CN115240854B - Pancreatitis prognosis data processing method and system - Google Patents
Pancreatitis prognosis data processing method and system Download PDFInfo
- Publication number
- CN115240854B CN115240854B CN202210908379.0A CN202210908379A CN115240854B CN 115240854 B CN115240854 B CN 115240854B CN 202210908379 A CN202210908379 A CN 202210908379A CN 115240854 B CN115240854 B CN 115240854B
- Authority
- CN
- China
- Prior art keywords
- sign data
- human body
- prediction model
- basic sign
- pancreatitis
- 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.)
- Active
Links
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Abstract
The invention discloses a method, a system, equipment and a computer readable storage medium for processing pancreatitis prognosis data, wherein the method comprises the following steps: acquiring human body basic sign data of a sample; inputting the human body basic sign data into a pre-trained prognosis prediction model to obtain a first classification result; calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result according to the grading value; the prognostic classification indicator includes: grading pancreatitis; carrying out weighted fusion processing on the first classification result and the second classification result to obtain a final classification result; the prognosis prediction model includes: pancreatitis grading prediction model.
Description
Technical Field
The invention relates to the technical field of medical biology, in particular to a method and a system for processing pancreatitis prognosis data.
Background
Acute pancreatitis (acute pancreatitis, AP) is a common acute abdomen and is the first digestive system disease of worldwide emergency hospital admission. Pancreatitis is classified as severe, moderate and mild according to systemic and local complications. About 20% of patients with acute pancreatitis develop severe pancreatitis, i.e. with persistent organ failure, with a mortality rate of up to 20% -40%. Moderately severe pancreatitis has localized complications with potential intervention therapy needs. Light pancreatitis is often self-limiting in supportive treatment. The severity of acute pancreatitis is pre-judged early, and targeted treatment is adopted timely, so that the severity of acute pancreatitis is very important to reducing the death rate.
There is currently no single variable or scoring system for acute pancreatitis that accurately predicts the severity of pancreatitis prognosis at the beginning of the onset of disease. Machine learning has been widely used in clinical studies including predicting the risk of severe pancreatitis, but most studies only perform dichotomous prediction, i.e., acute pancreatitis patients will develop severe pancreatitis or non-severe pancreatitis in the future, and no research results have been searched that can accurately predict the severity of pancreatitis prognosis in three categories, i.e., distinguish between light, medium, and severe pancreatitis. In addition, most of the existing researches are single-center researches, the number of samples is small, and the accuracy of the results is required to be commercially available.
In order to enable doctors to identify high-risk patients as early as possible and to make diagnosis and treatment plans to provide help references, the invention provides a method and a system for processing pancreatitis prognosis data.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. According to the method, a large amount of data from multiple centers is adopted, a prediction model is established for three-classification prognosis of acute pancreatitis, whether the acute pancreatitis dies, pancreas infection and necrosis, whether ICU is entered, hospitalization duration and other indexes by a plurality of machine learning methods, a classification result obtained by the prediction model is subjected to weighted fusion with a classification result obtained based on 5 traditional scoring systems, a final classification result is obtained, and a help reference is provided for doctors to identify high-risk patients as soon as possible and make diagnosis and treatment plans, so that the related life science problems are solved.
The application discloses a method for processing pancreatitis prognosis data, which comprises the following steps:
acquiring human body basic sign data of a sample;
inputting the human body basic sign data into a pre-trained prognosis prediction model to obtain a first classification result;
calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result according to the grading value; the prognostic classification indicator includes: grading pancreatitis;
carrying out weighted fusion processing on the first classification result and the second classification result to obtain a final classification result;
the prognosis prediction model includes: a pancreatitis grading prediction model; the training method of the pancreatitis grading prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise mild pancreatitis, moderate pancreatitis and severe pancreatitis;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed pancreatitis grading prediction model.
The scoring values include one or more of the following: APACHE-II score, marshall score, sofa score, qsfa score, bisap score.
The training method of the pancreatitis grading prediction model further comprises the following steps:
sequencing the human body basic sign data features to obtain sequenced human body basic sign data features;
performing model construction by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed pancreatitis grading prediction model;
optionally, the sorting process includes:
for one of the human body basic sign data features subjected to feature extraction, calculating all combinations and marginal contribution of a single human body basic sign data feature in the combinations according to a combination sequence formed by the human body basic sign data features;
obtaining the contribution degree of a single human body basic sign data characteristic in the human body basic sign data characteristics according to the marginal contribution;
sorting the human body basic sign data features based on the contribution degrees, and outputting N human body basic sign data features with high contribution degrees;
optionally, the N is at least 5.
The first classification result includes: mild pancreatitis, moderate pancreatitis, and severe pancreatitis;
Optionally, the second classification result includes: mild pancreatitis, moderate pancreatitis, and severe pancreatitis.
The prognostic classification indicator further includes: whether or not to die;
the prognosis prediction model further includes: a death prediction model;
the training method of the death prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise dead and non-dead;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed death prediction model;
optionally, the prognostic classification indicator further includes: whether or not to infect necrosis;
the prognosis prediction model further includes: infection necrosis prediction model;
the training method of the infection necrosis prediction model comprises the following steps:
acquiring human body basic sign data and classification labels of a training set sample, wherein the labels comprise infection necrosis and uninfected necrosis;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
Constructing a model by utilizing the characteristics of the human body basic sign data to obtain a constructed infection necrosis prediction model;
optionally, the prognostic classification indicator further includes: grading the hospitalization duration;
optionally, the prognosis prediction model further includes: a hospital stay prediction model;
the training method of the hospitalization duration prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise a first hospitalization duration and a second hospitalization duration; a first length of stay less than or equal to the classification threshold, and a second length of stay greater than or equal to the classification threshold;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed hospital stay prediction model;
optionally, the prognostic classification indicator further includes: whether to check in the ICU;
optionally, the prognosis prediction model further includes: ICU prediction model;
the training method of the ICU prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise an in-check ICU and an out-of-check ICU;
Performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed ICU prediction model.
