A method and device for inferring the underlying cause of death based on electronic death card information

Abstract

The present invention relates to a method and device for inferring the root cause of death based on electronic death card information; the method comprises: obtaining a preset range of cause of death chain information based on the electronic death card information to be processed; the cause of death chain information comprises a plurality of cause of death disease information and the time interval from the occurrence of each cause of death disease to death; after performing a value range conversion on the cause of death disease information, splicing is performed based on the time interval to obtain cause of death chain feature data; the cause of death chain feature data is input into a pre-trained root cause of death inference model to obtain a root cause of death category label corresponding to the electronic death card information; the root cause of death category label is restored to the disease category to obtain the root cause of death corresponding to the electronic death card information to be processed. The present invention solves the problem that the root cause of death inference and input method in the prior art is inefficient and the inference result error rate is high.

Description

Technical Field

[0001] The present invention belongs to the technical field of statistics and machine learning, and in particular relates to a method and device for inferring the underlying cause of death based on electronic death card information. Background Art

[0002] Population death information is the basic data for studying the level and cause of death, strengthening population management, and evaluating the health level of residents. It is an important basis for formulating development plans, improving health policies, and optimizing resource allocation. Filling in the cause of death chain is an important information for population death information registration. Manually filling in the root cause of death chain requires reference to a lot of information, such as the rules and notes for determining the root cause of death in the "Guide to Population Death Cause Monitoring". The work is time-consuming and laborious, and it is easy to make inaccurate judgments, resulting in errors in the entry of the root cause of death or non-compliance with the specifications. Therefore, how to make intelligent inferences of the root cause of death based on the information of the electronic death card to reduce the pressure of manual judgment and improve the quality of the coding of the root cause of death has become a very meaningful task. Summary of the invention

[0003] In view of the above analysis, the present invention aims to disclose a method and device for inferring the fundamental cause of death based on electronic death card information, which solves the problems of low efficiency and high error rate of inference results of the prior art inferring and entering the fundamental cause of death.

[0004] The purpose of the present invention is mainly achieved through the following technical solutions:

[0005] In one aspect, the present invention discloses a method for inferring the underlying cause of death based on electronic death card information, comprising:

[0006] Obtaining death cause chain information within a preset range based on the electronic death card information to be processed; the death cause chain information includes multiple death cause disease information and the time interval from the occurrence of each death cause disease to death;

[0007] After the value range of the cause of death disease information is converted, it is spliced ​​based on the time interval to obtain the cause of death chain characteristic data;

[0008] Inputting the cause of death chain feature data into a pre-trained underlying cause of death inference model to obtain an underlying cause of death category label corresponding to the electronic death card information;

[0009] The fundamental cause of death category label is restored to the disease category to obtain the fundamental cause of death corresponding to the electronic death card information to be processed.

[0010] Furthermore, the cause of death disease information is converted into a value range by the following method:

[0011] Obtain the ICD-10 code corresponding to the cause of death;

[0012] The letter part of the ICD-10 code is converted into ASCII value, and the value range of the ICD-10 code is converted by the following formula:

[0013] D=d ASCii *1000+d Dig *10;

[0014] Where D is the cause of death disease data value after the value range is converted; d ASCii Convert the letter part of the ICD-10 code to ASCII value, d Dig The value of the numeric part of the ICD-10 code;

[0015] The data of the cause of death disease in the cause of death chain information that is a null value is filled with 0.

[0016] Furthermore, the cause of death disease information after the value range conversion is sorted by occurrence time, and spliced ​​in the following way to obtain the cause of death chain feature data:

[0017] [d1,t1,d2,t2,……d i ,t i ……d n ,t n ];

[0018] Among them, d i is the data value of the ith cause of death disease after the value range is converted, t i is the time interval from the occurrence of the ith cause of death to death.

