CN117153380A - Method, system and equipment for predicting postoperative acute kidney injury of non-cardiac surgery patient - Google Patents
Method, system and equipment for predicting postoperative acute kidney injury of non-cardiac surgery patient Download PDFInfo
- Publication number
- CN117153380A CN117153380A CN202311432939.0A CN202311432939A CN117153380A CN 117153380 A CN117153380 A CN 117153380A CN 202311432939 A CN202311432939 A CN 202311432939A CN 117153380 A CN117153380 A CN 117153380A
- Authority
- CN
- China
- Prior art keywords
- risk
- patient
- kidney injury
- acute kidney
- total score
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 201000011040 acute kidney failure Diseases 0.000 title claims abstract description 125
- 208000009304 Acute Kidney Injury Diseases 0.000 title claims abstract description 102
- 208000033626 Renal failure acute Diseases 0.000 title claims abstract description 102
- 230000002980 postoperative effect Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000007675 cardiac surgery Methods 0.000 title claims abstract description 19
- 230000000747 cardiac effect Effects 0.000 claims abstract description 16
- 206010012601 diabetes mellitus Diseases 0.000 claims description 24
- 201000001474 proteinuria Diseases 0.000 claims description 17
- 238000010801 machine learning Methods 0.000 claims description 16
- 102000001554 Hemoglobins Human genes 0.000 claims description 14
- 108010054147 Hemoglobins Proteins 0.000 claims description 14
- 230000024924 glomerular filtration Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 claims description 11
- 230000036454 renin-angiotensin system Effects 0.000 claims description 11
- 229910052708 sodium Inorganic materials 0.000 claims description 11
- 239000011734 sodium Substances 0.000 claims description 11
- 102000009027 Albumins Human genes 0.000 claims description 10
- 108010088751 Albumins Proteins 0.000 claims description 10
- 210000004369 blood Anatomy 0.000 claims description 10
- 239000008280 blood Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000001356 surgical procedure Methods 0.000 claims description 8
- 206010053159 Organ failure Diseases 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 210000000056 organ Anatomy 0.000 claims description 5
- 230000004768 organ dysfunction Effects 0.000 claims description 5
- 206010019280 Heart failures Diseases 0.000 claims description 3
- 206010020772 Hypertension Diseases 0.000 claims description 3
- 208000006011 Stroke Diseases 0.000 claims description 3
- 208000026106 cerebrovascular disease Diseases 0.000 claims description 3
- 208000020832 chronic kidney disease Diseases 0.000 claims description 3
- 208000029078 coronary artery disease Diseases 0.000 claims description 3
- 208000014674 injury Diseases 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 230000008733 trauma Effects 0.000 claims description 3
- 238000002297 emergency surgery Methods 0.000 claims description 2
- 238000007477 logistic regression Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 8
- 206010001580 Albuminuria Diseases 0.000 description 4
- 208000007502 anemia Diseases 0.000 description 4
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 229940109239 creatinine Drugs 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 210000002966 serum Anatomy 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 208000037157 Azotemia Diseases 0.000 description 1
- 208000003623 Hypoalbuminemia Diseases 0.000 description 1
- 206010021036 Hyponatraemia Diseases 0.000 description 1
- 208000034767 Hypoproteinaemia Diseases 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 208000035850 clinical syndrome Diseases 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 238000010837 poor prognosis Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009256 replacement therapy Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Surgery (AREA)
- Urology & Nephrology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application provides a prediction method, a prediction system, prediction equipment, prediction media and prediction program products for acute kidney injury of a non-cardiac operation patient after operation, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring clinical information of a non-cardiac surgery patient; classifying patients into high-risk patients and non-high-risk patients based on the clinical information; when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score; when the patient is a non-high risk patient, inputting clinical information of the non-high risk patient into a non-high risk patient postoperative acute kidney injury prediction model, and dividing the non-high risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
Description
Technical Field
The present application relates to the field of intelligent medical technology, and more particularly, to a method, system, device, medium and program product for predicting acute kidney injury in patients with non-cardiac surgery after surgery.
Background
Acute kidney injury (Acute Kidney Injury, AKI) is an important clinical syndrome, meaning sudden (within 1-7 d) and sustained (> 24 h) sudden decline in kidney function, defined as an increase in serum creatinine (SCr) of at least 0.5mg/dl, manifested as azotemia, aqueous electrolyte and acid-base balance, and systemic symptoms, with little (< 400ml/24h or 17 ml/h) or no urine (< 100 ml/24 h). AKI occurs at about 20% in hospitalized patients, while in patients undergoing non-cardiac surgery its incidence varies from 6.8% to 37% depending on the disease characteristics of the patient and the surgery, with the occurrence of AKI being associated with poor prognosis for both near and distant patients. There is currently no therapeutic measure specific to AKI, so early identification of patients at high risk for AKI based on predictive models is critical.