The human body basic sign data comprise one or more of the following: age, sex, cause, body temperature, blood pressure, heart rate, respiratory rate, white blood cells, hematocrit, platelets, potassium, sodium, calcium, creatinine, urea nitrogen, whether the consciousness score is full, whether there is a peritoneal irritation, whether there is pleural effusion.
Performing model construction on the human body basic sign data by using a machine learning method to obtain a constructed prognosis prediction model;
optionally, the machine learning method includes one or more of the following: linear regression, logistic regression, linear Discriminant Analysis (LDA), classification and regression trees, naive bayes, KNN, learning vector quantization, support Vector Machine (SVM), random forest, lightGBM;
optionally, the machine learning method is as follows: the weighted fusion of any two algorithms;
optionally, the machine learning method is as follows: weighted fusion of random forest and LightGBM.
An apparatus for processing pancreatitis prognosis data, the apparatus comprising: a memory and a processor;
the memory is used for storing program instructions;
the processor is used for calling program instructions, and when the program instructions are executed, the processor is used for executing the processing method of pancreatitis prognosis data.
A system for processing pancreatitis prognosis data, comprising:
the acquisition unit is used for acquiring the human body basic sign data of the sample;
the first classification unit is used for inputting the human body basic sign data into a pre-trained prognosis prediction model to obtain a first classification result;
the second classification unit is used for calculating a grading value of a prognosis classification index based on the human body basic sign data and obtaining a second classification result according to the grading value; the prognostic classification indicator includes: grading pancreatitis;
the third classification unit is used for carrying out weighted fusion processing on the first classification result and the second classification result to obtain a final classification result;
the prognosis prediction model includes: the pancreatitis grading prediction model comprises the following training method:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise mild pancreatitis, moderate pancreatitis and severe pancreatitis;
Performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed pancreatitis grading prediction model.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of processing pancreatitis prognosis data as described above.
The application has the following beneficial effects:
1. the application creatively discloses a method for processing pancreatitis prognosis data, which establishes a three-classification prognosis prediction model for prognosis data indexes of acute pancreatitis by a plurality of machine learning methods, classifies the pancreatitis prognosis severity more accurately, namely mild pancreatitis, moderately severe pancreatitis or severe pancreatitis, and ensures that the pancreatitis prognosis severity is more accurately predicted and predicted in advance compared with the two classification prediction results, thereby being beneficial to early predicting the acute pancreatitis severity and assisting doctors to accurately predict;
2. the application creatively discloses a processing method of pancreatitis prognosis data, which skillfully carries out weighted fusion on classification results based on a constructed prognosis prediction model and classification results obtained by classifying scoring values based on 5 traditional scoring systems to obtain a new combined model, and the new combined model has better unexpected effect when processing pancreatitis prognosis data; after the parameters of the patient, namely the human body sign data are input, obtaining a final classification result through 2 classification methods; 5 scoring systems are studied to a certain extent in SAP classification, a traditional scoring system is fused with a prognosis prediction model constructed by clinical data, and the results obtained by the 2 methods are weighted and fused by using a machine learning algorithm, so that the method has multi-center and prospective properties, and the accuracy and depth of data analysis and processing are greatly improved;
3. The method creatively establishes and predicts the major endpoint to be the prognosis of the severity of pancreatitis, the minor endpoint to be whether death, pancreatic infection and necrosis, whether ICU and hospitalization duration are entered, and integrates various indexes, thereby providing help reference for doctors to identify high-risk patients as early as possible and make diagnosis and treatment plans and solving the related life science problems.
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 an analysis of a method for processing pancreatitis prognosis data according to an embodiment of the application;
FIG. 2 is a schematic diagram of a device for processing pancreatitis prognosis data according to the embodiment of the application;
FIG. 3 is a schematic flow chart of a system for processing pancreatitis prognosis data according to an embodiment of the present application;
FIG. 4 is a diagram of classification results of various machine learning algorithms in basic vital sign data of a human body provided by an embodiment of the present application;
FIG. 5 is a schematic diagram of an algorithm-classification method using random forests according to an embodiment of the present invention;
fig. 6 is a schematic diagram of classification by a method of using a LightGBM according to the second algorithm provided by the embodiment of the present invention;
FIG. 7 is a graph showing the difference in AUC of predicted acute pancreatitis prognosis (SAP, MSAP, MAP) under various machine learning algorithms provided by embodiments of the present invention;
FIG. 8 is a schematic diagram of the accuracy of predicting acute pancreatitis prognosis (SAP, MSAP, MAP) under different machine learning algorithms provided by embodiments of the present invention;
FIG. 9 is a diagram showing the comparison of the machine learning algorithm provided by the embodiment of the present invention with the conventional scoring model for predicting the severity of acute pancreatitis AUC;
FIG. 10 is a schematic diagram of a comparison of a calibration graph of a machine learning algorithm provided by an embodiment of the present invention with a traditional scoring model for predicting acute pancreatitis severity;
FIG. 11 is a diagram of a machine learning algorithm for predicting a secondary endpoint according to an embodiment of the present invention: schematic of whether dead, pancreatic necrosis, ICU in, and stay in hospital;
FIG. 12 is a diagram of a fusion model provided in an embodiment of the present invention when predicting a secondary endpoint: schematic representation of AUC, accuracy, sensitivity, specificity, PPV and dnpv;
fig. 13 is a schematic diagram of variable contribution values when predicting AP severity typing according to an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present invention with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present invention 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 invention 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 invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments according to the invention without any creative effort, are within the protection scope of the invention.
