Granule calculation-based new myocardial infarction grading and classification prediction method and device

Abstract

The invention discloses a new myocardial infarction grading and classifying prediction method and device based on granulocyte calculation. The method comprises the following steps: establishing a new myocardial infarction patient sample from real clinical data; respectively carrying out single-feature modeling analysis on the plurality of clinical features through an xgboost model to obtain an AUROC value, and reserving a plurality of first clinical features; modeling the plurality of clinical features through a plurality of tree models, outputting a feature importance score of each tree model, and retaining a plurality of second clinical features; performing intersection processing on the first clinical feature and the second clinical feature to obtain a target clinical feature; an integrated model is constructed and trained; the feature importance degree score of the trained integrated model is output, a set number of clinical features ranked in the front are subjected to modeling analysis again, the feature importance degree score of a new model is output, and the most important clinical features are screened out according to the feature importance degree score; and verifying the new model through internal and external data. According to the method, the data collection cost can be reduced, and the robustness of the model is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical artificial intelligence technology, and in particular to a method and device for predicting the grading and classification of new myocardial infarction based on granular computing. Background Art

[0002] Myocardial infarction (MI) is an acute cardiovascular disease that seriously threatens human health, and its morbidity and mortality rates remain high worldwide. Despite the continuous advancement of medical technology in recent years, the prognosis of patients with myocardial infarction is still not optimistic, especially the acute mortality rate and long-term disability rate are still high. Accurate and timely grading and classification of new myocardial infarction is crucial for optimizing treatment plans and improving patient prognosis. At present, the diagnosis and grading of myocardial infarction mainly rely on traditional methods such as electrocardiogram and myocardial enzyme spectrum in clinical practice, but these methods have certain limitations.

[0003] In recent years, with the rapid development of artificial intelligence technology, myocardial infarction prediction models based on machine learning, deep learning and other methods have gradually emerged. At present, although there are many machine learning-based methods for risk prediction of myocardial infarction, and have achieved good performance. However, they either require all the patient's examination data upon admission, or require the collection of additional multimodal data such as electrocardiograms, which is expensive and time-consuming for each patient. Granular computing, as an emerging computing model, can effectively process complex, uncertain and incomplete information, providing a new idea for solving the above problems.

[0004] Therefore, the prediction of the grading and classification of new myocardial infarction remains challenging. Existing methods cannot effectively screen out the important features of new myocardial infarction in clinical applications, and there is a lack of a simple, accurate and robust machine learning method. Summary of the invention

[0005] To this end, the present invention provides a new myocardial infarction classification prediction method and device based on granular computing, which can effectively screen out the important features of new myocardial infarction in clinical applications. At the same time, it reduces the cost of collecting data and improves the robustness of the model.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for predicting the grading and classification of new myocardial infarction based on granular computing, comprising:

[0007] Collect and obtain basic information and laboratory test data of several patients from real clinical data; screen the collected basic information and laboratory test data of the patients to establish a sample cohort of patients with new myocardial infarction;

[0008] Performing single-feature modeling analysis on a plurality of clinical features respectively through the xgboost model to obtain the AUROC value of each clinical feature; selecting and retaining a plurality of first clinical features according to the AUROC value and the first selection strategy;

[0009] Modeling the plurality of clinical features through a plurality of tree models, and outputting feature importance scores of each of the tree models respectively; selecting and retaining a plurality of second clinical features according to the feature importance scores and a second selection strategy;

[0010] Performing intersection processing on a plurality of the first clinical features and a plurality of the second clinical features to obtain a plurality of target clinical features;

[0011] Building an integrated model based on the automatic machine learning framework AutoGluon; training the integrated model through the target clinical features to obtain a trained integrated model;

[0012] The target clinical features are analyzed by the trained integrated model, and the feature importance scores of the trained integrated model are output; the target clinical features are sorted according to the feature importance scores of the integrated model, and a set number of clinical features that are ranked in front are remodeled and analyzed, and the feature importance scores of the newly created model are output; when the feature importance scores of the newly created model and the feature importance scores of the integrated model meet the set requirements, the most important clinical features are screened out;

[0013] The newly created model was validated by internal and external data to evaluate the robustness of the newly created model and the effectiveness of the most important clinical features.

