on the second data, and predicts a recurrence risk of a major adverse cardiac event within a predetermined period. , A prediction device for the risk of recurrence of major adverse cardiac events within a given period.