Fig. 1 is a schematic flow chart of a method for processing pancreatitis prognosis data according to an embodiment of the invention, specifically, the method includes the following steps:
101: acquiring human body basic sign data of a sample;
in one embodiment, the human underlying sign data includes one or more of the following: age (yes), gender Male (%), etiology Etiology, body Temperature (. Degree.C.), blood pressure SBP (mmHg), heart rate HR (bpm), respiratory rate RR (bpm), white blood cell WBC (. Times.109/L), hematocrit HCT, platelet PLT (. Times.109/L), potassium K (mmol/L), sodium Na (mmol/L), calcium Ca (mmol/L), creatinine Cr (umol/L), urea nitrogen Bun (mmol/L), whether the consciousness score is full of the mechanical disorder, whether there is a peritoneal irritation Peritoneal irritation, whether there is pleural effusion.
Optionally, the human body basic sign data further includes one or more of the following: demographic data (age, sex, etiology of acute pancreatitis), baseline laboratory tests (white blood cells, hematocrit, platelets, potassium, sodium, calcium, creatinine, urea nitrogen, blood glucose levels Glu (mmol/L)), baseline vital signs (body temperature, systolic blood pressure, heart rate, respiratory rate), baseline physical signs (presence or absence of mental changes, signs of peritoneal irritation, etc.), prognosis data (incidence of persistent organ dysfunction, incidence of localized complications, incidence of infectious pancreatic necrosis Infected necrosis, total Hospital day (days), ICU acceptance rate ICU admissions, mortality Die, etc.), and the like.
In one embodiment, the sample comprises: from 5 months 2018 to 4 months 2022, from 930 more than one acute pancreatitis patient in the multicenter, prospective, randomized controlled acute pancreatitis study database. The study was approved by the ethical committee (ethical ZS-1413). The inclusion criteria were: diagnosis of acute pancreatitis, onset of disease within 48 hours, age 18-75 years, informed consent to participate in the trial. The exclusion criteria were: 48 hours or more after onset of the disease, renal insufficiency, gestation or lactation, poorly controlled hypertension, barycentric vascular disease, abnormal mind, and acute pancreatitis caused by tumor or ERCP operation.
The research results show that: the average age of the sample of 930 cases of acute pancreatitis patients is 48.6+ -6.0; male patient ratio was 62.7% (586/930); the causes of acute pancreatitis include: biliary=383, lipogenic=291, alliholic=65, other=191; the body temperature is 37.1 plus or minus 1.05; the blood pressure was 130.3.+ -. 68.0.
102: inputting the human body basic sign data into a pre-trained prognosis prediction model to obtain a first classification result;
in one embodiment, the prognosis prediction model comprises: the pancreatitis grading prediction model comprises the following training method:
Acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise mild pancreatitis, moderate pancreatitis and severe pancreatitis; symptoms of mild pancreatitis MAP include: no complications of whole body or local parts, no organ failure; symptoms of moderate to severe pancreatitis MSAP include: with systemic or local complications, organ failure is transient, namely less than or equal to 48 hours; symptoms of severe pancreatitis SAP include: persistent organ failure; the data set is randomly divided into training and test sets in a ratio of 4 to 1.
Performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed pancreatitis grading prediction model.
In one embodiment, the training method of the pancreatitis grading prediction model further comprises:
sequencing the human body basic sign data features to obtain sequenced human body basic sign data features;
performing model construction by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed pancreatitis grading prediction model;
Optionally, the sorting process includes:
for one of the human body basic sign data features subjected to feature extraction, calculating all combinations and marginal contribution of a single human body basic sign data feature in the combinations according to a combination sequence formed by the human body basic sign data features;
obtaining the contribution degree of a single human body basic sign data characteristic in the human body basic sign data characteristics according to the marginal contribution;
sorting the human body basic sign data features based on the contribution degrees, and outputting N human body basic sign data features with high contribution degrees; the N is at least 5.
In the process of constructing the pancreatitis grading prediction model, sequencing the basic sign data of the human body according to the contribution degree from high to low, and the result is as follows: the program effect is shown in fig. 13, where HR, cr, RR, ca, glu, wbc, na, plt, BUN, age, temperature, gcs= 15,peritoneal irritation,sbp,k,etiology,hct,gender. In the grading prediction of pancreatitis, the AUC modeled with the most important 5 features HR, ca, glu, RR, temperature was 0.792 and the AUC modeled with the most important 10 features HR, ca, glu, RR, temperature, cr, wbc, BUN, k, plt was 0.836;
In one embodiment, the first classification result includes: mild pancreatitis, moderate pancreatitis, and severe pancreatitis;
in one embodiment, the human underlying sign data is input into a pre-trained pancreatitis grading prediction model, resulting in a first classification of mild pancreatitis, moderate pancreatitis, and severe pancreatitis.
In one embodiment, the prognostic classification indicator further comprises: whether or not to die;
the prognosis prediction model further includes: a death prediction model;
the training method of the death prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise dead and non-dead;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed death prediction model;
optionally, the training method of the death prediction model further includes: sequencing the human body basic sign data features to obtain sequenced human body basic sign data features; performing model construction by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed death prediction model; AUC modeled with the 5 most important features Ca, HR, wbc, BUN, etiology was 0.911 and AUC modeled with the 10 most important features Ca, HR, wbc, BUN, etiology, sbp, cr, age, glu, na was 0.949 when predicting whether to die;
In one embodiment, the human basic sign data is input into a pre-trained death prediction model to obtain a first classification result of death and non-death.