[0014] As a preferred embodiment of the method for grading and classifying prediction of new myocardial infarction based on granular computing, in the process of screening the collected basic information of the patients and the laboratory test data to establish the sample cohort of patients with new myocardial infarction, samples with new myocardial infarction are screened out from the basic information of the patients and the laboratory test data; samples with data missing rate greater than 20% among the screened samples are deleted to establish the sample cohort of patients with new myocardial infarction.

[0015] As a preferred scheme of the prediction method for the grading and classification of new myocardial infarction based on particle physics calculation, in the process of selecting and retaining a number of the first clinical characteristics according to the AUROC value and the first selection strategy, the first selection strategy is: retaining clinical characteristics with AUROC values ​​greater than 0.5.

[0016] As a preferred scheme of the new myocardial infarction grading and classification prediction method based on particle granular computing, in the process of modeling several clinical characteristics through several tree models, the tree models include: xgboost, catboost and lightgbm tree models; the second selection strategy is: retaining the clinical characteristics whose feature importance scores of the three tree models of xgboost, catboost and lightgbm are all greater than 0.

[0017] As a preferred solution of the new myocardial infarction classification prediction method based on particle computing, in the process of training the integrated model by the target clinical features, the training steps are:

[0018] The integrated model applies a separate embedding layer to each of the target clinical features and concatenates them with the numerical features into a large vector;

[0019] Using a multi-layer stack integration strategy, a set of basic models are trained separately in a common manner to obtain aggregated prediction results; the aggregated prediction results are used as features of the basic models to train the integrated model;

[0020] Based on the granular computing strategy, the target clinical characteristics are decomposed into several data sets; each of the data sets is further divided into a training subset and a validation subset; several of the training subsets or several of the validation subsets are merged into a final training subset or a final validation subset; and the integrated model is subjected to multi-granularity cross-validation through the final training subset and the final validation subset.

[0021] The present invention also provides a device for predicting the grading and classification of new myocardial infarction based on granular computing, which comprises:

[0022] A data screening module is used to collect basic information and laboratory test data of several patients from real clinical data; screen the collected basic information and laboratory test data of the patients to establish a sample cohort of new myocardial infarction patients;

[0023] A first clinical feature screening module is used to perform single feature modeling analysis on a plurality of clinical features respectively through an xgboost model to obtain an AUROC value for each of the clinical features; and select and retain a plurality of first clinical features according to the AUROC value and a first selection strategy;

[0024] A second clinical feature screening module is used to model the plurality of clinical features through a plurality of tree models, and output a feature importance score of each of the tree models respectively; and select and retain a plurality of second clinical features according to the feature importance score and a second selection strategy;

[0025] a target clinical feature acquisition module, used for performing intersection processing on a plurality of the first clinical features and a plurality of the second clinical features to obtain a plurality of target clinical features;

[0026] An integrated model construction and training module, used to construct an integrated model based on the automatic machine learning framework AutoGluon; train the integrated model through the target clinical features to obtain a trained integrated model;

[0027] The most important clinical feature screening module is used to analyze the target clinical features through the trained integrated model, and output the feature importance score of the trained integrated model; sort the target clinical features according to the feature importance score of the integrated model, and remodel and analyze the clinical features that are ranked in the front by a set number, and output the feature importance score of the newly created model; when the feature importance score of the newly created model and the feature importance score of the integrated model meet the set requirements, the most important clinical features are screened out;

[0028] The newly-created model verification module is used to verify the newly-created model through internal and external data, and to evaluate the robustness of the newly-created model and the effectiveness of the most important clinical features.

[0029] As a preferred embodiment of the device for grading and classifying new myocardial infarction based on granular computing, in the data screening module, in the process of screening the collected basic information of the patient and the laboratory test data to establish the sample cohort of new myocardial infarction patients, samples with new myocardial infarction are screened out from the basic information of the patient and the laboratory test data; samples with data missing rate greater than 20% among the screened samples are deleted to establish the sample cohort of new myocardial infarction patients.

[0030] As a preferred embodiment of the device for predicting the grading and classification of new myocardial infarction based on particle physics, in the first clinical feature screening module, in the process of selecting and retaining a number of the first clinical features according to the AUROC value and the first selection strategy, the first selection strategy is: retaining clinical features with AUROC values ​​greater than 0.5.

[0031] As a preferred solution of the device for predicting the grading and classification of new myocardial infarction based on particle computing, in the second clinical feature screening module, in the process of modeling the several clinical features through the several tree models, the tree models include: xgboost, catboost and lightgbm tree models; the second selection strategy is: retaining the clinical features whose feature importance scores of the three tree models of xgboost, catboost and lightgbm are all greater than 0.