The reduced post-operative AKI risk (Simple Postoperative AKI Risk, SPARK) index is the model currently modeled with the largest sample size incorporated, AKI defining the most standard for non-cardiac surgery, and externally validated. However, upon further external validation of the SPARK index, it was found that the SPARK index was not ideal for predicting post-operative AKI in elderly, more complicated patients, and that this group had a very high risk of post-operative AKI. Furthermore, the SPARK index is externally verified by adopting a high risk group with advanced age and more complications, and the discrimination AUC of the SPARK index for the postoperative AKI is only 0.67.
In addition, post-operative acute kidney injury (PO-AKI) is defined as an increase in serum creatinine of at least 0.3 mg/dL or 150% over 48 hours, or an increase in urine volume of less than 0.5 mL/kg/h over 1 week after surgery, as well as severe AKI, defined as AKI grade 2 or more and/or any AKI associated with post-operative death or the need for kidney replacement therapy prior to discharge, in which study the incidence of PO-AKI increases with an increase in the surk index score. However, in the elderly patient cohort with more co-morbidities, the accuracy of the predictive probability remains to be appreciated.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a prediction method of acute kidney injury of a non-heart operation patient after operation; according to clinical needs, whether the patient is a high-risk patient or not is judged firstly, and then the probability of postoperative acute kidney injury of the patient is respectively predicted according to the type of the patient, so that the problem that the current SPARK index is inaccurate in predicting postoperative AKI of the patient with advanced age and multiple complications is solved. In addition, based on the clinical problem, a specific model is also provided for predicting the probability of acute kidney injury or severe acute kidney injury of a dangerous patient group, so that the accuracy of disease prediction is ensured.
The first aspect of the application discloses a method for predicting postoperative acute kidney injury of a non-cardiac surgery patient, which comprises the following steps:
acquiring clinical information of a non-cardiac surgery patient;
classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score;
when the patient is a non-high risk patient, inputting clinical information of the non-high risk patient into a non-high risk patient postoperative acute kidney injury prediction model, and dividing the non-high risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
The clinical information of the non-cardiac surgery patient comprises preoperative information and intra-operative information; preoperative information for high-risk patients includes: age, sex, estimated glomerular filtration rate (gfr), proteinuria (dipstick albuminuria), diabetes (diabetes mellitus), renin angiotensin aldosterone system blocker (RAAS blocker administered), blood albumin, hemoglobin and sodium blood; the intra-operative information of the high risk patient includes the expected operation time and emergency operation.
After the classifying of the patient into a high-risk patient and a non-high-risk patient based on the clinical information, the method further comprises: when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative severe acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated third index total score.
A low risk when the first index total score or the third index total score is less than N; a medium risk when the first index total score or the third index total score is between N and M; when the first index total score or the third index total score is greater than or equal to M, a high risk is provided; wherein N is-3.89182 and M is-1.38629; wherein N is-3.89182 and M is-1.38629;
the low risk indicates that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury in a high-risk patient is less than 2%; the stroke risk represents that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury of a high-risk patient is more than or equal to 2% and less than 20%; the high risk indicates that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury of high-risk patients is more than or equal to 20%.
The classifying the patient into a high-risk patient and a non-high-risk patient based on the clinical information includes: when the clinical information meets any one or several of the following conditions, the patient is classified as a high-risk patient; the conditions include: age equal to or greater than a first threshold, pre-operative complications present, operative trauma present, predicted operative time equal to or greater than a second threshold, progressive organ dysfunction present, single organ sequential organ failure estimation score equal to or greater than a third threshold; the first threshold is 65; the second threshold is 2; the third threshold is 2;
the pre-operative complications include any one or more of the following: hypertension, diabetes, coronary heart disease, heart failure, cerebrovascular disease and chronic kidney disease.
The high-risk patient postoperative acute kidney injury prediction model or the high-risk patient postoperative severe acute kidney injury prediction model is constructed by a machine learning method, and the specific method comprises the following steps of: inputting clinical information of a high-risk patient in a training set into a machine learning model to obtain a prediction classification result, comparing the prediction classification result with an actual result, and obtaining a prediction model of the acute kidney injury after operation of the high-risk patient according to a comparison result optimization model: the machine learning method comprises one or more of the following steps: logistic regression algorithm, naive bayes classification, support vector machine, k nearest neighbor, decision tree, random forest, xgboost, perceptron algorithm, GBM, NNET; the machine learning method is preferably as follows: a logistic regression algorithm; the machine learning method is preferably as follows: ordered logistic regression algorithm (proportional dominant regression).
The high-risk patient postoperative acute kidney injury prediction model or the high-risk patient postoperative severe acute kidney injury prediction model is constructed by a machine learning method, and the specific method comprises the following steps of: inputting clinical information of a training set high-risk patient into a machine learning model, calculating to obtain an index total score, outputting a prediction classification result according to the index total score, comparing the prediction classification result with an actual result, and obtaining a post-operation acute kidney injury prediction model of the high-risk patient according to a comparison result optimization model; wherein, the clinical information of the high-risk patient of the training set comprises any one or several continuous variables as follows: age, estimated glomerular filtration rate, albumin, hemoglobin, sodium, expected surgery time; the clinical information of the training set high-risk patient also comprises any one or more of the following variables: sex, diabetes, proteinuria, renin angiotensin aldosterone system blockers and emergency procedures.