Optionally, the prognostic classification indicator further includes: whether or not to infect necrosis;
the prognosis prediction model further includes: infection necrosis prediction model;
the training method of the infection necrosis prediction model comprises the following steps:
acquiring human body basic sign data and classification labels of a training set sample, wherein the labels comprise infection necrosis and uninfected necrosis;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the characteristics of the human body basic sign data to obtain a constructed infection necrosis prediction model;
optionally, the training method of the infection necrosis prediction model further comprises: sequencing the human body basic sign data features to obtain sequenced human body basic sign data features; performing model construction by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed infection necrosis prediction model; AUC modeled with the most important 5 features glu, HR, ca, plt, age was 0.776 and AUC modeled with the most important 10 features glu, HR, ca, plt, age, wbc, hct, BUN, temperature, RR was 0.825 when predicting whether necrosis was infected;
In one embodiment, the human basic sign data is input into a pre-trained infection necrosis prediction model to obtain a first classification result of infection necrosis and non-infection necrosis.
Optionally, the prognostic classification indicator further includes: grading the hospitalization duration;
optionally, the prognosis prediction model further includes: a hospital stay prediction model;
the training method of the hospitalization duration prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise a first hospitalization duration and a second hospitalization duration; a first length of stay less than or equal to the classification threshold, and a second length of stay greater than or equal to the classification threshold; the classification threshold is the first 24 hours of admission, and the data of the first 24 hours are used for predicting the later prognosis of the patient;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed hospital stay prediction model;
optionally, the training method of the hospital stay prediction model further includes: sequencing the human body basic sign data features to obtain sequenced human body basic sign data features; performing model construction by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed hospital stay prediction model; AUC modeled with the most important 5 features Ca, glu, wbc, plt, HR was 0.790 and AUC modeled with the most important 10 features Ca, glu, wbc, plt, HR, hct, temperature, na, BUN, age was 0.807 when predicting hospital stay ratings;
In one embodiment, the human body basic sign data is input into a pre-trained hospital stay prediction model to obtain a first classification result of a first hospital stay and a second hospital stay.
Optionally, the prognostic classification indicator further includes: whether to check in the ICU;
optionally, the prognosis prediction model further includes: ICU prediction model;
the training method of the ICU prediction model comprises the following steps:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise an in-check ICU and an out-of-check ICU;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed ICU prediction model;
optionally, the training method of the ICU prediction model further includes: sequencing the human body basic sign data features to obtain sequenced human body basic sign data features; performing model construction by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed ICU prediction model; in predicting whether to check in the ICU, the AUC modeled with the 5 most important features glu, RR, HR, ca, plt was 0.863 and the AUC modeled with the 10 most important features glu, RR, HR, ca, plt, cr, wbc, temperature, na, BUN was 0.887.
In one embodiment, the human basic sign data is input into a pre-trained ICU prediction model to obtain first classification results of in-check ICU and out-check ICU.
In one embodiment, a machine learning method is utilized to perform model construction on the human body basic sign data to obtain the constructed prognosis prediction model;
optionally, the machine learning method includes one or more of the following: linear regression, logistic regression, linear Discriminant Analysis (LDA), classification and regression trees, naive bayes, KNN, learning vector quantization, support Vector Machine (SVM), random forest, lightGBM;
optionally, the machine learning method is as follows: the weighted fusion of any two algorithms;
optionally, the machine learning method is as follows: weighted fusion of random forest and LightGBM.
In one embodiment, the study uniformly uses 5-step cross-validation, targeting the average AUC, using bayesian probability-based Optuna for hyper-parametric tuning of all models. First, support vector machines are a classical efficient method to find an optimal hyperplane to classify a dataset. Attempts were made to model by adjusting gamma and pentaty term using kernel functions including linear, sigmoid, polynomial and radial basis functions. Second, logistic regression is a simple, efficient and interpretable method, which assumes that data obeys Bernoulli distribution, introduces Sigmoid on the basis of a linear model, and adopts a gradient descent method to update parameters to realize data classification. We try to model by selecting different regularization functions, setting different regularization coefficients, residual convergence conditions, and maximum number of iterations. Thirdly, the decision tree is a basic method of various tree models, simulates decision judgment ideas of people, and simply and intuitively carries out decision classification according to feature attribution. And comparing the information entropy with gini coefficient to perform feature division, and constructing a model by adopting different tree depths, minimum sample numbers of leaf nodes and minimum unrepeated reduction values. Fourth, random forest is a method ensemble learning of bagging class with decision tree as sub-model, which adopts bootstrap sample method to randomly extract training sample to train each sub-model, and each sub-model votes to obtain final classification result. In addition to the basic sub-model super-parameters including maximum tree depth, etc., we also try to adjust the ensable super-parameters such as the number of sub-models. Fifth, lightGBM is a lightweight and efficient (Gradient Boosting Decision Tree, GBDT) -based improved model that uses histogram algorithm for feature discretization, and using Leaf-wise to suppress Leaf growth, while increasing algorithm speed, and enhancing algorithm robustness and generalization capability. The super parameters to be adjusted by the LightGBM mainly comprise maximum tree depth, maximum leaf node number, learning rate, regularization parameters, iteration times, minimum splitting gain, maximum histogram bin and the like. Sixth, for random forests and lightgbms with excellent comprehensive performance, we use a soft voting fusion method with weights to fuse the two to generate an optimal classification model.
We evaluated the accuracy of the machine learning algorithm with the area AUC under Receiver Operating Characteristic (ROC) curve combined with accuracy, sensitivity, specificity, positive predictive value, negative predictive value. The registration belt verifies the consistency of the output probability and the true probability of the model. The interpretability of the model and the contribution of various parameters to classification are important in clinical studies, and a general machine learning interpretation method ShapleyAdditive explanation (SHAP) is used to analyze the characteristic contribution of the optimal model for each endpoint. For the tree model we used a rapid and efficient SHAP variant TreeSHAP for analysis.