[0032] As a preferred solution of the device for predicting the grading and classification of new myocardial infarction based on particle computing, in the integrated model construction and training module, the training submodule includes:

[0033] A large vector generation submodule, used for the integrated model to apply a separate embedding layer to each of the target clinical features and connect them with the numerical features into a large vector;

[0034] A multi-layer stack integration training submodule is used to use a multi-layer stack integration strategy to train a group of basic models separately in a common way to obtain an aggregated prediction result; and use the aggregated prediction result as a feature of the basic model to train the integrated model;

[0035] The granular computing training submodule is used to decompose the target clinical characteristics into several data sets based on the granular computing strategy; each of the data sets is further divided into a training subset and a validation subset; several of the training subsets or several of the validation subsets are merged into a final training subset or a final validation subset; and the integrated model is cross-validated at multiple granularities through the final training subset and the final validation subset.

[0036] The present invention has the following advantages: the present invention collects and obtains basic information and laboratory test data of several patients from real clinical data; screens the collected basic information and laboratory test data of the patients to establish a sample cohort of newly diagnosed myocardial infarction patients; performs single feature modeling analysis on several clinical features through the xgboost model to obtain the AUROC value of each clinical feature; selects and retains several first clinical features according to the AUROC value; models several clinical features through several tree models, and outputs the feature importance score of each tree model; selects and retains several second clinical features according to the second selection strategy according to the feature importance score; performs intersection processing on several first clinical features and several second clinical features to obtain several target features. The target clinical features are selected; an integrated model is constructed based on the automatic machine learning framework AutoGluon; the integrated model is trained by the target clinical features to obtain a trained integrated model; the target clinical features are analyzed by the trained integrated model, and the feature importance score of the trained integrated model is output; the target clinical features are sorted according to the feature importance score of the integrated model, and the clinical features with a set number of features in front are remodeled and analyzed, and the feature importance score of the newly created model is output; when the feature importance score of the newly created model and the feature importance score of the integrated model meet the set requirements, the most important clinical features are screened out; the newly created model is verified by internal and external data to evaluate the robustness of the newly created model and the effectiveness of the most important clinical features. The present invention solves the challenges of high cost of clinical data collection in the classification and prediction of new myocardial infarction. By modeling and analyzing a large number of clinical features of patients, the important features of the occurrence of new myocardial infarction in clinical applications are accurately screened out based on the granular computing method; the new myocardial infarction classification prediction model constructed by this method only needs to input common clinical features of patients (such as blood routine), which reduces the cost of data collection and improves the robustness of the model. The present invention introduces automatic machine learning, multi-layer stack integration strategy and granular computing data partitioning method to further improve the accuracy and robustness of the model; the present invention has stable performance in both internal and external validation sets collected from real clinical cases. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0038] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0039] Figure 1 This is a schematic diagram of the process flow of the new myocardial infarction classification prediction method based on particle computing provided in Example 1 of the present invention;

[0040] Figure 2 This is a schematic diagram of a specific implementation process of the method for grading and classifying new myocardial infarction based on particle computing provided in Example 1 of the present invention;

[0041] Figure 3 It is a schematic diagram illustrating the multi-layer stack integration strategy and the granular computing strategy in the granular computing-based prediction method for new myocardial infarction classification provided in Example 1 of the present invention;

[0042] Figure 4 This is a schematic diagram of the importance ranking of the integrated model features in the new myocardial infarction classification prediction method based on granular computing provided in Example 1 of the present invention;

[0043] Figure 5 A schematic diagram of the AUROC value of the newly created model in the test set in the new myocardial infarction classification prediction method based on particle computing provided in Example 1 of the present invention;

[0044] Figure 6 This is a schematic diagram of the architecture of the device for predicting the grading and classification of new myocardial infarction based on granular computing provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0045] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Example 1

[0047] See also Figure 1 and Figure 2 Embodiment 1 of the present invention provides a method for predicting the classification of newly-occurring myocardial infarction based on granular computing, comprising the following steps:

[0048] S1. Collect basic information and laboratory test data of several patients from real clinical data; screen the collected basic information and laboratory test data of the patients to establish a sample cohort of patients with new myocardial infarction;

[0049] S2. Perform single feature modeling analysis on a plurality of clinical features respectively through the xgboost model to obtain the AUROC value of each clinical feature; and select and retain a plurality of first clinical features according to the AUROC value and the first selection strategy;