The calculation mode of the first index total score comprises the following steps:the method comprises the steps of carrying out a first treatment on the surface of the The calculation mode of the third index total score comprises the following steps:;
wherein y1 is a first index total score, y2 is a third index total score, x1 is age, x2 is an estimated glomerular filtration rate, x3 is albumin, x4 is hemoglobin, x5 is sodium in blood, x6 is an expected operation time, x7 is gender, i.e., male vs female, x8 is diabetes, i.e., diabetes vs is non-diabetic, x9 is proteinuria, i.e., proteinuria vs is non-proteinuria, x10 is a renin angiotensin aldosterone system blocker, i.e., vs is not used, x11 is emergency operation, i.e., emergency operation vs is a phase-selecting operation; a. b, c, d, e, f, g, h, i, j, k are coefficients, a=0.0104, b= -0.0314, c= 0.3150, d= -0.1687, e=0.0292, f= 0.2250, g= 0.5155, h= -0.00166, i=0.6335, j= 0.00611, k= 0.9558; m1 is a constant, m1 is-4.1322; m2 is a constant and m2 is-6.2114.
In a second aspect, the application discloses a system for predicting acute kidney injury in a non-cardiac surgical patient after surgery, the system comprising:
the acquisition module is used for acquiring clinical information of a patient who is not subjected to cardiac surgery;
a judgment module for classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
the first prediction module is used for inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model when the patient is a high-risk patient, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score;
and the second prediction module is used for inputting clinical information of the non-high-risk patient into a non-high-risk patient postoperative acute kidney injury prediction model when the patient is a non-high-risk patient, and dividing the non-high-risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
In a third aspect, the application discloses a system for predicting post-operative acute kidney injury in a non-cardiac surgical patient, the system comprising:
the acquisition module is used for acquiring clinical information of a patient at high risk of non-cardiac operation;
the high-risk patient prediction module is used for inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model or a high-risk patient postoperative severe acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated index total score.
A fourth aspect of the application discloses a computer device, the device comprising: a memory and a processor; the memory is used for storing program instructions; the processor is configured to invoke program instructions, which when executed, are configured to perform the steps of the method disclosed in the first aspect of the application.
A fifth aspect of the application discloses a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method disclosed in the first aspect of the application.
A sixth aspect of the application discloses a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method disclosed in the first aspect of the application.
The application has the following beneficial effects:
1. the application creatively discloses a prediction method of postoperative acute kidney injury of a non-cardiac surgery patient, which is based on the problem that the current SPARK index is inaccurate in predicting postoperative AKI of a patient with advanced age and multiple complications, and provides 2 schemes, wherein the first scheme is to directly predict the risk of postoperative acute kidney injury or postoperative severe acute kidney injury of a high-risk patient; the scheme gives consideration to the effective prediction of the postoperative acute kidney injury or postoperative severe acute kidney injury of high-risk patients or non-high-risk patients through 2 models. The second scheme is to classify patients firstly, and then predict the patients according to the specificity of the classified patient types (high-risk patients or non-high-risk patients) in a targeted mode, and the scheme fully ensures the accuracy of the probability of occurrence of postoperative acute kidney injury or postoperative severe acute kidney injury to different crowds through 3 models.
2. The SPARK index is innovatively improved, so that the SPARK index is suitable for prediction of AKI after operation of high-risk patients; in particular, the inventors improved the semi-quantitative scoring form in the SPARK index to continuous variables based on artificial medical experience, such as: age, estimated glomerular filtration rate, albumin, hemoglobin and sodium and the like, and reconstructing SPARK index by proportional dominance regression (ordered logistic regression) to obtain an improved model. The improved model is changed from the original four-classification to three-classification, which is more beneficial to clinical screening.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method provided in a first aspect of an embodiment of the present application;
FIG. 2 is a schematic flow chart of a system provided by a second aspect of an embodiment of the present application;
FIG. 3 is a schematic flow chart of a system provided by a third aspect of an embodiment of the present application;
fig. 4 is a schematic diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present application with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present application and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments according to the application without any creative effort, are within the protection scope of the application.
Fig. 1 is a schematic flow chart of a method provided in the first aspect of the embodiment of the present application, specifically, the method includes the following steps:
101: acquiring clinical information of a non-cardiac surgery patient;
in one embodiment, the clinical information of the non-cardiac surgical patient includes preoperative information and intra-operative information.