[0019] Furthermore, the underlying cause of death inference model includes: an incremental prediction module, a recurrent neural network prediction module, a naive Bayes classification module and a fusion module;

[0020] The incremental prediction module, the recurrent neural network prediction module, and the naive Bayes classification module are used to perform classification prediction based on the death cause chain feature data, and output the prediction probability of each disease category respectively;

[0021] The fusion module is used to perform weighted fusion on the predicted probabilities of the same cause of death category output by each module to obtain the underlying cause of death corresponding to the death card information to be processed.

[0022] Furthermore, the incremental prediction module includes multiple decision tree models, which are trained using a k-fold cross-validation method;

[0023] During the training process, the training sample set is divided into k training subsets, one training subset is randomly selected as a test set, and each training subset is trained as a training set to obtain multiple decision tree models; the decision tree model is used to output the predicted disease category;

[0024] A grid search is performed on the output of each decision tree model to obtain the optimal hyperparameters of the incremental prediction module after training.

[0025] Further, each training subset is used to perform training based on a preset number of training times; during each training, the size of the sliding window is adjusted, multiple feature extractions are performed on each data block, and a decision tree model for each training is generated respectively, so as to obtain multiple decision tree models corresponding to each data block; wherein,

[0026] In a training process, a preset proportion of sample data is randomly selected, and the selected sample data is divided into multiple data blocks; feature data is extracted from each data block based on a sliding window and information entropy and information gain are calculated, and a decision tree model obtained from this training is generated based on the information entropy and information gain.

[0027] Furthermore, after the training of the underlying cause of death inference model is completed, the weights of the incremental prediction module, the recurrent neural network prediction module and the naive Bayes classification module are set by the following method:

[0028] Obtain the cause of death chain information of multiple death cards within a preset time, and perform value range conversion to generate multiple feature data to be predicted;

[0029] Inputting the feature data to be predicted into the incremental prediction module, the recurrent neural network prediction module and the naive Bayes classification module respectively to predict the underlying cause of death;

[0030] The accuracy of the underlying cause of death inference of each module was calculated, and the accuracy of each module was converted into the weight of the model using the following formula:

[0031]

[0032] Among them, α j is the weight of the jth module, ACC j is the accuracy of the jth model, is the total accuracy of the three models.

[0033] Furthermore, the predicted probabilities of the same cause of death category predicted by each classification prediction model are weighted and fused using the following formula:

[0034]

[0035] Among them, LP i is the predicted probability after weighted fusion of the i-th disease category, α j is the weight of the jth module, P ij The probability of the i-th disease category predicted by the j-th model.

[0036] Furthermore, the fundamental cause of death category label is the cause of death disease data after the value range of the cause of death disease is converted; the disease category restoration of the fundamental cause of death category label includes:

[0037] Dividing the disease category label data value output by the underlying cause of death inference model by 1000 to obtain an integer part and a remainder part;

[0038] The integer part is converted into a letter of ASCII value, and concatenated with the number obtained by dividing the remainder part by 10 to obtain the ICD-10 code corresponding to the disease category.

[0039] In another aspect, a computer device is disclosed, comprising at least one processor, and at least one memory communicatively connected to the processor;

[0040] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the aforementioned method for inferring the underlying cause of death based on electronic death card information.

[0041] In another aspect, a computer device is disclosed, comprising at least one processor, and at least one memory communicatively connected to the processor;

[0042] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the aforementioned method for inferring the underlying cause of death based on electronic death card information.