In one embodiment, a weighted fusion model of random forests and LightGBM is used in particular; for patient parameter x input to the model, the output classification result y of the model is shown as follows
w 1 And w 2 The fusion weights of the random forest and the LightGBM are respectively; for random forests, it consists of N 1 And each base learner DT is formed by respectively carrying out decision prediction on input by each base learner trained by different data subsets, and obtaining a prediction result after averaging all prediction values. For the N 2 The input of each base learner is firstly subjected to a histogram function H to determine the histogram sub-block to which the input belongs, then the corresponding predicted value is generated through the base learner, and all the predicted values and the initial value y0 are summed to generate a predicted result. The random forest and the LightGBM are fused through the respective weights to obtain a final fusion classification result;
Alternatively, the initial value y0 may be:wherein->The average value of the training set labels;
optionally, the N 1 The individual basis learner DT is: ID3, C4.5, CART; the N2 base learners CART are: a CART decision tree;
alternatively, referring to fig. 5, a method of performing computation using a random forest algorithm; referring to fig. 6, a method for performing calculation using the LightGBM algorithm;
103: calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result according to the grading value;
in one embodiment, the scoring values include one or more of the following: APACHE-II score, marshall score, sofa score, qsfa score, bisap score; calculating a scoring value by adopting a public scoring rule, and directly discarding the index when the index is not included in the public scoring rule; or, according to the sorting result of sorting the human body basic sign data features based on the contribution degree, scoring the indexes which are not included in the public scoring rule according to the scoring rule closest to the index of the contribution degree; for example, when the a-indicator is not included in the disclosed scoring rule, the result obtained according to the ranking process: and if the index closest to the contribution degree of the index A is the index B, the scoring rule of the index A is consistent with the scoring rule of the index B.
In one embodiment, the prognostic classification indicator includes: grading pancreatitis; the second classification result includes: mild pancreatitis, moderate pancreatitis, and severe pancreatitis. Calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining second classification results of mild pancreatitis, moderate pancreatitis and severe pancreatitis according to the grading value;
in one embodiment, the prognostic classification indicator further comprises: whether or not to die; calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result of death and non-death according to the grading value;
in one embodiment, the prognostic classification indicator further comprises: whether or not to infect necrosis; calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result of the infection necrosis and the non-infection necrosis according to the grading value;
in one embodiment, the prognostic classification indicator further comprises: grading the hospitalization duration; calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result of the first hospitalization duration and the second hospitalization duration according to the grading value;
In one embodiment, the prognostic classification indicator further comprises: whether to check in the ICU; and calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result of the check-in ICU and the check-out ICU according to the grading value.
104: carrying out weighted fusion processing on the first classification result and the second classification result to obtain a final classification result;
in one embodiment, the process of weighted fusion processing is accomplished using conventional modeling algorithms.
FIG. 2 is a schematic diagram of a conventional deviceThe embodiment of the invention provides a device for processing pancreatitis prognosis data, which comprises: a memory and a processor;
the memory is used for storing program instructions;
the processor is used for calling program instructions, and when the program instructions are executed, the processor is used for executing the processing method of pancreatitis prognosis data.
FIG. 3 is a schematic diagram of a preferred embodiment of the present inventionThe system for processing pancreatitis prognosis data provided by the embodiment of the invention comprises:
an acquisition unit 301, configured to acquire human body basic sign data of a sample;
the first classification unit 302 is configured to input the basic human body sign data into a pre-trained prognosis prediction model, so as to obtain a first classification result;
A second classification unit 303, configured to calculate a score value of a prognostic classification indicator based on the human body basic sign data, and obtain a second classification result according to the score value; the prognostic classification indicator includes: grading pancreatitis;
a third classification unit 304, configured to perform weighted fusion processing on the first classification result and the second classification result, so as to obtain a final classification result;
the prognosis prediction model includes: the pancreatitis grading prediction model comprises the following training method:
acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise mild pancreatitis, moderate pancreatitis and severe pancreatitis;
performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed pancreatitis grading prediction model.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of processing pancreatitis prognosis data as described above.
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 invention in detail, those skilled in the art will appreciate that the foregoing description is not meant to limit the invention thereto, as long as the scope of the invention is defined by the claims appended hereto.
Claims (15)
1. A method of processing pancreatitis prognosis data, comprising:
acquiring human body basic sign data of a sample; the human body basic sign data includes: whether the consciousness score is full;
Inputting the human body basic sign data into a pre-trained prognosis prediction model to obtain a first classification result; calculating a grading value of a prognosis classification index based on the human body basic sign data, and obtaining a second classification result according to the grading value; the prognostic classification indicator includes: grading pancreatitis;
carrying out weighted fusion processing on the first classification result and the second classification result to obtain a final classification result;
the prognosis prediction model includes: a pancreatitis grading prediction model; the training method of the pancreatitis grading prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise mild pancreatitis, moderate pancreatitis and severe pancreatitis; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed pancreatitis grading prediction model; the prognostic classification indicator further includes: whether or not to die; the prognosis prediction model further includes: a death prediction model; the training method of the death prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise dead and non-dead; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed death prediction model;
The prognostic classification indicator further includes: whether or not to infect necrosis; the prognosis prediction model further includes: infection necrosis prediction model; the training method of the infection necrosis prediction model comprises the following steps: acquiring human body basic sign data and classification labels of a training set sample, wherein the labels comprise infection necrosis and uninfected necrosis; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the characteristics of the human body basic sign data to obtain a constructed infection necrosis prediction model;
the prognostic classification indicator further includes: grading the hospitalization duration; the prognosis prediction model further includes: a hospital stay prediction model; the training method of the hospitalization duration prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise a first hospitalization duration and a second hospitalization duration; a first length of stay less than or equal to the classification threshold, and a second length of stay greater than or equal to the classification threshold; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed hospital stay prediction model;
The prognostic classification indicator further includes: whether to check in the ICU; the prognosis prediction model further includes: ICU prediction model; the training method of the ICU prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise an in-check ICU and an out-of-check ICU; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed ICU prediction model.