102: classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
in one embodiment, the classifying the patient into a high-risk patient and a non-high-risk patient based on the clinical information includes: when the clinical information meets any one or several of the following conditions, the patient is classified as a high-risk patient; the conditions include: age equal to or greater than a first threshold, pre-operative complications present, operative trauma present, predicted operative time equal to or greater than a second threshold, progressive organ dysfunction present, single organ sequential organ failure estimation score equal to or greater than a third threshold;
wherein the preoperative complications include any one or more of the following: hypertension, diabetes, coronary heart disease, heart failure, cerebrovascular disease and chronic kidney disease. The first threshold is 65; the second threshold is 2; the third threshold is 2.
The single organ sequential organ failure estimation score was the SOFA score (Sequential Organ Failure Assessment), which was proposed in 1994 by the scholars of the ESICM (European Soeiety of Intensive CareMedicine) european intensive care medical association in paris. Principle of SOFA score creation: an objective and simple method is sought which can describe the dysfunction or failure of individual organs in a continuous fashion, and evaluate the extent from mild dysfunction to severe failure, and can repeatedly gauge the occurrence and development of individual or whole organ dysfunction in clinical studies, thereby determining the characteristics describing organ dysfunction or failure.
103: when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score;
in one embodiment, the preoperative information of the high risk patient includes: age, sex, estimated glomerular filtration rate (gfr), proteinuria (dipstick albuminuria), diabetes (diabetes mellitus), renin angiotensin aldosterone system blocker (RAAS blocker administered), blood albumin, hemoglobin and sodium blood; the intra-operative information of the high risk patient includes the expected operation time and emergency operation. Wherein age, expected operating time, estimated glomerular filtration rate (evfr), haemoglobin and sodium are continuous variables, proteinuria (dipstick albuminuria), diabetes (diabetes mellitus), renin angiotensin aldosterone system blocker (RAAS blocker administered), sex, emergency surgery are still semi-quantitative scoring. Hemoglobin is also called hemoglobin, is commonly called hemoglobin, and is an important index for evaluating whether a patient is anemic or not; blood loss and reduction due to various causes, such that hemoglobin below the reference value is anemia.
Continuous variables such as: the range of the age variable value can theoretically take any positive real number, note that it is not a positive integer, for example, the age of a person can be recorded as 17.55 years, the age is 17 years, 6 months and 18 days, and even the information of the birth time can be used to be accurate to a smaller time unit (such as minutes and seconds). The value range of the continuous variable is continuous in theory.
In one embodiment, after the classifying the patient into a high-risk patient and a non-high-risk patient based on the clinical information, the method further comprises: when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative severe acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated third index total score.
In one embodiment, the first index total score or the third index total score is low risk when less than N; a medium risk when the first index total score or the third index total score is between N and M; when the first index total score or the third index total score is greater than or equal to M, a high risk is provided; wherein N is-3.89182 and M is-1.38629; wherein N is-3.89182 and M is-1.38629;
in one embodiment, the low risk indicates that the high risk patient has less than 2% of the probability of developing postoperative acute kidney injury and severe acute kidney injury; the stroke risk represents that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury of a high-risk patient is more than or equal to 2% and less than 20%; the high risk indicates that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury of high-risk patients is more than or equal to 20%.
In one embodiment, the high-risk patient postoperative acute kidney injury prediction model or the high-risk patient postoperative severe acute kidney injury prediction model is constructed by a machine learning method, and the specific method comprises the following steps of: inputting clinical information of a high-risk patient in a training set into a machine learning model to obtain a prediction classification result, comparing the prediction classification result with an actual result, and obtaining a prediction model of the acute kidney injury after operation of the high-risk patient according to a comparison result optimization model: the machine learning method comprises one or more of the following steps: logistic regression algorithm, naive bayes classification, support vector machine, k nearest neighbor, decision tree, random forest, xgboost, perceptron algorithm, GBM, NNET; the machine learning method is preferably as follows: a logistic regression algorithm; the machine learning method is preferably as follows: ordered logistic regression algorithm (proportional dominant regression). The proportion advantage model is as follows: there are multiple types of logistic regression, and if they are classified according to the type of outcome, there are multiple types of logistic regression because there are multiple types of classification variables. At least, logistic regression, multiple unordered logistic regression, ordered logistic regression (also known as cumulative ratio logistic model, proportional dominance model) can be classified into two categories.
In one embodiment, the high-risk patient postoperative acute kidney injury prediction model or the high-risk patient postoperative severe acute kidney injury prediction model is constructed by a machine learning method, and the specific method comprises the following steps of: inputting clinical information of a training set high-risk patient into a machine learning model, calculating to obtain an index total score, outputting a prediction classification result according to the index total score, comparing the prediction classification result with an actual result, and obtaining a post-operation acute kidney injury prediction model of the high-risk patient according to a comparison result optimization model; wherein, the clinical information of the high-risk patient of the training set comprises any one or several continuous variables as follows: age, estimated glomerular filtration rate, albumin, hemoglobin, sodium, expected surgery time; the clinical information of the training set high-risk patient also comprises any one or more of the following variables: sex, diabetes, proteinuria, renin angiotensin aldosterone system blockers and emergency procedures.