[0043] The present invention can achieve at least one of the following beneficial effects:

[0044] 1. This method obtains the cause-of-death disease information and corresponding time information related to the cause of death based on the electronic death card information, and uses the pre-trained underlying cause-of-death inference model to perform intelligent inference of the underlying cause of death based on multiple cause-of-death disease information and the time interval from the occurrence of each cause-of-death disease to death, thereby improving the efficiency and accuracy of the underlying cause-of-death inference;

[0045] 2. The present invention utilizes the characteristic of ICD-10 codes to classify similar diseases into the same category, and converts the value range of ICD-10 codes corresponding to the cause of death diseases based on a specific method, converting similar diseases into similar values, which is beneficial to model training and improves the accuracy of the underlying cause of death inference;

[0046] 3. Based on the characteristics of large amount of newly added electronic death card data in practical applications, the need for continuous updating of disease categories, and the discrete type of death cause chain data, the present invention adaptively adopts incremental prediction module, recurrent neural network prediction module and naive Bayes classification module to perform feature extraction and classification prediction on electronic death card information data respectively, and obtains the final prediction result through data fusion, thereby avoiding the problem that a single classification prediction model is biased towards certain features of the data when performing classification prediction, which easily leads to inaccurate prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are only used for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. In the entire drawings, the same reference symbols represent the same components;

[0048] Figure 1 is a flow chart of a method for inferring the underlying cause of death based on electronic death card information in an embodiment of the present invention;

[0049] Figure 2 Schematic diagram of the training process of the underlying cause of death prediction model in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used to illustrate the principles of the present invention together with the embodiments of the present invention.

[0051] The embodiment of the present invention discloses a method for inferring the underlying cause of death based on electronic death card information, such as Figure 1 As shown, the following steps are included:

[0052] Step S1: obtaining the cause of death chain information within a preset range based on the electronic death card information to be processed, that is, obtaining the cause of death disease information of a preset number closest to the death time;

[0053] Specifically, the electronic death card information records the cause of death chain information of the deceased, which usually includes multiple cause of death disease information related to the cause of death of the deceased (i.e., the name of the cause of death disease) and the time interval from the occurrence of each cause of death disease to death; in this embodiment, the cause of death diseases in the cause of death chain information are sorted from near to far according to the time of occurrence, and multiple cause of death diseases with the shortest time interval to death are selected, and the disease names and death times of the selected multiple cause of death diseases are used for the prediction of the root cause of death.

[0054] Step S2: After performing value range conversion on the cause of death disease information, splicing is performed based on the time interval to obtain the cause of death chain feature data;

[0055] Specifically, this embodiment converts the value range of the cause of death disease information by the following method:

[0056] Obtain the ICD-10 code corresponding to the name of the cause of death disease; convert the letter part of the ICD-10 code into ASCII value, and convert the value range of the ICD-10 code by the following formula:

[0057] D=d ASCii *1000+d Dig *10;

[0058] Where D is the cause of death disease data value after the value range is converted; d ASCii Convert the letter portion of the ICD-10 code to ASCII. Dig The value of the numeric part of the ICD-10 code;

[0059] The data of the cause of death disease name that is empty in the cause of death chain information is filled with 0.

[0060] Furthermore, the cause of death disease information after the value range conversion is sorted by occurrence time, and spliced ​​in the following way to obtain the cause of death chain feature data:

[0061] [d1,t1,d2,t2,……d i ,t i ……d n ,t n ];

[0062] Among them, d i is the data value of the ith cause of death disease after the value range is converted, t i is the time interval from the occurrence of the ith cause of death to death.

[0063] More specifically, ICD-10 (International Classification of Diseases, 10th Edition) coding is an international unified disease classification method developed by WHO. It classifies diseases according to their etiology, pathology, clinical manifestations, and anatomical location, making them an orderly combination and a system represented by coding methods. It consists of structures such as chapters, blocks, categories, and subcategories. The ICD-10 coding of existing diseases covers all codes from A00.0 to Y98. In order to convert the ICD-10 coding corresponding to the cause of death disease information into data that can be used for machine learning, the ord method of Python can be used to convert the letter part of the ICD-10 coding into ASCII values, multiply it by 1000, and then multiply the value of the numeric part by 10 for value range conversion to obtain a number between 65000 and 89980; if the cause of death disease is a null value, it is filled with 0. Because ICD-10 codes classify similar diseases into the same chapter blocks and categories, the above-mentioned value range conversion method will also classify similar diseases into similar values, which is beneficial to model training and prediction and improves prediction accuracy.