2. The method of claim 1, wherein the scoring values include one or more of the following: APACHE-II score, marshall score, sofa score, qsfa score, bisap score.
3. The method for processing pancreatitis prognosis data according to claim 1, characterized in that the training method of the pancreatitis gradation prediction model further comprises:
sequencing the human body basic sign data features to obtain sequenced human body basic sign data features;
and constructing a model by using the human body basic sign data characteristics subjected to the sorting treatment to obtain a constructed pancreatitis grading prediction model.
4. A method of processing pancreatitis prognosis data according to claim 3, characterized in that the sorting process comprises: for one of the human body basic sign data features subjected to feature extraction, calculating all combinations and marginal contribution of a single human body basic sign data feature in the combinations according to a combination sequence formed by the human body basic sign data features; obtaining the contribution degree of a single human body basic sign data characteristic in the human body basic sign data characteristics according to the marginal contribution; and sequencing the human body basic sign data features based on the contribution degrees, and outputting N human body basic sign data features with high contribution degrees.
5. The method of claim 4, wherein N is at least 5.
6. The method of claim 1, wherein the first classification result comprises: mild pancreatitis, moderate pancreatitis, and severe pancreatitis.
7. The method of claim 1, wherein the second classification result comprises: mild pancreatitis, moderate pancreatitis, and severe pancreatitis.
8. The method of claim 1, wherein the human underlying sign data comprises one or more of the following: age, sex, cause, body temperature, blood pressure, heart rate, respiratory rate, white blood cells, hematocrit, platelets, potassium, sodium, calcium, creatinine, urea nitrogen, whether there is a peritoneal irritation, whether there is pleural effusion.
9. The method for processing pancreatitis prognosis data according to claim 1, characterized in that the human basic sign data is model-constructed by a machine learning method to obtain a constructed prognosis prediction model.
10. The method of claim 9, wherein the machine learning method comprises one or more of the following: linear regression, logistic regression, linear Discriminant Analysis (LDA), classification and regression trees, naive bayes, KNN, learning vector quantization, support Vector Machine (SVM), random forest, lightGBM.
11. The method for processing pancreatitis prognosis data according to claim 10, characterized in that the machine learning method is: weighted fusion of any two of the algorithms described above.
12. The method for processing pancreatitis prognosis data according to claim 11, characterized in that the machine learning method is: weighted fusion of random forest and LightGBM.
13. An apparatus for processing pancreatitis prognosis data, the apparatus 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 method of processing pancreatitis prognosis data according to any of claims 1-12.
14. A system for processing pancreatitis prognosis data, comprising:
the acquisition unit is used for acquiring the human body basic sign data of the sample; the human body basic sign data includes: whether the consciousness score is full;
the first classification unit is used for inputting the human body basic sign data into a pre-trained prognosis prediction model to obtain a first classification result;
the second classification unit is used for calculating a grading value of a prognosis classification index based on the human body basic sign data and obtaining a second classification result according to the grading value; the prognostic classification indicator includes: grading pancreatitis;
the third classification unit is used for carrying out weighted fusion processing on the first classification result and the second classification result to obtain a final classification result;
The prognosis prediction model includes: the pancreatitis grading prediction model comprises the following training method: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise mild pancreatitis, moderate pancreatitis and severe pancreatitis; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction;
constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed pancreatitis grading prediction model;
the prognostic classification indicator further includes: whether or not to die; the prognosis prediction model further includes: a death prediction model; the training method of the death prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise dead and non-dead; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed death prediction model;
the prognostic classification indicator further includes: whether or not to infect necrosis; the prognosis prediction model further includes: infection necrosis prediction model; the training method of the infection necrosis prediction model comprises the following steps: acquiring human body basic sign data and classification labels of a training set sample, wherein the labels comprise infection necrosis and uninfected necrosis; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the characteristics of the human body basic sign data to obtain a constructed infection necrosis prediction model;
The prognostic classification indicator further includes: grading the hospitalization duration; the prognosis prediction model further includes: a hospital stay prediction model; the training method of the hospitalization duration prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise a first hospitalization duration and a second hospitalization duration; a first length of stay less than or equal to the classification threshold, and a second length of stay greater than or equal to the classification threshold; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed hospital stay prediction model;
the prognostic classification indicator further includes: whether to check in the ICU; the prognosis prediction model further includes: ICU prediction model; the training method of the ICU prediction model comprises the following steps: acquiring human basic sign data and classification labels of a training set sample, wherein the labels comprise an in-check ICU and an out-of-check ICU; performing feature extraction on the human body basic sign data of the training set sample to obtain human body basic sign data features after feature extraction; and constructing a model by utilizing the human body basic sign data characteristics to obtain a constructed ICU prediction model.
15. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements a method for processing pancreatitis prognosis data according to any of the preceding claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210908379.0A CN115240854B (en) | 2022-07-29 | 2022-07-29 | Pancreatitis prognosis data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210908379.0A CN115240854B (en) | 2022-07-29 | 2022-07-29 | Pancreatitis prognosis data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115240854A CN115240854A (en) | 2022-10-25 |
| CN115240854B true CN115240854B (en) | 2023-10-03 |
Family
ID=83677647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210908379.0A Active CN115240854B (en) | 2022-07-29 | 2022-07-29 | Pancreatitis prognosis data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115240854B (en) |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002086478A2 (en) * | 2001-04-23 | 2002-10-31 | Metabometrix Limited | Methods for analysis of spectral data and their applications |
| CN1973778A (en) * | 2006-12-08 | 2007-06-06 | 南京大学 | Method of predicting serious complication risk degree after gastric cancer operation |
| WO2015042421A1 (en) * | 2013-09-20 | 2015-03-26 | Siemens Aktiengesellschaft | Biopsy-free detection and staging of cancer using a virtual staging score |
| CN108537773A (en) * | 2018-02-11 | 2018-09-14 | 中国科学院苏州生物医学工程技术研究所 | Intelligence auxiliary mirror method for distinguishing is carried out for cancer of pancreas and pancreas inflammatory disease |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN109637663A (en) * | 2018-11-14 | 2019-04-16 | 浙江大学山东工业技术研究院 | A kind of prediction meanss of the percutaneous coronary intervention (pci) Cardia cevent based on machine learning |
| WO2020008365A2 (en) * | 2018-07-02 | 2020-01-09 | 3M Innovative Properties Company | Transferring learning in classifier-based sensing systems |
| CN111081377A (en) * | 2020-01-16 | 2020-04-28 | 四川大学 | Necrotic acute pancreatitis patient operation time prediction model |
| WO2020163589A1 (en) * | 2019-02-08 | 2020-08-13 | Genentech, Inc. | Diagnostic and therapeutic methods for cancer |
| WO2020249125A1 (en) * | 2019-06-14 | 2020-12-17 | 第四范式（北京）技术有限公司 | Method and system for automatically training machine learning model |
| JPWO2021020198A1 (en) * | 2019-07-26 | 2021-02-04 | ||
| CN112633601A (en) * | 2020-12-31 | 2021-04-09 | 天津开心生活科技有限公司 | Method, device, equipment and computer medium for predicting disease event occurrence probability |
| CN112992346A (en) * | 2021-04-09 | 2021-06-18 | 中山大学附属第三医院（中山大学肝脏病医院） | Method for establishing prediction model for prognosis of severe spinal cord injury |
| CN113724876A (en) * | 2021-09-10 | 2021-11-30 | 南昌大学第二附属医院 | Intra-stroke hospital complication prediction model based on multi-mode fusion and DFS-LLE algorithm |
| CA3181163A1 (en) * | 2020-06-03 | 2021-12-09 | Rachel Elizabeth KAST | Electronic health record (ehr)-based classifier for acute respiratory distress syndrome (ards) subtyping |
| CN113871009A (en) * | 2021-09-27 | 2021-12-31 | 山东师范大学 | Sepsis prediction system, storage medium and apparatus in intensive care unit |
| CN113903460A (en) * | 2021-12-10 | 2022-01-07 | 中国医学科学院北京协和医院 | System for predicting severe acute pancreatitis and application thereof |
| CN113948211A (en) * | 2021-11-04 | 2022-01-18 | 复旦大学附属中山医院 | Prediction model for noninvasive quantitative assessment of postoperative concurrent pancreatic fistula risk before pancreas resection |
| CN114141363A (en) * | 2021-12-07 | 2022-03-04 | 川北医学院附属医院 | Severe pancreatitis prediction model construction method based on machine learning method |
| WO2022060883A1 (en) * | 2020-09-16 | 2022-03-24 | Seattle Children's Hospital D/B/A Seattle Children's Research Institute | Diagnostic methods for kawasaki disease |
| FI20205993A1 (en) * | 2020-10-09 | 2022-04-10 | Datahammer Oy | Training of computerized mode and non-invasive detection of a life-threatening condition using the trained computerized model |
| CN114550930A (en) * | 2022-02-18 | 2022-05-27 | 平安国际智慧城市科技股份有限公司 | Disease prediction method, device, equipment and storage medium |
| WO2022116914A1 (en) * | 2020-12-03 | 2022-06-09 | Ping An Technology (Shenzhen) Co., Ltd. | Method, device, and storage medium for pancreatic mass segmentation, diagnosis, and quantitative patient management |
| 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 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050130321A1 (en) * | 2001-04-23 | 2005-06-16 | Nicholson Jeremy K. | Methods for analysis of spectral data and their applications |
| US20180166174A1 (en) * | 2016-08-02 | 2018-06-14 | Thomas J. Lewis | Disease Mitigation and Elimination Health Learning Engine |
| CA3095056A1 (en) * | 2018-04-13 | 2019-10-17 | Freenome Holdings, Inc. | Machine learning implementation for multi-analyte assay of biological samples |
| US20220076828A1 (en) * | 2020-09-10 | 2022-03-10 | Babylon Partners Limited | Context Aware Machine Learning Models for Prediction |
-
2022
- 2022-07-29 CN CN202210908379.0A patent/CN115240854B/en active Active
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002086478A2 (en) * | 2001-04-23 | 2002-10-31 | Metabometrix Limited | Methods for analysis of spectral data and their applications |
| CN1973778A (en) * | 2006-12-08 | 2007-06-06 | 南京大学 | Method of predicting serious complication risk degree after gastric cancer operation |
| WO2015042421A1 (en) * | 2013-09-20 | 2015-03-26 | Siemens Aktiengesellschaft | Biopsy-free detection and staging of cancer using a virtual staging score |
| CN108537773A (en) * | 2018-02-11 | 2018-09-14 | 中国科学院苏州生物医学工程技术研究所 | Intelligence auxiliary mirror method for distinguishing is carried out for cancer of pancreas and pancreas inflammatory disease |