In one embodiment, the calculating manner of the first index total score includes:the method comprises the steps of carrying out a first treatment on the surface of the The calculation mode of the third index total score comprises the following steps:;
wherein y1 is a first index total score, y2 is a third index total score, x1 is age, x2 is an estimated glomerular filtration rate, x3 is albumin, x4 is hemoglobin, x5 is sodium in blood, x6 is an expected operation time, x7 is gender, i.e., male vs female, x8 is diabetes, i.e., diabetes vs is non-diabetic, x9 is proteinuria, i.e., proteinuria vs is non-proteinuria, x10 is a renin angiotensin aldosterone system blocker, i.e., vs is not used, x11 is emergency operation, i.e., emergency operation vs is a phase-selecting operation; a. b, c, d, e, f, g, h, i, j, k are coefficients, a=0.0104, b= -0.0314, c= 0.3150, d= -0.1687, e=0.0292, f= 0.2250, g= 0.5155, h= -0.00166, i=0.6335, j= 0.00611, k= 0.9558; m1 is a constant, m1 is-4.1322; m2 is a constant, m2 is-6.2114; the various variable coefficients and constants in the high-risk patient postoperative acute kidney injury prediction model are shown in table 1:
TABLE 1 various variable coefficients and constants in the prediction model of postoperative acute kidney injury in high-risk patients
In one embodiment, the training set of high risk patient postoperative acute kidney injury prediction model includes 639 patients, and the model is further validated externally in 334 patients, which model is raised from 0.67 (made by conventional SPARK index) to 0.77 (p=0.02). The model may be integrated into an electronic case system application.
104: when the patient is a non-high risk patient, inputting clinical information of the non-high risk patient into a non-high risk patient postoperative acute kidney injury prediction model, and dividing the non-high risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
In one embodiment, the clinical information of the non-cardiac surgical patient includes preoperative information and intra-operative information; preoperative information for non-high risk patients includes: age, sex, estimated glomerular filtration rate (gfr), proteinuria (dipstick albuminuria), diabetes (diabetes mellitus), renin angiotensin aldosterone system blocker (RAAS blocker administered), hypoproteinemia (hypoalbuminaemia), anemia (Anemia) and Hyponatremia (hyponatmia); the intra-operative information of the non-high risk patient comprises the expected operation time and emergency operation, and the specific information is shown in table 2:
table 2 scoring profile for predictive model of acute kidney injury after surgery in non-cardiac surgical non-high risk patients
In one embodiment, the predicting the non-high risk patient into A, B, C, D based on the calculated index total score comprises:
when the index total score is less than 20, it is classified as class a; when the index total score is 20 or more and 40 or less, it is classified as class B; when the index total score is 40 or more and 60 or less, it is classified as class C; when the index total score is 60 or more, it is classified as class D; wherein the class a indicates that the non-high risk patient has a probability of developing postoperative acute kidney injury and severe acute kidney injury of less than 2%; the B grade indicates that the probability of occurrence of the postoperative acute kidney injury of the non-high risk patient is more than or equal to 2 percent, and the probability of occurrence of severe acute kidney injury is less than 2 percent; the C grade indicates that the probability of occurrence of the postoperative acute kidney injury of the non-high risk patient is more than or equal to 10 percent, and the probability of occurrence of severe acute kidney injury is more than or equal to 2 percent; the D grade indicates that the probability of occurrence of the acute kidney injury after operation of the non-high risk patient is more than or equal to 20 percent, and the probability of occurrence of the severe acute kidney injury is more than or equal to 10 percent.
In one embodiment, the non-high risk patient postoperative acute kidney injury prediction model scores the risk of postoperative AKI as a semi-quantitative score of 4, the scores are shown on the right, i.e., <20 scores less likely (< 2%) to AKI; 20-40 are divided into AKI existence possibility (more than or equal to 2 percent); 40-60 minutes AKI is at risk (more than or equal to 10 percent); the AKI risk of more than or equal to 60 minutes is definite (more than or equal to 20%). Concentric external verification showed that the differentiation AUC of this model to AKI predictions was 0.72.
FIG. 2 is a schematic flow chart of a system provided by a second aspect of an embodiment of the application, including:
a first acquisition module 201 for acquiring clinical information of a non-cardiac surgery patient;
a judgment module 202 for classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
the first prediction module 203 is configured to, when the patient is a high-risk patient, input clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model, and divide the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score;
and the second prediction module 204 is configured to, when the patient is a non-high risk patient, input clinical information of the non-high risk patient into a non-high risk patient postoperative acute kidney injury prediction model, and divide the non-high risk patient into A, B, C, D four-level prediction results according to the calculated second score total score.
As shown in fig. 3, a schematic flow chart of a system provided in the second aspect of the embodiment of the present application specifically includes:
a second acquisition module 301, configured to acquire clinical information of a patient at high risk of non-cardiac surgery;
the high-risk patient prediction module 302 is configured to input clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model or a high-risk patient postoperative severe acute kidney injury prediction model, and divide the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated index total score.