[0064] Step S3: inputting the cause of death chain feature data into a pre-trained underlying cause of death inference model to obtain an underlying cause of death category label corresponding to the electronic death card information;

[0065] Specifically, the underlying cause of death inference model includes: incremental prediction module, recurrent neural network prediction module, naive Bayes classification module and fusion module;

[0066] The incremental prediction module, the recurrent neural network prediction module, and the naive Bayes classification module are used to perform classification prediction based on the death cause chain feature data, and output the prediction probability of each disease category respectively;

[0067] The fusion module is used to perform weighted fusion on the predicted probabilities of the same cause of death category output by each module to obtain the underlying cause of death corresponding to the death card information to be processed.

[0068] like Figure 2 As shown, based on multiple copies of historical death card information obtained in advance, after the value range conversion and splicing of the cause of death chain data, the incremental prediction module, recurrent neural network prediction module, and naive Bayes classification module are trained respectively, and the weights are calculated based on the prediction accuracy of each module to obtain the final root cause of death prediction model.

[0069] Among them, the incremental prediction module includes multiple decision tree models, which are trained using the k-fold cross-validation method;

[0070] During the training process, the training sample set is divided into k training subsets, one training subset is randomly selected as a test set, and each training subset is trained as a training set to obtain multiple decision tree models; the decision tree model is used to output the predicted disease category;

[0071] A grid search is performed on the output of each decision tree model to obtain the optimal hyperparameters of the incremental prediction module after training.

[0072] Further, each training subset is used to perform training based on a preset number of training times; during each training, the size of the sliding window is adjusted, multiple feature extractions are performed on each data block, and a decision tree model for each training is generated respectively, so as to obtain multiple decision tree models corresponding to each data block; wherein,

[0073] In a training process, a preset proportion of sample data is randomly selected, and the selected sample data is divided into multiple data blocks; feature data is extracted from each data block based on a sliding window and information entropy and information gain are calculated, and a decision tree model obtained from this training is generated based on the information entropy and information gain.

[0074] That is, this embodiment uses a combination of k-fold group cross-validation and grid search to determine the hyperparameters of the incremental prediction model. First, initialize a Fold object. The parameter n_splits represents the number of folds of the data set, which is set to k. Shuffle is set to true, which means that the data will be shuffled to the greatest extent possible to make the data evenly distributed. The Fold object divides the sample data set into k folds to obtain k sample subsets. Each sample subset is used as a training set for model training. During each iterative training, a sample subset is randomly selected as a test set for model testing. The value of k is k=n / 50000 (where n is the number of samples in the data set). In practical applications, as the amount of data increases, the value of k can be adaptively adjusted.

[0075] Then define the hyperparameter combination interval of the incremental tree. The hyperparameter spf_sample_prop represents the proportion of samples randomly selected each time the incremental training partial_fit() method is called, and the interval is 0.1-0.9, which means that each time the partial_fit() method is called, 10% to 90% of the samples will be randomly selected from the training set used for training to perform partial fitting of the model. spf_n_fits is used to specify the number of times the partial_fit() method is called, and the interval is set to 10-50. By calling the partial_fit() method multiple times, data can be provided step by step and the model can be updated step by step. This embodiment adopts the StreamingRFC algorithm, and the training data in each training process is divided into multiple data blocks. The parameter n_estimators_per_chunk is used to specify the number of decision trees in each data block (chunk), and each data block contains a portion of sample data and corresponding labels. The n_estimators_per_chunk parameter determines the number of decision trees to be trained in each data block, and the interval is set to 2-10. max_n_estimators is used to specify the maximum number of decision trees. In this embodiment, this parameter is set to np.inf, that is, the maximum number of decision trees is unlimited.