[0050] S3, modeling the plurality of clinical features through a plurality of tree models, and outputting the feature importance score of each of the tree models respectively; and selecting and retaining a plurality of second clinical features according to the feature importance score and a second selection strategy;

[0051] S4, performing intersection processing on a plurality of the first clinical characteristics and a plurality of the second clinical characteristics to obtain a plurality of target clinical characteristics;

[0052] S5. Building an integrated model based on the automatic machine learning framework AutoGluon; training the integrated model through the target clinical features to obtain a trained integrated model;

[0053] S6. Analyze the target clinical features through the trained integrated model, and output the feature importance score of the trained integrated model; sort the target clinical features according to the feature importance score of the integrated model, and remodel and analyze the clinical features that are ranked in the front by a set number, and output the feature importance score of the newly created model; when the feature importance score of the newly created model and the feature importance score of the integrated model meet the set requirements, screen out the most important clinical features;

[0054] S7. Verify the newly created model through internal and external data to evaluate the robustness of the newly created model and the effectiveness of the most important clinical features.

[0055] In this embodiment, in step S1, basic information and laboratory test data of several patients are collected from real clinical data; the collected basic information and laboratory test data of the patients are screened to establish a sample cohort of newly diagnosed myocardial infarction patients;

[0056] Among them, in the process of screening the collected basic information of the patients and the laboratory test data to establish the sample cohort of patients with new myocardial infarction, samples with new myocardial infarction are screened out from the basic information of the patients and the laboratory test data; samples with a data missing rate greater than 20% among the screened samples are deleted to establish the sample cohort of patients with new myocardial infarction.

[0057] Specifically, 102 clinical characteristics of 3556 patients were collected from real clinical practice, of which 1018 (28.6%) patients had new-onset myocardial infarction in the hospital, and the remaining patients did not have myocardial infarction; samples with missing rates greater than 20% in the data were deleted, and finally 3419 patients were obtained.

[0058] In this embodiment, in step S2, single feature modeling analysis is performed on a plurality of clinical features respectively through the xgboost model to obtain the AUROC value of each clinical feature; according to the AUROC value, a plurality of first clinical features are selected and retained according to the first selection strategy;

[0059] Specifically, the xgboost model was used to perform single-feature modeling analysis on 102 clinical features. Only one feature was used for model training and testing each time. Each feature was randomly sampled 10-fold based on the bootstrap method. Then, the test was performed on the test set, and the receiver operating characteristic curve was plotted and the AUROC value was calculated. The AUROC value of each clinical feature when it was modeled separately was obtained, and clinical features with AUROC greater than 0.5 were retained.

[0060] Specifically, clinical characteristics such as B-type brain natriuretic peptide precursor, mean platelet area, urine glucose, and lymphocyte percentage had high AUROC performance, while clinical characteristics such as liver function total protein and electrolyte potassium had AUROC less than 0.5.

[0061] In this embodiment, in step S3, a plurality of clinical features are modeled by a plurality of tree models, and feature importance scores of each of the tree models are output respectively; based on the feature importance scores, a plurality of second clinical features are selected and retained according to a second selection strategy;

[0062] Specifically, three tree models, xgboost, catboost and lightgbm, are used to model 102 features, and then the feature importance scores of the models are output respectively;

[0063] The clinical features whose feature importance scores in all three tree models were greater than 0 were retained, including myocardial enzyme creatine kinase, stool routine_red blood cells, hemoglobin and other clinical features.

[0064] In this embodiment, in step S4, a plurality of the first clinical features and a plurality of the second clinical features are subjected to intersection processing to obtain a plurality of target clinical features;

[0065] Specifically, the clinical features with AUROC greater than 0.5 and feature importance scores greater than 0 in step S2 and step S3 are retained, and the remaining features are deleted from the data set to obtain several target clinical features;

[0066] Specifically, a total of 12 data that produced noise to the model were deleted, and the remaining 90 clinical features were further used for subsequent modeling.

[0067] In this embodiment, in step S5, an integrated model is constructed based on the automatic machine learning framework AutoGluon; the integrated model is trained by the target clinical features to obtain a trained integrated model;

[0068] Among them, Figure 3 As shown, in the process of training the integrated model by the target clinical features, the training steps are:

[0069] S51, the integrated model applies a separate embedding layer to each of the target clinical features and connects them with the numerical features into a large vector;

[0070] Specifically, based on the clinical features screened in step S4, the automatic machine learning framework AutoGluon is applied to further model and construct an integrated model; the integrated model applies a separate embedding layer to each categorical feature (such as gender), and then connects it with the numerical features (such as age) into a large vector.