In one embodiment, the embodiment of the application further provides a system for predicting acute kidney injury after operation of a non-cardiac surgery patient, comprising:
the third acquisition module is used for acquiring clinical information of a patient who is not subjected to cardiac surgery;
a judgment module for classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
the high-risk patient prediction module is used for inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model or a high-risk patient postoperative severe acute kidney injury prediction model when the patient is a high-risk patient, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated index total score;
and the non-high risk patient prediction module is used for inputting clinical information of the non-high risk patient into a non-high risk patient postoperative acute kidney injury prediction model when the patient is a non-high risk patient, and dividing the non-high risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
Fig. 4 is a computer device according to an embodiment of the present application, where the device includes: a memory and a processor; the memory is used for storing program instructions; the processor is configured to invoke program instructions, which when executed, are configured to perform the steps of the method described above.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the method described above.
The embodiment of the application also discloses a computer program product, which comprises a computer program, wherein the computer program realizes the steps of the method when being executed by a processor.
The results of the verification of the present verification embodiment show that assigning an inherent weight to an indication may moderately improve the performance of the present method relative to the default settings.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in implementing the methods of the above embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, where the storage medium may be a read only memory, a magnetic disk or optical disk, etc.
While the foregoing describes a computer device provided by the present application in detail, those skilled in the art will appreciate that the foregoing description is not meant to limit the application thereto, as long as the scope of the application is defined by the claims appended hereto.
Claims (10)
1. A method for predicting acute kidney injury in a patient following a non-cardiac procedure, the method comprising:
acquiring clinical information of a non-cardiac surgery patient;
classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score;
when the patient is a non-high risk patient, inputting clinical information of the non-high risk patient into a non-high risk patient postoperative acute kidney injury prediction model, and dividing the non-high risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
2. The method for predicting post-operative acute kidney injury in a non-cardiac surgical patient as recited in claim 1 wherein the clinical information of the non-cardiac surgical patient includes pre-operative information and intra-operative information; preoperative information for high-risk patients includes: age, sex, estimated glomerular filtration rate, proteinuria, diabetes mellitus, renin angiotensin aldosterone system blocker, blood albumin, hemoglobin and sodium blood; the intra-operative information of the high risk patient includes the expected operation time and emergency operation.
3. A method for predicting post-operative acute kidney injury in a non-cardiac surgical patient as recited in claim 1 wherein, after said classifying the patient into a high-risk patient and a non-high-risk patient based on said clinical information, said method further comprises: when the patient is a high-risk patient, inputting clinical information of the high-risk patient into a high-risk patient postoperative severe acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated third index total score.
4. A method of predicting post-operative acute kidney injury in a non-cardiac surgical patient as set forth in claim 3 wherein the first index total score or the third index total score is low risk when less than N; a medium risk when the first index total score or the third index total score is between N and M; when the first index total score or the third index total score is greater than or equal to M, a high risk is provided;
the low risk indicates that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury in a high-risk patient is less than 2%; the stroke risk represents that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury of a high-risk patient is more than or equal to 2% and less than 20%; the high risk indicates that the probability of occurrence of postoperative acute kidney injury and severe acute kidney injury of high-risk patients is more than or equal to 20%.
5. The method for predicting post-operative acute kidney injury in non-cardiac surgical patients of claim 1, wherein said classifying patients into high-risk patients and non-high-risk patients based on said clinical information comprises: when the clinical information meets any one or several of the following conditions, the patient is classified as a high-risk patient; the conditions include: age equal to or greater than a first threshold, pre-operative complications present, operative trauma present, predicted operative time equal to or greater than a second threshold, progressive organ dysfunction present, single organ sequential organ failure estimation score equal to or greater than a third threshold;
the pre-operative complications include any one or more of the following: hypertension, diabetes, coronary heart disease, heart failure, cerebrovascular disease and chronic kidney disease.