| WO2020008365A2 (en) * | 2018-07-02 | 2020-01-09 | 3M Innovative Properties Company | Transferring learning in classifier-based sensing systems |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN109637663A (en) * | 2018-11-14 | 2019-04-16 | 浙江大学山东工业技术研究院 | A kind of prediction meanss of the percutaneous coronary intervention (pci) Cardia cevent based on machine learning |
| WO2020163589A1 (en) * | 2019-02-08 | 2020-08-13 | Genentech, Inc. | Diagnostic and therapeutic methods for cancer |
| WO2020249125A1 (en) * | 2019-06-14 | 2020-12-17 | 第四范式（北京）技术有限公司 | Method and system for automatically training machine learning model |
| JPWO2021020198A1 (en) * | 2019-07-26 | 2021-02-04 | ||
| CN111081377A (en) * | 2020-01-16 | 2020-04-28 | 四川大学 | Necrotic acute pancreatitis patient operation time prediction model |
| CA3181163A1 (en) * | 2020-06-03 | 2021-12-09 | Rachel Elizabeth KAST | Electronic health record (ehr)-based classifier for acute respiratory distress syndrome (ards) subtyping |
| WO2022060883A1 (en) * | 2020-09-16 | 2022-03-24 | Seattle Children's Hospital D/B/A Seattle Children's Research Institute | Diagnostic methods for kawasaki disease |
| FI20205993A1 (en) * | 2020-10-09 | 2022-04-10 | Datahammer Oy | Training of computerized mode and non-invasive detection of a life-threatening condition using the trained computerized model |
| WO2022116914A1 (en) * | 2020-12-03 | 2022-06-09 | Ping An Technology (Shenzhen) Co., Ltd. | Method, device, and storage medium for pancreatic mass segmentation, diagnosis, and quantitative patient management |
| CN112633601A (en) * | 2020-12-31 | 2021-04-09 | 天津开心生活科技有限公司 | Method, device, equipment and computer medium for predicting disease event occurrence probability |
| CN112992346A (en) * | 2021-04-09 | 2021-06-18 | 中山大学附属第三医院（中山大学肝脏病医院） | Method for establishing prediction model for prognosis of severe spinal cord injury |
| CN113724876A (en) * | 2021-09-10 | 2021-11-30 | 南昌大学第二附属医院 | Intra-stroke hospital complication prediction model based on multi-mode fusion and DFS-LLE algorithm |
| CN113871009A (en) * | 2021-09-27 | 2021-12-31 | 山东师范大学 | Sepsis prediction system, storage medium and apparatus in intensive care unit |
| CN113948211A (en) * | 2021-11-04 | 2022-01-18 | 复旦大学附属中山医院 | Prediction model for noninvasive quantitative assessment of postoperative concurrent pancreatic fistula risk before pancreas resection |
| CN114141363A (en) * | 2021-12-07 | 2022-03-04 | 川北医学院附属医院 | Severe pancreatitis prediction model construction method based on machine learning method |
| CN113903460A (en) * | 2021-12-10 | 2022-01-07 | 中国医学科学院北京协和医院 | System for predicting severe acute pancreatitis and application thereof |
| CN114550930A (en) * | 2022-02-18 | 2022-05-27 | 平安国际智慧城市科技股份有限公司 | Disease prediction method, device, equipment and storage medium |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| 急性胰腺炎的严重程度及预后评估的研究进展;丁宁;周阳;杨贵芳;柴湘平;;实用休克杂志(中英文)(第01期);全文 * |
| 李福增.现代创伤医学.吉林科学技术出版社,2007,第347页. * |
| 阿杰伊·K·辛格.胃肠影像学精要.中国科学技术出版社,2018,第231页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115240854A (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gjoreski et al. | Machine learning and end-to-end deep learning for the detection of chronic heart failure from heart sounds | |
| Arumugam et al. | Multiple disease prediction using Machine learning algorithms | |
| Ali | Stroke prediction using distributed machine learning based on apache spark | |
| Kamadi et al. | A computational intelligence technique for the effective diagnosis of diabetic patients using principal component analysis (PCA) and modified fuzzy SLIQ decision tree approach | |
| Varma et al. | A computational intelligence approach for a better diagnosis of diabetic patients | |
| Sun et al. | Prediction of cardiovascular diseases based on machine learning | |
| Barhoom et al. | Prediction of Heart Disease Using a Collection of Machine and Deep Learning Algorithms | |
| CN116364299B (en) | Disease diagnosis and treatment path clustering method and system based on heterogeneous information network | |
| Jamshidi et al. | Symptom prediction and mortality risk calculation for COVID-19 using machine learning | |
| Al-Mualemi et al. | A deep learning-based sepsis estimation scheme | |
| Yang et al. | Predicting coronary heart disease using an improved LightGBM model: Performance analysis and comparison | |
| Pavithra et al. | Hybrid feature selection technique for prediction of cardiovascular diseases | |
| Pradhan et al. | Diabetes mellitus prediction and classifier comparitive study | |
| Adi et al. | Stroke risk prediction model using machine learning | |
| Maheshwari et al. | A comprehensive evaluation for the prediction of mortality in intensive care units with LSTM networks: patients with cardiovascular disease | |
| Pereira et al. | Fuzzy modeling to predict severely depressed left ventricular ejection fraction following admission to the intensive care unit using clinical physiology | |
| Shukla et al. | Cloud computing with artificial intelligence techniques for effective disease detection | |
| Jaganathan et al. | Machine learning for smartphone-based early detection of diabetic disease in Pima Indians diabetes database | |
| CN115240854B (en) | Pancreatitis prognosis data processing method and system | |
| Nazlı et al. | Classification of Coronary Artery Disease Using Different Machine Learning Algorithms | |
| Siddiqa et al. | Robust Length of Stay Prediction Model for Indoor Patients. | |
| Riadi et al. | A Comparative Study of Machine Learning Methods for Baby Cry Detection Using MFCC Features | |
| Sonia et al. | An empirical evaluation of benchmark machine learning classifiers for risk prediction of cardiovascular disease in diabetic males | |
| CN115331819A (en) | Pancreatitis prognosis data processing method and system based on artificial intelligence | |
| Riyaz et al. | Improving coronary heart disease prediction by outlier elimination |
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 |