[0071] S52, using a multi-layer stack integration strategy, training a group of basic models separately in a common manner to obtain an aggregated prediction result; using the aggregated prediction result as a feature of the basic model to train the integrated model;

[0072] Specifically, a multi-layer stacking integration strategy is used to first train a set of separate base models in a general manner, and then the aggregated predictions of the base models are used as their features to train the stacker model. The stacker model can improve the shortcomings of a single basic prediction and utilize the interactions between the basic models to provide enhanced predictive capabilities.

[0073] S53. Based on the granular computing strategy, the target clinical characteristics are decomposed into several data sets; each of the data sets is further divided into a training subset and a validation subset; several of the training subsets or several of the validation subsets are merged into a final training subset or a final validation subset; and the integrated model is cross-validated at multiple granularities through the final training subset and the final validation subset.

[0074] Specifically, based on the granular computing strategy, the data set is decomposed into multiple data sets, each of which is further divided into a training subset and a validation subset (i.e., the granulation process). Then, multiple training subsets or validation subsets are merged into the final training subset or validation subset (i.e., the organization process). This method enables the data set to form a multi-granularity hierarchical structure, and multi-granularity cross-validation is performed on the integrated model.

[0075] In this embodiment, in step S6, the target clinical features are analyzed by the trained integrated model, and the feature importance scores of the trained integrated model are output; the target clinical features are sorted according to the feature importance scores of the integrated model, and the clinical features that are ranked in the front by a set number are remodeled and analyzed, and the feature importance scores of the newly created model are output; when the feature importance scores of the newly created model and the feature importance scores of the integrated model meet the set requirements, the most important clinical features are screened out;

[0076] Specifically, according to the trained integrated model obtained in step S5, its feature importance score is output, and the features with the highest feature importance are modeled and tested separately in turn; the target clinical features are sorted according to the feature importance scores of the integrated model, and the clinical features with a set number of features in the front are remodeled and analyzed, and the feature importance score of the newly created model is output; when the feature importance score of the newly created model and the feature importance score of the integrated model meet the set requirements, the most important clinical features are screened out; Figure 4 As shown in the figure, when the top 22 features in terms of feature importance were retained, the performance of the new model was comparable to that of the integrated model. Finally, these 20 clinical features were selected as input features for predicting the risk of new myocardial infarction, including "myocardial enzyme 0 lactate dehydrogenase, systolic blood pressure, myocardial enzyme 0 creatine kinase, hepatitis B virus surface antigen, coagulation complete set_quantitative fibrinogen, percentage of large platelets, age, liver function_white / globulin ratio, liver function_aspartate aminotransferase, myocardial enzyme 0 myoglobin, B-type brain natriuretic peptide precursor, hemoglobin, urine sediment urobilinogen, renal function_uric acid, coagulation complete set_*PT international normalized ratio, stool routine_red blood cells, stool routine_character, urine sediment specific gravity, low-density lipoprotein cholesterol, liver function_alanine aminotransferase, urine sediment transparent casts and liver function_globulin".

[0077] In this embodiment, in step S7, the newly created model is verified by internal and external data to evaluate the robustness of the newly created model and the effectiveness of the most important clinical features.

[0078] Specifically, the newly created model trained with 22 clinical features in step S6 was used to test the external validation to evaluate the robustness of the model and the effectiveness of the screening features. The final evaluation results are as follows: Figure 5 As shown, the area under the receiver operating characteristic curve (AUROC, or AUC) of the model in the external validation set, that is, the area of ​​the cyan line in the figure is 0.915, which indicates that the machine learning model constructed by the present invention can also perform well in the external validation set and has good generalization performance.

[0079] In a possible embodiment, a verification example is provided as follows:

[0080] As shown in Table 1, the comparison results between the learning model constructed by the present invention and other classic machine learning models are shown. In the table, the area under the receiver operating characteristic curve (AUROC) commonly used in binary classification problems is used as the evaluation index:

[0081] Model Area under receiver operating characteristic curve (AUROC) K-nearest neighbor method 0.685 Neural Networks 0.693 Random Forest 0.893 LightGBM 0.881 CatBoost 0.890 XGBoost 0.885 The method proposed by the present invention 0.915

[0082] Table 1 Performance results of different models in the prediction task of new myocardial infarction

[0083] It can be seen from Table 1 that the model proposed in the present invention has more accurate prediction and better generalization performance than other classic machine learning models.

[0084] In summary, the present invention collects basic information and laboratory test data of several patients from real clinical data; screens the collected basic information and laboratory test data of the patients to establish a sample cohort of patients with new myocardial infarction; performs single feature modeling analysis on several clinical features through the xgboost model to obtain the AUROC value of each clinical feature; selects and retains several first clinical features according to the AUROC value; models several clinical features through several tree models, and outputs the feature importance score of each tree model; selects and retains several second clinical features according to the second selection strategy according to the feature importance score; performs intersection processing on several first clinical features and several second clinical features to obtain several target clinical features. Clinical features; build an integrated model based on the automatic machine learning framework AutoGluon; train the integrated model through the target clinical features to obtain a trained integrated model; analyze the target clinical features through the trained integrated model, and output the feature importance score of the trained integrated model; sort the target clinical features according to the feature importance score of the integrated model, and remodel and analyze the clinical features that are ranked in front of a set number, and output the feature importance score of the newly built model; when the feature importance score of the newly built model and the feature importance score of the integrated model meet the set requirements, the most important clinical features are screened out; verify the newly built model through internal and external data, and evaluate the robustness of the newly built model and the effectiveness of the most important clinical features. The present invention solves the challenges of high cost of clinical data collection in the classification and prediction of new myocardial infarction. By modeling and analyzing a large number of clinical features of patients, the important features of the occurrence of new myocardial infarction in clinical applications are accurately screened out based on the granular computing method; the new myocardial infarction classification prediction model constructed by this method only needs to input common clinical features of patients (such as blood routine), which reduces the cost of data collection and improves the robustness of the model. The present invention introduces automatic machine learning, multi-layer stack integration strategy and granular computing data partitioning method to further improve the accuracy and robustness of the model; the present invention has stable performance in both internal and external validation sets collected from real clinical cases.

[0085] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0086] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0087] Example 2

[0088] See also Figure 6 Embodiment 2 of the present invention also provides a device for predicting the grading and classification of new myocardial infarction based on granular computing, comprising:

[0089] The data screening module 001 is used to collect basic information and laboratory test data of several patients from real clinical data; screen the collected basic information and laboratory test data of the patients to establish a sample cohort of new myocardial infarction patients;

[0090] The first clinical feature screening module 002 is used to perform single feature modeling analysis on a plurality of clinical features respectively through the xgboost model to obtain the AUROC value of each clinical feature; and select and retain a plurality of first clinical features according to the AUROC value and the first selection strategy;

[0091] The second clinical feature screening module 003 is used to model the clinical features through a plurality of tree models, and output the feature importance score of each tree model respectively; and select and retain a plurality of second clinical features according to the feature importance score and a second selection strategy;

[0092] A target clinical feature acquisition module 004 is used to perform intersection processing on a plurality of the first clinical features and a plurality of the second clinical features to obtain a plurality of target clinical features;

[0093] The integrated model construction and training module 005 is used to construct an integrated model based on the automatic machine learning framework AutoGluon; train the integrated model through the target clinical features to obtain a trained integrated model;

[0094] The most important clinical feature screening module 006 is used to analyze the target clinical features through the trained integrated model, and output the feature importance score of the trained integrated model; sort the target clinical features according to the feature importance score of the integrated model, and remodel and analyze the clinical features that are ranked in the front by a set number, and output the feature importance score of the newly created model; when the feature importance score of the newly created model and the feature importance score of the integrated model meet the set requirements, the most important clinical features are screened out;

[0095] The newly-created model verification module 007 is used to verify the newly-created model through internal and external data, and to evaluate the robustness of the newly-created model and the effectiveness of the most important clinical features.

[0096] In this embodiment, in the data screening module 001, in the process of screening the collected basic information of the patient and the laboratory test data to establish the sample cohort of patients with new myocardial infarction, samples with new myocardial infarction are screened out from the basic information of the patient and the laboratory test data; samples with a data missing rate greater than 20% among the screened samples are deleted to establish the sample cohort of patients with new myocardial infarction.