[0076] After training multiple decision trees, grid search and cross-validation are performed based on the output of each decision tree to obtain the optimal hyperparameters of the incremental prediction model. Then, based on the optimal hyperparameters, the incremental learning method is called in batches to learn and the final incremental prediction module can be obtained.

[0077] It should be noted that after the training of the incremental prediction model is completed, in actual application, the new electronic death card information obtained will be added to the training sample set, and the partial_fit() method will be called to perform incremental training of the model to adapt to the characteristics of the continuous increase of electronic death card data and the continuous updating of disease categories, so as to improve the accuracy of the model in inferring the underlying cause of death.

[0078] Furthermore, the recurrent neural network prediction module is a classification prediction model based on the GRU model (gated recurrent unit), which is used to process sequence data to capture the long-term dependency of the cause of death chain feature data and solve the gradient vanishing problem. The recurrent neural network prediction module of this embodiment includes a two-layer GRU model. The first layer is a GRU layer with 64 units, and return_sequences=True is set to pass the sequence output to the next layer. The second layer is a GRU layer with 32 units, and a fully connected layer with 10 units and a softmax activation function is added to the output layer to predict the category of the underlying cause of death.

[0079] The recurrent neural network prediction module adopts the loss function

[0080] sparse_categorical_crossentropy, to handle the multi-classification problem of integer labels in this embodiment and calculate the appropriate loss during model training. The metric metric uses accuracy.

[0081] The calculation formula of the sparse_categorical_crossentropy function is as follows:

[0082]

[0083] Among them, Q is the result of the loss function, m represents the number of samples, and y i represents the underlying cause of death category label of the i-th sample data, that is, the actual result value, x i Represents the i-th sample data.

[0084] Furthermore, the naive Bayes classification module is a naive Bayes classifier in the Scikit-Learn library for processing classification features, which is suitable for processing classification problems of multiple discrete features. It assumes that each feature is independent and has better effects when the features are all classification variables. Therefore, it is suitable for the root cause of death inference based on the death chain information in this embodiment. The model generation steps are as follows:

[0085] Initialize the CategoricalNB model and set the smoothness parameter alpha to 1.0 to control the estimated prior probability and solve the problem of data sparsity. Set fit_prior to true to indicate that the prior probability of the label category needs to be learned. Then, pass the pre-built sample data set and the underlying cause of death category label into the model, call the fit training function for training, and you can get the final naive Bayes classification module.

[0086] Furthermore, after the training of the underlying cause of death inference model is completed, the weights of the incremental prediction module, the recurrent neural network prediction module and the naive Bayes classification module are set by the following method:

[0087] The cause of death chain information of multiple electronic death cards within a preset time is obtained. Preferably, in this embodiment, electronic death card data within one month is selected for weight calculation, and the selected electronic death card data is data with a fundamental cause of death label; the cause of death disease information in the selected electronic death card data is converted into a value range, and the cause of death disease information is spliced ​​based on the death time to generate multiple feature data to be predicted; the feature data to be predicted is respectively input into an incremental prediction module, a recurrent neural network prediction module, and a naive Bayes classification module to predict the fundamental cause of death; based on the prediction results and the pre-marked fundamental cause of death label, the accuracy of the fundamental cause of death inference of each module is calculated, and the accuracy of each module is converted into the weight of the model by the following formula:

[0088]

[0089] Among them, α j is the weight of the jth module, ACC j is the accuracy of the jth model, is the total accuracy of the three models.

[0090] The fusion module performs weighted fusion on the predicted probabilities of the same cause of death category predicted by each classification prediction model using the following formula:

[0091]

[0092] Among them, LP i is the predicted probability after weighted fusion of the i-th disease category, α j is the weight of the jth module, P ij The probability of the i-th disease category predicted by the j-th model.

[0093] In practical applications, the model can also be updated based on a preset cycle. In this embodiment, the update cycle is set to 1 month, that is, the cause of death chain data within the last month is collected, and the cause of death chain data is organized into training data according to the above-mentioned value range conversion method, and is respectively passed into the above-mentioned three modules. The incremental prediction module and the naive Bayes classification module respectively call the predict_proba function to generate the probability of each cause of death disease category label result, and then use the np.argsort function to sort the probability array and take the highest three category labels. The recurrent neural network module calls the softmax function to generate the results and probabilities of each cause of death disease category label, and then sorts them according to the probability to obtain the three labels with the highest probability and probability. Then, the final probability of each label is calculated according to the weights of the three modules, and the probabilities of the same labels are summed to obtain the cause of death disease category label with the highest probability, that is, the final prediction result of the fundamental cause of death inference model.

[0094] Step S4: performing disease category reduction on the root cause of death category label to obtain the root cause of death corresponding to the electronic death card information to be processed.

[0095] Specifically, the fundamental cause of death category label is the cause of death disease data after the value range of the cause of death disease is converted; the disease category restoration of the fundamental cause of death category label includes:

[0096] Dividing the disease category label data value output by the underlying cause of death inference model by 1000 to obtain an integer part and a remainder part;

[0097] The integer part is converted into a letter of ASCII value, and concatenated with the number obtained by dividing the remainder part by 10 to obtain the ICD-10 code corresponding to the disease category.

[0098] Another embodiment of the present invention further discloses a computer device, comprising at least one processor, and at least one memory communicatively connected to the processor;

[0099] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the aforementioned method for inferring the underlying cause of death based on electronic death card information.

[0100] In summary, a method for inferring the underlying cause of death based on electronic death card information of the present invention obtains the cause of death disease information and the corresponding time information related to the cause of death based on the electronic death card information, and based on multiple cause of death disease information and the time interval from the occurrence of each cause of death disease to death, uses a pre-trained underlying cause of death inference model to perform intelligent inference of the underlying cause of death, thereby improving the efficiency and accuracy of the underlying cause of death inference; and the present invention utilizes the characteristic of ICD-10 coding to classify similar diseases into the same category, and based on a specific method, performs value range conversion on the ICD-10 coding corresponding to the cause of death disease, and converts similar diseases into similar numerical values, which is beneficial to model training and improves the accuracy of the underlying cause of death inference; based on the characteristics of large amount of newly added electronic death card data in actual applications, continuous updating of disease categories, discrete type of cause of death chain data, etc., the present invention adaptively adopts an incremental prediction module, a recurrent neural network prediction module and a naive Bayes classification module to perform feature extraction and classification prediction on the electronic death card information data respectively, and obtains the final prediction result through data fusion, thereby avoiding the problem that a single classification prediction model focuses on certain features of the data when performing classification prediction, which easily leads to inaccurate prediction.

[0101] Those skilled in the art will appreciate that all or part of the process of the method in the above embodiment can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0102] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for inferring the underlying cause of death based on electronic death card information, characterized in that: include: Obtaining a preset range of cause of death chain information based on the electronic death card information to be processed; the cause of death chain information includes multiple cause of death disease information and the time interval from the occurrence of each cause of death disease to death; After the value range conversion of the cause of death disease information is performed, splicing is performed based on the time interval to obtain the cause of death chain feature data; wherein, the value range conversion of the cause of death disease information is performed by the following method: obtaining the ICD-10 code corresponding to the cause of death disease; converting the letter part of the ICD-10 code into ASCII value, and performing value range conversion on the ICD-10 code by the following formula: D=d ASCii *1000+d Dig *10; Among them, D is the data value corresponding to the cause of death disease after the value range is converted; d ASCii Convert the letter part of the ICD-10 code to ASCII value, d Dig The value of the numeric part of the ICD-10 code; Fill the data with 0 for the cause of death disease in the cause of death chain information that is empty; The cause-of-death disease information after the value range conversion is sorted by occurrence time and concatenated as follows to obtain the cause-of-death chain feature data: [d1,t1,d2,t2,……d i ,t i ……d n ,t n ]; Among them, d i is the data value of the ith cause of death disease after the value range is converted, t i is the time interval from the occurrence of the i-th cause of death to death; Inputting the cause-of-death chain characteristic data into a pre-trained fundamental cause-of-death inference model to obtain a fundamental cause-of-death category label corresponding to the electronic death card information; the fundamental cause-of-death inference model comprises: an incremental prediction module, a recurrent neural network prediction module, a naive Bayes classification module and a fusion module; the incremental prediction module, the recurrent neural network prediction module and the naive Bayes classification module are used to perform classification prediction based on the cause-of-death chain characteristic data respectively, and output the prediction probability of each disease category respectively; the fusion module is used to perform weighted fusion on the prediction probabilities of the same cause-of-death category output by each module to obtain the fundamental cause of death corresponding to the death card information to be processed; The underlying cause of death category label is restored to a disease category to obtain the underlying cause of death corresponding to the electronic death card information to be processed; wherein the underlying cause of death category label is the cause of death disease data after the value range of the cause of death disease is converted; the underlying cause of death category label is restored to a disease category, including: dividing the disease category label data value output by the underlying cause of death inference model by 1000 to obtain an integer part and a remainder part; converting the integer part into a letter of ASCII value, and concatenating it with the number obtained by dividing the remainder part by 10 to obtain an ICD-10 code corresponding to the disease category.

2. The method for inferring the underlying cause of death based on electronic death card information according to claim 1, characterized in that: The incremental prediction module includes multiple decision tree models, which are trained using a k-fold cross-validation method; During the training process, the training sample set is divided into k training subsets, one training subset is randomly selected as a test set, and each training subset is trained as a training set to obtain multiple decision tree models; the decision tree model is used to output the predicted disease category; A grid search is performed on the output of each decision tree model to obtain the optimal hyperparameters of the incremental prediction module after training.

3. The method for inferring the underlying cause of death based on electronic death card information according to claim 2, characterized in that: Using each training subset, training is performed based on a preset number of training times; During each training, the size of the sliding window is adjusted, multiple feature extractions are performed on each data block, and a decision tree model for each training is generated respectively, so as to obtain multiple decision tree models corresponding to each data block; wherein, In a training process, a preset proportion of sample data is randomly selected, and the selected sample data is divided into multiple data blocks; feature data is extracted from each data block based on a sliding window and information entropy and information gain are calculated, and a decision tree model obtained from this training is generated based on the information entropy and information gain.

4. The method for inferring the underlying cause of death based on electronic death card information according to claim 2, characterized in that: After the training of the underlying cause of death inference model is completed, the weights of the incremental prediction module, the recurrent neural network prediction module and the naive Bayes classification module are set by the following method: Obtain the cause of death chain information of multiple death cards within a preset time, and perform value range conversion to generate multiple feature data to be predicted; Inputting the feature data to be predicted into the incremental prediction module, the recurrent neural network prediction module and the naive Bayes classification module respectively to predict the underlying cause of death; The accuracy of the underlying cause of death inference of each module was calculated, and the accuracy of each module was converted into the weight of the model using the following formula: Among them, α j is the weight of the jth module, ACC j is the accuracy of the jth model, is the total accuracy of the three models.

5. The method for inferring the underlying cause of death based on electronic death card information according to claim 1, characterized in that: The predicted probabilities of the same cause of death category predicted by each classification prediction model are weighted and fused using the following formula: Among them, LP i is the predicted probability after weighted fusion of the i-th disease category, α j is the weight of the jth module, P ij The probability of the i-th disease category predicted by the j-th model.

6. A computer device, characterized in that: comprising at least one processor, and at least one memory communicatively connected to the processor; The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the method for inferring the underlying cause of death based on electronic death card information as described in any one of claims 1 to 5.

Images