6. The method for predicting postoperative acute kidney injury in non-cardiac surgery patients according to claim 3, wherein the high-risk patient postoperative acute kidney injury prediction model or the high-risk patient postoperative severe acute kidney injury prediction model is constructed by a machine learning method, and the specific method comprises: inputting clinical information of a training set high-risk patient into a machine learning model, calculating to obtain an index total score, outputting a prediction classification result according to the index total score, comparing the prediction classification result with an actual result, and obtaining a post-operation acute kidney injury prediction model of the high-risk patient according to a comparison result optimization model; wherein, the clinical information of the high-risk patient of the training set comprises any one or several continuous variables as follows: age, estimated glomerular filtration rate, albumin, hemoglobin, sodium, expected surgery time; the clinical information of the training set high-risk patient also comprises any one or more of the following variables: sex, diabetes, proteinuria, renin angiotensin aldosterone system blockers, emergency surgery;
the calculation mode of the first index total score comprises the following steps:the method comprises the steps of carrying out a first treatment on the surface of the The calculation mode of the third index total score comprises the following steps:the method comprises the steps of carrying out a first treatment on the surface of the Wherein y1 is a first index total score, y2 is a third index total score, x1 is age, x2 is an estimated glomerular filtration rate, x3 is albumin, x4 is hemoglobin, x5 is sodium in blood, x6 is an expected operation time, x7 is gender, i.e., male vs female, x8 is diabetes, i.e., diabetes vs is non-diabetic, x9 is proteinuria, i.e., proteinuria vs is non-proteinuria, x10 is a renin angiotensin aldosterone system blocker, i.e., vs is not used, x11 is emergency operation, i.e., emergency operation vs is a phase-selecting operation; a. b, c, d, e, f, g, h, i, j, k are coefficients, a=0.0104, b= -0.0314, c= 0.3150, d= -0.1687, e=0.0292, f= 0.2250, g= 0.5155, h= -0.00166, i=0.6335, j= 0.00611, k= 0.9558; m1 is a constant, m1 is-4.1322; m2 is a constant and m2 is-6.2114.
7. A system for predicting acute kidney injury in a patient following a non-cardiac procedure, the system comprising:
the acquisition module is used for acquiring clinical information of a patient who is not subjected to cardiac surgery;
a judgment module for classifying patients into high-risk patients and non-high-risk patients based on the clinical information;
the first prediction module is used for inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model when the patient is a high-risk patient, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated first index total score;
and the second prediction module is used for inputting clinical information of the non-high-risk patient into a non-high-risk patient postoperative acute kidney injury prediction model when the patient is a non-high-risk patient, and dividing the non-high-risk patient into A, B, C, D-grade prediction results according to the calculated second index total score.
8. A system for predicting acute kidney injury in a patient following a non-cardiac procedure, the system comprising:
the acquisition module is used for acquiring clinical information of a patient at high risk of non-cardiac operation;
the high-risk patient prediction module is used for inputting clinical information of the high-risk patient into a high-risk patient postoperative acute kidney injury prediction model or a high-risk patient postoperative severe acute kidney injury prediction model, and dividing the high-risk patient into low-risk, medium-risk and high-risk prediction results according to the calculated index total score.
9. A computer device, the device comprising: a memory and a processor; the memory is used for storing program instructions; the processor being adapted to invoke program instructions, which when executed, are adapted to carry out the steps of the method according to any of claims 1-6.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, realizes the steps of the method of any of the preceding claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311432939.0A CN117153380B (en) | 2023-11-01 | 2023-11-01 | Method, system and equipment for predicting postoperative acute kidney injury of non-cardiac surgery patient |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311432939.0A CN117153380B (en) | 2023-11-01 | 2023-11-01 | Method, system and equipment for predicting postoperative acute kidney injury of non-cardiac surgery patient |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117153380A true CN117153380A (en) | 2023-12-01 |
CN117153380B CN117153380B (en) | 2024-02-06 |
Family
ID=88908545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311432939.0A Active CN117153380B (en) | 2023-11-01 | 2023-11-01 | Method, system and equipment for predicting postoperative acute kidney injury of non-cardiac surgery patient |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117153380B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117894466A (en) * | 2024-03-15 | 2024-04-16 | 四川大学华西医院 | Continuous acute nephritis risk prediction method and system based on recurrent neural network |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2716452C1 (en) * | 2018-12-28 | 2020-03-11 | Федеральное государственное бюджетное военное образовательное учреждение высшего образования "Военно-медицинская академия имени С.М. Кирова" Министерства обороны Российской Федерации (ВМедА) | Method for prediction of developing renal dysfunction at the end of subacute period of myocardial infarction in men younger than 60 years old |
CN111276230A (en) * | 2020-02-24 | 2020-06-12 | 上海市同仁医院 | Cardiovascular and cerebrovascular disease integrated hierarchical management system and method |