[0097] In this embodiment, in the first clinical feature screening module 002, in the process of selecting and retaining a number of the first clinical features according to the AUROC value and the first selection strategy, the first selection strategy is: retaining clinical features with an AUROC value greater than 0.5.

[0098] In this embodiment, in the second clinical feature screening module 003, in the process of modeling the several clinical features through the several tree models, the tree models include: xgboost, catboost and lightgbm tree models; the second selection strategy is: retaining the clinical features whose feature importance scores of the three tree models of xgboost, catboost and lightgbm are all greater than 0.

[0099] In this embodiment, in the integrated model construction and training module 005, the training submodule includes:

[0100] A large vector generation submodule 051, used for the integrated model to apply a separate embedding layer to each of the target clinical features and connect them with the numerical features into a large vector;

[0101] The multi-layer stack integrated training submodule 052 is used to use the multi-layer stack integrated strategy to train a group of basic models separately in a common way to obtain an aggregated prediction result; and use the aggregated prediction result as a feature of the basic model to train the integrated model;

[0102] The granular computing training submodule 053 is used to decompose the target clinical characteristics into several data sets based on the granular computing strategy; each of the data sets is further divided into a training subset and a validation subset; several of the training subsets or several of the validation subsets are merged into a final training subset or a final validation subset; and the integrated model is cross-validated at multiple granularities through the final training subset and the final validation subset.

[0103] It should be noted that the information interaction, execution process and other contents between the modules of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the present application, and will not be repeated here.

[0104] Example 3

[0105] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a method for predicting the grading and classification of new myocardial infarction based on granular computing is stored. The program code includes instructions for executing the method for predicting the grading and classification of new myocardial infarction based on granular computing of embodiment 1 or any possible implementation thereof.

[0106] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0107] Example 4

[0108] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0109] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the new myocardial infarction grading and classification prediction method based on particle computing of Example 1 or any possible implementation thereof.

[0110] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0111] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0112] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0113] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A new myocardial infarction classification prediction method based on granular computing, characterized in that: include: From real clinical data, basic information and laboratory test data of several patients were collected; Screening the collected basic information of the patients and the laboratory test data to establish a sample cohort of patients with new myocardial infarction; Performing single-feature modeling analysis on a plurality of clinical features respectively through the xgboost model to obtain the AUROC value of each clinical feature; selecting and retaining a plurality of first clinical features according to the AUROC value and the first selection strategy; Modeling the plurality of clinical features through a plurality of tree models, and outputting feature importance scores of each of the tree models respectively; selecting and retaining a plurality of second clinical features according to the feature importance scores and a second selection strategy; Performing intersection processing on a plurality of the first clinical features and a plurality of the second clinical features to obtain a plurality of target clinical features; Building an integrated model based on the automatic machine learning framework AutoGluon; training the integrated model through the target clinical features to obtain a trained integrated model; The target clinical features are analyzed by the trained integrated model, and the feature importance scores of the trained integrated model are output; the target clinical features are sorted according to the feature importance scores of the integrated model, and a set number of clinical features that are ranked in front are remodeled and analyzed, and the feature importance scores of the newly created model are output; when the feature importance scores of the newly created model and the feature importance scores of the integrated model meet the set requirements, the most important clinical features are screened out; The newly created model was validated by internal and external data to evaluate the robustness of the newly created model and the effectiveness of the most important clinical features.

2. The method for predicting the grade and classification of new myocardial infarction based on granular computing according to claim 1, characterized in that: In the process of screening the collected basic information of the patients and the laboratory test data to establish the sample cohort of patients with new myocardial infarction, samples with new myocardial infarction are screened out from the basic information of the patients and the laboratory test data; samples with a data missing rate greater than 20% among the screened samples are deleted to establish the sample cohort of patients with new myocardial infarction.

3. The method for predicting the grade and classification of new myocardial infarction based on granular computing according to claim 2 is characterized in that: In the process of selecting and retaining a plurality of the first clinical features according to the AUROC value and the first selection strategy, the first selection strategy is: retaining clinical features with an AUROC value greater than 0.

5.

4. The method for predicting the grade and classification of new myocardial infarction based on granular computing according to claim 3 is characterized in that: In the process of modeling the several clinical features through the several tree models, the tree models include: xgboost, catboost and lightgbm tree models; the second selection strategy is: retaining the clinical features whose feature importance scores of the three tree models of xgboost, catboost and lightgbm are all greater than 0.

5. The method for predicting the classification of newly-occurring myocardial infarction based on granular computing according to claim 4, characterized in that: In the process of training the integrated model by the target clinical features, the training steps are: The integrated model applies a separate embedding layer to each of the target clinical features and concatenates them with the numerical features into a large vector; Using a multi-layer stacking ensemble strategy, a set of basic models are trained separately in a common way to obtain aggregated prediction results; Using the aggregated prediction results as features of the base model to train the integrated model; Based on a granular computing strategy, the target clinical features are decomposed into several data sets; each of the data sets is further divided into a training subset and a validation subset; Merging several of the training subsets or several of the validation subsets into a final training subset or a final validation subset; The integrated model is cross-validated at multiple granularities using the final training subset and the final validation subset.

6. A device for predicting the grading and classification of new myocardial infarction based on granular computing, using the method for predicting the grading and classification of new myocardial infarction based on granular computing according to any one of claims 1 to 5, characterized in that: include: The data screening module is used to collect basic information and laboratory test data of several patients from real clinical data; Screening the collected basic information of the patients and the laboratory test data to establish a sample cohort of patients with new myocardial infarction; A first clinical feature screening module is used to perform single feature modeling analysis on a plurality of clinical features respectively through an xgboost model to obtain an AUROC value for each of the clinical features; and select and retain a plurality of first clinical features according to the AUROC value and a first selection strategy; A second clinical feature screening module is used to model the plurality of clinical features through a plurality of tree models, and output a feature importance score of each of the tree models respectively; and select and retain a plurality of second clinical features according to the feature importance score and a second selection strategy; a target clinical feature acquisition module, used for performing intersection processing on a plurality of the first clinical features and a plurality of the second clinical features to obtain a plurality of target clinical features; An integrated model construction and training module, used to construct an integrated model based on the automatic machine learning framework AutoGluon; train the integrated model through the target clinical features to obtain a trained integrated model; The most important clinical feature screening module is used to analyze the target clinical features through the trained integrated model, and output the feature importance score of the trained integrated model; sort the target clinical features according to the feature importance score of the integrated model, and remodel and analyze the clinical features that are ranked in the front by a set number, and output the feature importance score of the newly created model; when the feature importance score of the newly created model and the feature importance score of the integrated model meet the set requirements, the most important clinical features are screened out; The newly-created model verification module is used to verify the newly-created model through internal and external data, and to evaluate the robustness of the newly-created model and the effectiveness of the most important clinical features.

7. The device for predicting the grading and classification of new myocardial infarction based on granular computing according to claim 6, characterized in that: In the data screening module, in the process of screening the collected basic information of the patient and the laboratory test data to establish the sample cohort of patients with new myocardial infarction, samples with new myocardial infarction are screened out from the basic information of the patient and the laboratory test data; samples with a data missing rate greater than 20% among the screened samples are deleted to establish the sample cohort of patients with new myocardial infarction.

8. The device for predicting the classification and classification of newly-occurring myocardial infarction based on granular computing according to claim 7, characterized in that: In the first clinical feature screening module, in the process of selecting and retaining a number of the first clinical features according to the AUROC value and the first selection strategy, the first selection strategy is: retaining clinical features with an AUROC value greater than 0.

5.

9. The device for predicting the grading and classification of new myocardial infarction based on granular computing according to claim 8, characterized in that: In the second clinical feature screening module, in the process of modeling the several clinical features through the several tree models, the tree models include: xgboost, catboost and lightgbm tree models; the second selection strategy is: retaining the clinical features whose feature importance scores of the three tree models of xgboost, catboost and lightgbm are all greater than 0.

10. The device for predicting the grade and classification of new myocardial infarction based on granular computing according to claim 9, characterized in that: In the integrated model construction and training module, the training submodule includes: A large vector generation submodule, used for the integrated model to apply a separate embedding layer to each of the target clinical features and connect them with the numerical features into a large vector; The multi-layer stack ensemble training submodule is used to train a set of basic models separately in a common way using the multi-layer stack ensemble strategy to obtain aggregated prediction results; Using the aggregated prediction results as features of the base model to train the integrated model; A granular computing training submodule, for decomposing the target clinical features into a plurality of data sets based on a granular computing strategy; each of the data sets is further divided into a training subset and a validation subset; Merging several of the training subsets or several of the validation subsets into a final training subset or a final validation subset; The integrated model is cross-validated at multiple granularities using the final training subset and the final validation subset.

Images