CN113571166A (en) * | 2021-07-28 | 2021-10-29 | 广西医科大学第一附属医院 | AKI layered early warning and clinical disease monitoring management method and system |
US20220008018A1 (en) * | 2018-11-16 | 2022-01-13 | Seoul National University Hospital | System and method for predicting risk of acute renal failure following non-cardiac surgery |
CN114613517A (en) * | 2022-03-25 | 2022-06-10 | 深圳市第二人民医院(深圳市转化医学研究院) | Prognosis prediction method and device, electronic equipment and storage medium |
KR102526577B1 (en) * | 2022-09-27 | 2023-04-27 | 주식회사 비투엔 | Artificial intelligence based risk prediction system and method for patient management |
WO2023201647A1 (en) * | 2022-04-21 | 2023-10-26 | China Medical University | Method for assessing acute kidney injury and acute kidney injury assessment system |
-
2023
- 2023-11-01 CN CN202311432939.0A patent/CN117153380B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220008018A1 (en) * | 2018-11-16 | 2022-01-13 | Seoul National University Hospital | System and method for predicting risk of acute renal failure following non-cardiac surgery |
RU2716452C1 (en) * | 2018-12-28 | 2020-03-11 | Федеральное государственное бюджетное военное образовательное учреждение высшего образования "Военно-медицинская академия имени С.М. Кирова" Министерства обороны Российской Федерации (ВМедА) | Method for prediction of developing renal dysfunction at the end of subacute period of myocardial infarction in men younger than 60 years old |
CN111276230A (en) * | 2020-02-24 | 2020-06-12 | 上海市同仁医院 | Cardiovascular and cerebrovascular disease integrated hierarchical management system and method |
CN113571166A (en) * | 2021-07-28 | 2021-10-29 | 广西医科大学第一附属医院 | AKI layered early warning and clinical disease monitoring management method and system |
CN114613517A (en) * | 2022-03-25 | 2022-06-10 | 深圳市第二人民医院(深圳市转化医学研究院) | Prognosis prediction method and device, electronic equipment and storage medium |
WO2023201647A1 (en) * | 2022-04-21 | 2023-10-26 | China Medical University | Method for assessing acute kidney injury and acute kidney injury assessment system |
KR102526577B1 (en) * | 2022-09-27 | 2023-04-27 | 주식회사 비투엔 | Artificial intelligence based risk prediction system and method for patient management |
Non-Patent Citations (3)
Title |
---|
谷定英: "高危和非高危病员肾移植临床对比观察", 温州医学院学报, no. 03 * |
谷鸿秋 等: "缺血性卒中患者卒中复发风险预测模型研究进展及展望", 《中国卒中杂志》, vol. 18, no. 07, pages 2 * |
赵梦林;祖凌云;高炜;: "非心脏手术围术期心血管事件风险预测模型研究进展", 中国医学前沿杂志(电子版), no. 03 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117894466A (en) * | 2024-03-15 | 2024-04-16 | 四川大学华西医院 | Continuous acute nephritis risk prediction method and system based on recurrent neural network |
CN117894466B (en) * | 2024-03-15 | 2024-05-17 | 四川大学华西医院 | Continuous acute nephritis risk prediction method and system based on recurrent neural network |
Also Published As
Publication number | Publication date |
---|---|
CN117153380B (en) | 2024-02-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Panahiazar et al. | Using EHRs and machine learning for heart failure survival analysis | |
Hsieh et al. | Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks | |
Azab et al. | Neutrophil-lymphocyte ratio as a predictor of adverse outcomes of acute pancreatitis | |
CN117153380B (en) | Method, system and equipment for predicting postoperative acute kidney injury of non-cardiac surgery patient | |
Sufriyana et al. | Prediction of preeclampsia and intrauterine growth restriction: development of machine learning models on a prospective cohort | |
Chuang et al. | Predicting the prolonged length of stay of general surgery patients: a supervised learning approach | |
Schneider et al. | Predicting acute kidney injury among burn patients in the 21st century: a classification and regression tree analysis | |
Khwannimit | A comparison of three organ dysfunction scores: MODS, SOFA and LOD for predicting ICU mortality in critically ill patients | |
Bihorac | Acute kidney injury in the surgical patient: recognition and attribution | |
Thakar et al. | Degree of acute kidney injury before dialysis initiation and hospital mortality in critically ill patients | |
Balpande et al. | Review on prediction of diabetes using data mining technique | |
Shinjo et al. | Comparison of kidney disease: improving global outcomes and acute kidney injury network criteria for assessing patients in intensive care units | |
CN106845140A (en) | A kind of kidney failure method for early warning monitored based on specific gravity of urine and urine volume and system | |
Moreno-Sánchez | Data-driven early diagnosis of chronic kidney disease: development and evaluation of an explainable AI model | |
Manoochehri et al. | Predicting preeclampsia and related risk factors using data mining approaches: A cross-sectional study | |
Herrgårdh et al. | Digital twins and hybrid modelling for simulation of physiological variables and stroke risk | |
Nagayasu et al. | Use of an artificial intelligence‐based rule extraction approach to predict an emergency cesarean section | |
Yıldız et al. | Analysis of congenital heart surgery results: A comparison of four risk scoring systems | |
CN117116475A (en) | Method, system, terminal and storage medium for predicting risk of ischemic cerebral apoplexy | |
Umut et al. | Prediction of sepsis disease by Artificial Neural Networks | |
Maria et al. | Obesity Risk Prediction Using Machine Learning Approach | |
Lin et al. | Predictors of type 2 diabetes among T aiwanese women with prior gestational diabetes mellitus | |
CN114446470A (en) | Artificial intelligence model-based acute kidney injury recovery time prediction method | |
CN113345584A (en) | Disease prognosis risk prediction model training method and device and electronic equipment | |
CN112259231A (en) | High-risk gastrointestinal stromal tumor patient postoperative recurrence risk assessment method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |