Children drug-induced liver injury data fusion and prediction method and system based on time sequence

Abstract

The invention provides a time sequence-based children drug-induced liver injury data fusion and prediction method and system, and relates to the technical field of children drug-induced liver injury information process.The method mainly comprises the following steps: collecting historical medical data of hospitalized children as a longitudinal data set, transversely arranging the data according to a time sequence, and constructing a clinical database; performing entity relationship labeling on unstructured information in the research data set based on related event phenotypes of the child drug-induced liver injury; an MUIRFTI model is constructed and trained, and is used for carrying out structured mapping reconstruction based on time sequence information on the unstructured text; a machine learning prediction model is trained to predict whether the drug-induced liver injury is attacked or not; and inputting medical data of a detected child patient into the machine learning prediction model, and predicting whether the child patient suffers from the drug-induced liver injury or not. According to the scheme, the information amount and logicality of the research data set can be greatly improved, so that the machine learning prediction model which has a better effect and is used for predicting the drug-induced liver injury of children is trained.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing of drug-induced liver injury in children, and in particular to a method and system for data fusion and prediction of drug-induced liver injury in children based on time series. Background Art

[0002] The pathogenesis of drug-induced liver injury (DILI) is complex, and most of the time it is the result of multiple mechanisms acting sequentially or together, including direct drug hepatotoxicity and idiosyncratic hepatotoxicity. Direct drug hepatotoxicity refers to the direct damage to the liver caused by drugs and / or their metabolites ingested into the human body, which can further cause other immune and inflammatory responses. Idiosyncratic hepatotoxicity refers to increased susceptibility to drug-induced liver injury in individuals due to factors such as abnormal individual drug metabolism, drug-mediated immune damage, or individual genetic differences.

[0003] Children are still in the developmental stage and are highly susceptible to DILI. Monitoring DILI in children has important clinical and public health significance. In recent years, in order to overcome the limitations of passive monitoring, the use of electronic medical record (EMR) data for active DILI monitoring has become a research hotspot. However, the lack of temporal information of DILI-related events (including symptoms, signs, etc.) will seriously affect the accuracy of DILI identification. Therefore, studying the temporal processing strategy of DILI-related events is a scientific problem that needs to be solved urgently to improve the accuracy of DILI prediction. Summary of the invention

[0004] The object of the present invention is to provide a time series-based data fusion and prediction method and system for drug-induced liver injury in children to solve at least one of the above-mentioned technical problems existing in the prior art.

[0005] In the first aspect, in order to solve the above technical problems, the present invention provides a method for fusion and prediction of drug-induced liver injury in children based on time series, comprising: Step 1. Collect historical medical data of hospitalized children as a longitudinal data set, arrange them horizontally in chronological order, and construct a clinical database; perform data cleaning and standardization on the clinical database; calculate the sample size of the prediction model for drug-induced liver injury in children, and extract the research data set from the clinical database according to the inclusion and exclusion criteria; based on the relevant event phenotypes of drug-induced liver injury in children, annotate the entity relationships of the unstructured information in the research data set, and process the missing values ​​and outliers of the structured information in the research data set; in the research data set, use whether drug-induced liver injury occurs as a label, and divide it into a training set and a test set according to a preset ratio.

[0006] In a feasible implementation manner, the historical medical data includes electronic medical record (EMR) data of hospitalized children.

[0007] In a feasible implementation manner, the data cleaning includes data desensitization, screening out errors and duplicate records, etc.

[0008] In a feasible implementation, the standardization process includes making the diagnosis name and drug name consistent with the terminology specifications such as the International Statistical Classification of Diseases and Related Health Problems, 10th edition (ICD-10) and the Anatomical, Therapeutic and Chemical Classification of Drugs (ATC) coding.

[0009] In a feasible implementation, the sample size calculation method includes: Based on literature search and expert consultation, the number of specific manifestations of liver injury and related clinical events were selected for inclusion; The sample size was calculated based on the four-step method for sample size calculation of prediction models published in BMJ.

[0010] In a feasible embodiment, the inclusion and exclusion criteria include: Children with the preset age limit and whose first laboratory biochemical examination indicators at admission were within the normal range: alkaline phosphatase (ALP), alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin (TB), and glutamyl transferase (GGT); the age range of the children was 1 month to 18 years old; Children with underlying diseases that affect liver-related functions at admission and those with abnormal liver function before using the target drug were excluded.

[0011] In a feasible embodiment, the research data set includes a standard positive event group and a control group: The standard positive event group is selected from the longitudinal data set using the ADR causal evaluation method and the RUCAM scale, using historical medical data of children with DILI; The control group is randomly selected from the longitudinal data set according to a preset control ratio, and includes historical medical data of children who are not DILI patients and have used target drugs (drugs that induce DILI).

[0012] In a feasible embodiment, the relevant event phenotype is determined based on literature in this field, such as the "Common Clinical Medical Terminology 2023 Edition", and combined with the characteristics of electronic medical record writing of hospitalized children, through multiple rounds of Delphi expert consultation, including symptom indicators, laboratory test indicators, demographic indicators, target drug use indicators and disease indicators; The symptom indicators include jaundice, nausea, vomiting, rash, itchy skin, abdominal discomfort, upper abdominal discomfort, right upper abdominal pain, fever, loss of appetite, decreased appetite, fatigue, weakness, mild jaundice, moderate jaundice, severe jaundice, and jaundice that has not completely subsided; The laboratory test indicators include alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, total bilirubin and glutamyl transferase; The demographic indicators include age, height, weight and gender; The target drug use indicators include dosage, dosage form, route of administration, whether to change medications, and combined medications; The disease indicators include discharge diagnoses and comorbidities.

[0013] In a feasible implementation, the unstructured information includes text data such as medical record homepage information, admission records, daily medical course, handover records, ward rounds records, and first postoperative medical course in the electronic medical record data of hospitalized children.

[0014] In a feasible implementation, the specific method of entity relationship labeling includes: Segment and word segmentation are performed on the unstructured information to obtain a corpus; non-standard entity naming and corresponding relationship extraction are performed on the corpus; the entity naming includes: symptoms (jaundice, nausea, vomiting, rash, skin itching, abdominal discomfort, upper abdominal discomfort, right upper abdominal pain, fever, loss of appetite, decreased appetite, fatigue, weakness, mild jaundice, moderate jaundice, severe jaundice, jaundice has not completely faded) and the severity level of the corresponding symptoms; the names and attributes of the medications used before and after the onset of these symptoms (dosage, frequency and course of treatment, etc.); The pre-trained MedBERT model is then used to perform standard entity naming and corresponding relationship extraction on the corpus.

[0015] In a feasible implementation, the missing value and outlier processing includes: Missing values ​​should be uniformly labeled first, and then statistically analyzed, filled or eliminated; For outliers, they are first identified based on the variable characteristics and coding table, and those that cannot be identified are treated as missing values.

[0016] Step 2: Construct and train a time-series-based reconstruction and fusion model for medical unstructured information, referred to as the MUIRFTI model, which is used to reconstruct the structured mapping of unstructured text based on time-series information; input the unstructured text of the research dataset into the trained MUIRFTI model, perform structured reconstruction according to the rules of each module in the MUIRFTI model, and after obtaining the reconstructed structured text, fuse it with the original structured text in the research dataset to obtain a modeling dataset based on time-series fusion.

[0017] In a feasible implementation, the MUIRFTI model includes a text correction module (TC), a text structuring module (TS), a medical fact and event extraction module (MFEE) and a time information extraction module (TIE) which are arranged in sequence; The text correction module includes a correction strategy library for correcting spelling errors in the text according to regularization strategies through a natural language processing (NLP) tool; The text structuring module includes a grammatical rule library, which is used to adjust grammatical errors in the text and segment sentences according to grammatical rules through natural language processing (NLP) tools; the grammatical rule library includes symptom description rules for children's cases and terminology for drug-induced liver injury related events; in this way, the writing characteristics of symptom descriptions for children's cases can be taken into account to determine the noun terminology for drug-induced liver injury related events; The medical fact and event extraction module includes a key value model (KV), a temporal event description model (TED), a medical research knowledge base and a marked corpus, which is used to extract medical facts and events in the text according to the time sequence mapping through a natural language processing (NLP) tool to obtain a structured database of clinical events with DILI as the target outcome; The time information extraction module includes a time expression rule library, which is used to process the time expression in the clinical event structured database through natural language processing (NLP) tools to construct a child's disease time development model (TDM-PC).

[0018] In a feasible implementation manner, the specific formula of the key value model includes: ; in, Indicates The key value extraction results of the statements; Indicates The key parameter name of the statement; Indicates The key parameter value of each statement; Indicates the number of keywords in a sentence; Represents a key value extraction result set; Indicates the project to which the key value belongs; Indicates the number of statements.

[0019] In a feasible implementation manner, the specific formula of the time event model includes: ; in, Indicates statements; Indicates The key time in a sentence; Indicates The key action in a sentence; Indicates The key effect in each sentence; Represents probability.

[0020] In a feasible implementation, the time information extraction module identifies the time expression in the clinical event structured database through a natural language processing (NLP) tool.

[0021] In a feasible implementation, the temporal development model of the child's condition is used to identify key information on the child's condition in the clinical event structured database, and based on time expression, sort it in chronological order to reproduce the development process of the disease and clinical events; the key information on the child's condition includes: health status (initial symptoms and diagnosis) information, hospitalization diagnosis information, treatment process information, therapeutic medication and laboratory examination information, clinical follow-up information and re-examination information.

[0022] In a feasible implementation, the method for evaluating the training effect of the MUIRFTI model is: by calculating the change in information entropy between the unstructured text before the MUIRFTI model conversion and the structured text after the conversion, the improvement of text uncertainty is quantified, thereby judging the conversion effect of the MUIRFTI model, specifically including: Step a1: Calculate the total text information entropy of unstructured text based on the training set , the specific formula is: ; in, Indicates the total number of phrases in the total text; Indicates the preset occurrence probability of a single phrase in a text; the total text is composed of sentences, the sentences are composed of segments, the segments are composed of phrases, and the phrases are composed of words; Step a2: Calculate the information entropy of the output stage of the text structuring module. The information entropy of the total text at this stage is equal to the sum of the information entropy of each sentence. The specific formula is: ; in, Indicates the number of sentences in the text; Indicates The first sentence of Sentences; Indicates The first sentence of The preset probability of occurrence of words; in this stage, equal ; Calculate the information entropy of this stage and the change in the information entropy in step a1 to evaluate the training effect of the text structuring module; Step a3: Calculate the information entropy of the output stage of the medical facts and events extraction module. Based on the formula in step a2, it also includes calculating the information entropy of phrases in the text. , the specific formula is: ; in, Represents the frequency of occurrence of adjacent words. The specific calculation formula is: ; in, Indicates the length of the word; Calculate the change in information entropy between this stage and the information entropy in step a1 to evaluate the training effect of the text structuring module and the medical fact and event extraction module; Step a4: Calculate the information entropy of the output stage of the time information extraction module , the specific formula is: ; in, Indicated in The information entropy of the phrase at each time node; Indicates the preset probability of occurrence of the phrase in the text; The information entropy of this stage and the change in the information entropy in step a1 are calculated to evaluate the training effect of the MUIRFTI model.

[0023] In a feasible implementation, the method for evaluating the training effect of the MUIRFTI model further includes: Step a5. Based on the test set, calculate the information entropy of each stage according to the method in steps a1-a4, and compare them with the information entropy in steps a1-a4 respectively; by comparing the changes in the information quotient before and after the time series reconstruction process, according to the actual corpus of electronic medical record text records of hospitalized children and the actual corpus of children's symptom descriptions, supplement and correct the strategy library, grammatical rule library, medical research knowledge base and marked corpus, so as to improve the MUIRFTI model in combination with the writing characteristics of the electronic medical record data of hospitalized children.

[0024] Step 3: train a machine learning prediction model based on different strategy combinations through the training set in the modeling data set to predict whether drug-induced liver injury occurs; test the machine learning prediction model through the test set in the modeling data set; evaluate the performance of the machine learning prediction model under different strategy combinations and parameters through evaluation indicators, and optimize the final machine learning prediction model; the independent variables of the feature set in the machine learning prediction model include the number of occurrences of clinical events; the strategy combination includes three clinical event time series processing strategies for counting the number of occurrences of each clinical event, specifically including: independent event set strategy, bundled event set strategy and weighted event set strategy.

[0025] In a feasible implementation, the machine learning prediction model is a classification model.

[0026] In a feasible embodiment, the independent event set strategy means that when calculating the number of each clinical event, the temporal relationship with the occurrence of drug-induced liver injury is not considered, and the total number of occurrences of the clinical event in a preset time period before the occurrence of drug-induced liver injury is directly calculated.

[0027] In a feasible implementation, the bundled event set strategy refers to taking into account the temporal relationship with the occurrence of drug-induced liver injury when calculating the number of each clinical event, and calculating the number of occurrences of the clinical event on each day before the onset of drug-induced liver injury.

[0028] In a feasible implementation, the weighted event set strategy refers to taking into account the temporal relationship with the occurrence of drug-induced liver injury when calculating the number of each clinical event, and assuming that the closer the clinical event occurs to the onset of drug-induced liver injury, the greater the contribution to the drug-induced liver injury, and the greater the weight assigned, that is, the weight of 1 day before the onset of drug-induced liver injury is assigned to 1, and the weight of d days before the onset of drug-induced liver injury is assigned to 1 / d, and then the total number of occurrences of the clinical event is calculated by weighted summation. The specific formula is: ; in, Indicates the preset statistical days before the onset of drug-induced liver injury; Indicates the number of occurrences of the clinical event on the previous d days.

[0029] In a feasible embodiment, the clinical events include prescribed medications, symptoms, and laboratory test results.

[0030] In a feasible implementation, in the training set, the days before the onset of drug-induced liver injury are divided into several time windows for model training; the reason for this setting is that the closer to the onset of drug-induced liver injury, the more clinical events occur and the higher their importance, and the more intensive attention is needed.

[0031] In a feasible implementation, the prediction results of the machine learning prediction model are verified by a 10-fold cross-validation method, and the parameters of the machine learning prediction model are optimized.

[0032] In a feasible implementation, the evaluation indicators include the area under the precision-recall curve (PR-AUC), precision, recall and F1 score.

[0033] Step 4: Input the medical data of the tested child into the machine learning prediction model to predict whether the child will suffer from drug-induced liver injury.

[0034] In the second aspect, based on the same inventive concept, the present application also provides a time-series-based data fusion and prediction system for drug-induced liver injury in children, including a data receiving module, a data processing module and a result generating module; The data receiving module is used to receive the medical data of the tested child; The data processing module predicts whether the child will suffer from drug-induced liver injury based on the medical data of the child being tested by using the time series-based data fusion and prediction method for drug-induced liver injury in children as described above; The result generation module is used to send the prediction results externally.

[0035] By adopting the above technical solution, the present invention has the following beneficial effects: The present invention provides a method and system for fusion and prediction of drug-induced liver injury in children based on time series, which can structure the unstructured data related to drug-induced liver injury in children, reconstruct it according to time series, and then fuse it with the original structured data, thereby greatly improving the information volume and logic of the research data set, and training a better machine learning prediction model for predicting drug-induced liver injury in children; this scheme also optimizes and compares different clinical event time series processing strategies, and clearly considers the rich time series information contained in EMR compared with the strategy of simply building a model based on structured demographic information, medication information and laboratory indicators, which can effectively improve the prediction efficiency and effect of the machine learning prediction model; at the same time, the processing strategy that considers the occurrence weight of DILI-related events can further improve the effect of the DILI prediction model compared with the strategy based on the event occurrence time series. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flow chart of a method for data fusion and prediction of drug-induced liver injury in children based on time series provided in an embodiment of the present invention; Figure 2 A diagram of the MUIRFTI model architecture provided by an embodiment of the present invention; Figure 3 A diagram illustrating the principle of a time-course model for the disease progression of a child provided by an embodiment of the present invention; Figure 4 A flow chart of a method for evaluating the training effect of a MUIRFTI model provided in an embodiment of the present invention; Figure 5 An illustrative diagram of three clinical event timing processing strategies provided in an embodiment of the present invention; Figure 6 An illustrative diagram of weight allocation provided by an embodiment of the present invention; Figure 7 A time series-based data fusion and prediction system for drug-induced liver injury in children provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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.

[0039] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0040] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] The present invention is further explained below in conjunction with specific implementation modes.

[0042] It should also be noted that the following specific embodiments or specific implementations are a series of optimized settings listed in the present invention to further explain the specific content of the invention, and these settings can be used in combination or in association with each other.

[0043] Embodiment 1: like Figure 1 As shown, this embodiment provides a method for fusion and prediction of drug-induced liver injury in children based on time series, including: Step 1. Collect historical medical data of hospitalized children as a longitudinal data set, arrange them horizontally in chronological order, and construct a clinical database; perform data cleaning and standardization on the clinical database; calculate the sample size of the prediction model for drug-induced liver injury in children, and extract the research data set from the clinical database according to the inclusion and exclusion criteria; based on the relevant event phenotypes of drug-induced liver injury in children, annotate the entity relationships of the unstructured information in the research data set, and process the missing values ​​and outliers of the structured information in the research data set; in the research data set, use whether drug-induced liver injury occurs as a label, and divide it into a training set and a test set according to a preset division ratio.

[0044] Furthermore, the historical medical data includes electronic medical record (EMR) data of hospitalized children.

[0045] Furthermore, the data cleaning includes data desensitization, screening out errors and duplicate records, etc.

[0046] Furthermore, the standardization process includes aligning the diagnosis names and drug names with the terminology specifications of the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) and the Anatomical, Therapeutic and Chemical Classification of Drugs (ATC) codes.

[0047] Furthermore, the sample size calculation method includes: Based on literature search and expert consultation, the number of specific manifestations of liver injury and related clinical events were selected for inclusion (23 related event phenotypes can be referenced); The sample size was calculated based on the four-step method for sample size calculation of prediction models published in BMJ.

[0048] Furthermore, the inclusion and exclusion criteria include: Children with the preset years and whose first laboratory biochemical examination indicators at admission were within the normal range: alkaline phosphatase (ALP), alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin (TB), and glutamyl transferase (GGT); Children with underlying diseases that affect liver-related functions at admission, such as those in the Department of Hematology and Oncology, Department of Oncology, and those with abnormal liver function before using the target drug were excluded.

[0049] Furthermore, the research data set includes a standard positive event group and a control group: The standard positive event group is selected from the longitudinal data set using the ADR causal evaluation method (e.g., Naranjo assessment method) and the RUCAM scale, using historical medical data of children with DILI; The control group is randomly selected from the longitudinal data set according to a preset control ratio (e.g., 1:2), and includes historical medical data of children who are not DILI patients and have used the target drug (the drug that induces DILI); For example, from January 2009 to February 2022, a hospital had a total of 826 children with DILI, which served as the standard positive event group; based on the aforementioned sample size calculation method, the sample size was calculated to be 1,783 cases, so a total of approximately 2,478 children were included, which can be used for subsequent modeling.

[0050] Furthermore, the relevant event phenotype is determined based on the literature in this field, "Common Clinical Medical Terminology 2023 Edition", and combined with the characteristics of electronic medical record writing of hospitalized children, through two rounds of Delphi expert consultation, including symptom indicators, laboratory test indicators, demographic indicators, target drug use indicators and disease indicators; The symptom indicators include jaundice, nausea, vomiting, rash, itchy skin, abdominal discomfort, upper abdominal discomfort, right upper abdominal pain, fever, loss of appetite, decreased appetite, fatigue, weakness, mild jaundice, moderate jaundice, severe jaundice, and jaundice that has not completely subsided; The laboratory test indicators include alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, total bilirubin and glutamyl transferase; The demographic indicators include age, height, weight and gender; The target drug use indicators include dosage, dosage form, route of administration, whether to change medications, and combined medications; The disease indicators include discharge diagnoses and comorbidities.

[0051] Furthermore, the unstructured information includes text data such as the medical record homepage information, admission records, daily medical course, handover records, ward rounds records and the first postoperative medical course in the electronic medical record data of hospitalized children.

[0052] Furthermore, the specific method of entity relationship annotation includes: Segment and word segmentation are performed on the unstructured information to obtain a corpus; non-standard entity naming and corresponding relationship extraction are performed on the corpus; the entity naming includes: symptoms (jaundice, nausea, vomiting, rash, skin itching, abdominal discomfort, upper abdominal discomfort, right upper abdominal pain, fever, loss of appetite, decreased appetite, fatigue, weakness, mild jaundice, moderate jaundice, severe jaundice, jaundice has not completely faded) and the severity level of the corresponding symptoms; the names and attributes of the medications used before and after the onset of these symptoms (dosage, frequency and course of treatment, etc.); Then, the pre-trained conventional MedBERT model is used to perform standard entity naming and corresponding relationship extraction on the corpus.

[0053] Furthermore, the missing value and outlier processing includes: Missing values ​​should be uniformly labeled first, and then statistically analyzed, filled or eliminated; For outliers, they are first identified based on the variable characteristics and coding table, and those that cannot be identified are treated as missing values.

[0054] Furthermore, the preset division ratio is 7:3, that is, the research data set is divided into a training set and a test set in a ratio of 7:3.

[0055] Step 2: construct and train a MUIRFTI model for reconstructing structured mapping of unstructured text based on temporal information; input the unstructured text of the research dataset into the trained MUIRFTI model, perform structural reconstruction according to the rules of each module in the MUIRFTI model, and after obtaining the reconstructed structured text, fuse it with the original structured text in the research dataset to obtain a modeling dataset based on temporal fusion.

[0056] Furthermore, if Figure 2 As shown, the MUIRFTI model includes a text correction module (TC), a text structuring module (TS), a medical fact and event extraction module (MFEE) and a time information extraction module (TIE) which are arranged in sequence; The text correction module includes a correction strategy library for correcting spelling errors in the text according to regular strategies using conventional natural language processing (NLP) tools; The text structuring module includes a grammatical rule base, which is used to adjust grammatical errors in the text and segment sentences according to grammatical rules through conventional natural language processing (NLP) tools; the grammatical rule base includes symptom description rules for children's cases and terms related to drug-induced liver injury events; The medical fact and event extraction module includes a key value model (KV), a temporal event description model (TED), a medical research knowledge base and a tagged corpus, which is used to extract medical facts and events in the text according to time sequence mapping through conventional natural language processing (NLP) tools to obtain a structured database of clinical events with DILI as the target outcome; The time information extraction module includes a time expression rule library, which is used to process the time expression in the clinical event structured database through conventional natural language processing (NLP) tools, and construct a time development model of the child's condition (TDM-PC) to achieve time-series-based structured data reconstruction. By identifying DILI-related events and time-critical information in the electronic medical record text of hospitalized children, the various time scenarios corresponding to the changes in the children's condition are vertically outlined.

[0057] Furthermore, the specific formula of the key value model includes: ; in, Indicates The key value extraction results of the statements; Indicates The key parameter name of the statement; Indicates The key parameter value of each statement; Indicates the number of keywords in a sentence; Represents a key value extraction result set; Indicates the project to which the key value belongs; Indicates the number of statements; For example: The statement is "On March 11, 2018, he developed sore throat and was given azithromycin to fight infection but it was ineffective. A blood test was performed in our hospital: WBC: 2.13×10 9 / L, Hb:102g / L, PLT:177×10 9 / L"; After key-value model mapping, the following is extracted: ; ; ; ; .

[0058] Furthermore, the specific formula of the time event model includes: ; in, Indicates statements; Indicates The key time in a sentence; Indicates The key action in a sentence; Indicates The key effect in each sentence; represents probability; For example: The statement is “On March 11, 2018, I developed sore throat and was given azithromycin to fight infection but it was ineffective. A blood test was performed in our hospital: WBC: 2.13×10 9 / L, Hb: 102g / L, PLT: 177×10 9 / L"; After time event model mapping, the following is extracted: ; ; ; ; in, Represents the final structured information formed after time event mapping.

[0059] Furthermore, if Figure 3 As shown, the time development model of the child's condition (TDM-PC) is used to identify the key information of the child's condition in the clinical event structured database, and sort it in chronological order based on time expression to reproduce the development process of the disease and clinical events; the key information of the child's condition includes: health status (initial symptoms and diagnosis) information, hospitalization diagnosis information, treatment process information, treatment medication and laboratory examination information, clinical follow-up information and re-examination information.

[0060] Figure 3 The five stages of the patient's disease time development model are shown. By continuously recording these five stages, a structural reconstruction of all data (in the electronic medical records of hospitalized children) can be achieved as the child's disease progresses over time, including: Phase 1 ) is the health status stage, which requires extracting the health status information of the children at the time of admission from the electronic medical records of the hospitalized children, including baseline symptoms, admission complaints and preliminary diagnosis information; the information at this stage will serve as the initial input of the children's status in the subsequent stages; Phase 2 ) is the stage of hospital definite diagnosis, during which the child receives a definite diagnosis from the hospital and records the child's hospitalization diagnosis information; Phase 3 ) is the treatment process stage, which records the treatment process information of the child; Phase 4 ( ) is the drug treatment stage, which records the child's treatment medication and laboratory test information; Phase 5 ) is the stage of discharge and prognosis follow-up for children, which records clinical follow-up information and re-examination information; when children are discharged from the hospital, their health status can be observed based on clinical follow-up information, and the long-term changes in the hospital's treatment effect can be evaluated; Through the time development model of the child's condition, the data of the above stages are arranged and sorted in sequence according to the development of the child's condition, which helps to record and analyze the entire course of the hospitalized child from the time series dimension.

[0061] Furthermore, the method for evaluating the training effect of the MUIRFTI model is to quantify the improvement of text uncertainty by calculating the change in information entropy between the unstructured text before the MUIRFTI model conversion and the structured text after the conversion, so as to judge the conversion effect of the MUIRFTI model, such as Figure 4 As shown, specifically including: Step a1: Calculate the total text information entropy of unstructured text based on the training set , the specific formula is: ; in, Indicates the total number of phrases in the total text; Indicates the preset occurrence probability of a single phrase in a text; the total text is composed of sentences, the sentences are composed of segments, the segments are composed of phrases, and the phrases are composed of words; Step a2: Calculate the information entropy of the output stage of the text structuring module. The information entropy of the total text at this stage is equal to the sum of the information entropy of each sentence. The specific formula is: ; in, Indicates the number of sentences in the text; Indicates The first sentence of Sentences; Indicates The first sentence of The preset probability of occurrence of words; in this stage, equal ; Calculate the information entropy of this stage and the change in the information entropy in step a1 to evaluate the training effect of the text structuring module; Step a3: Calculate the information entropy of the output stage of the medical facts and events extraction module. Based on the formula in step a2, it also includes calculating the information entropy of phrases in the text. , the specific formula is: ; in, Indicates the frequency of occurrence of adjacent words. The specific calculation formula is: ; in, Indicates the length of the word; Calculate the change in information entropy between this stage and the information entropy in step a1 to evaluate the training effect of the text structuring module and the medical fact and event extraction module; Step a4: Calculate the information entropy of the output stage of the time information extraction module , the specific formula is: ; in, Indicated in The information entropy of the phrase at each time node; Indicates the preset probability of occurrence of the phrase in the text; The information entropy of this stage and the change in the information entropy in step a1 are calculated to evaluate the training effect of the MUIRFTI model.

[0062] Furthermore, the method for evaluating the training effect of the MUIRFTI model also includes: Step a5. Based on the test set, calculate the information entropy of each stage according to the method in steps a1-a4, and compare them with the information entropy in steps a1-a4 respectively; by comparing the changes in the information quotient before and after the time series reconstruction process, according to the actual corpus of electronic medical record text records of hospitalized children and the actual corpus of children's symptom descriptions, supplement and correct the strategy library (adjust the unstructured text regularization method), grammatical rule library, medical research knowledge base and marked corpus, so as to improve the MUIRFTI model in combination with the writing characteristics of the electronic medical record data of hospitalized children.

[0063] Furthermore, the MUIRFTI model can be implemented using the statsmodels library in Python 3.11.0.

[0064] Furthermore, information entropy calculation can be achieved through Matlab R2021b program.

[0065] Step 3: train a machine learning prediction model based on different strategy combinations through the training set in the modeling data set to predict whether drug-induced liver injury occurs; test the machine learning prediction model through the test set in the modeling data set; evaluate the performance of the machine learning prediction model under different strategy combinations and parameters through evaluation indicators, and optimize the final machine learning prediction model; the independent variables of the feature set in the machine learning prediction model include the number of occurrences of clinical events; the strategy combination includes three clinical event time series processing strategies for counting the number of occurrences of each clinical event, specifically including: independent event set strategy, bundled event set strategy and weighted event set strategy.

[0066] Furthermore, the machine learning prediction model includes classification models such as random forest (RF), support vector machine (SVM) and naive Bayesian.

[0067] Furthermore, the machine learning prediction model can be implemented by scikitlearn and SHAP packages of Python 3.10.2.

[0068] Furthermore, if Figure 5 As shown, the independent event set strategy means that when calculating the number of each clinical event, the temporal relationship with the occurrence of drug-induced liver injury is not considered, and the total number of occurrences of the clinical event in the preset time period before the occurrence of drug-induced liver injury is directly calculated. For example, "the symptom (examination) occurred 4 times in the first three days", the total number of occurrences of the clinical event is recorded as 4; The bundled event set strategy refers to the calculation of the number of each clinical event, taking into account the temporal relationship with the occurrence of drug-induced liver injury, and calculating the number of occurrences of the clinical event on each day before the occurrence of drug-induced liver injury; The weighted event set strategy refers to the consideration of the temporal relationship with the occurrence of drug-induced liver injury when calculating the number of each clinical event, and assuming that the closer the clinical event occurs to the onset of drug-induced liver injury, the greater the contribution to the drug-induced liver injury, and the greater the weight assigned, that is, the weight of 1 day before the onset of drug-induced liver injury is assigned to 1, and the weight of d days before the onset of drug-induced liver injury is assigned to 1 / d, and then the total number of occurrences of the clinical event is calculated by weighted summation. The specific formula is: ; in, Indicates the preset statistical days before the onset of drug-induced liver injury; Indicates the number of occurrences of the clinical event on the previous d days.

[0069] Furthermore, the clinical events include prescribed medications, symptoms (examinations) and laboratory test (measurement) results.

[0070] Furthermore, in the training set, the days before the onset of drug-induced liver injury were divided into 10 time windows, namely the 1st, 2nd, 3rd, 4th, 5th, 6th, 7th, 14th, 21st, and 30th days, for model training; the reason for this setting is that the closer to the onset of drug-induced liver injury, the more clinical events occur and the higher their importance, and the more intensive attention is needed.

[0071] Furthermore, if Figure 6 As shown, the weights of the weighted event set strategy also include time window weights, individual event weights, and time window and event type weights. The specific calculation methods are: The time window weight refers to the weight calculated based on the distance from the event to the occurrence of DILI outcome, and only the distance from the event to the occurrence of DILI outcome is considered; The individual event weight refers to the weight calculated by considering only the importance of clinical events (medication, laboratory tests and symptoms); The time window and event type weights refer to weight calculations that consider both the distance of the event from the DILI outcome and the importance of different events to DILI prediction.

[0072] Furthermore, the prediction results of the machine learning prediction model were verified through the 10-fold cross-validation method, and the parameters of the machine learning prediction model were optimized.

[0073] Furthermore, the evaluation indicators include the area under the precision-recall curve (PR-AUC), precision, recall and F1 score.

[0074] Step 4: Input the medical data of the tested child into the machine learning prediction model to predict whether the child will suffer from drug-induced liver injury.

[0075] Embodiment 2: like Figure 7 As shown, this embodiment provides a time series-based data fusion and prediction system for drug-induced liver injury in children, including a data receiving module, a data processing module and a result generating module; The data receiving module is used to receive the medical data of the tested child; The data processing module predicts whether the child will suffer from drug-induced liver injury based on the medical data of the child being tested by using the time series-based data fusion and prediction method for drug-induced liver injury in children as described above; The result generation module is used to send the prediction results externally.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for data fusion and prediction of drug-induced liver injury in children based on time series, characterized in that: include: Step 1: Collect the historical medical data of hospitalized children as a longitudinal data set, arrange them horizontally in chronological order, and build a clinical database; Perform data cleaning and standardization on clinical database; The sample size of the prediction model for drug-induced liver injury in children was calculated, and the research data set was extracted from the clinical database according to the inclusion and exclusion criteria: Based on the relevant event phenotypes of drug-induced liver injury in children, the entity relationship of unstructured information is annotated, and missing values ​​and outliers of structured information are processed; whether drug-induced liver injury occurs is used as a label, and the data are divided into training set and test set according to the preset ratio; Step 2: construct and train a MUIRFTI model for reconstructing unstructured text into a structured mapping based on temporal information; input the unstructured text of the research dataset into the trained MUIRFTI model, perform structural reconstruction according to the rules of each module in the MUIRFTI model, obtain the reconstructed structured text, and then fuse it with the original structured text in the research dataset to obtain a modeling dataset based on temporal fusion; Step 3: Train the machine learning prediction model through the training set in the modeling data set to predict whether drug-induced liver injury occurs; test the machine learning prediction model through the test set in the modeling data set; evaluate the performance of the machine learning prediction model under different strategy combinations and parameters through evaluation indicators, and optimize to obtain the final machine learning prediction model; The independent variables of the machine learning prediction model include the number of occurrences of clinical events; the strategy combination includes three clinical event temporal processing strategies: independent event set strategy, bundled event set strategy and weighted event set strategy; Step 4: Input the medical data of the tested child into the machine learning prediction model to predict whether the child will suffer from drug-induced liver injury.

2. The method according to claim 1, characterized in that The inclusion and exclusion criteria in step 1 include: Children with the preset years and whose first laboratory biochemical examination indicators at admission were within the normal range: alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, total bilirubin, and glutamyl transferase; Children with underlying diseases that affect liver-related functions at admission and those with abnormal liver function before using the target drug were excluded.

3. The method according to claim 1, characterized in that The research data set in step 1 includes a standard positive event group and a control group: The standard positive event group is selected from the longitudinal data set using the ADR causal evaluation method and the RUCAM scale to obtain historical medical data of children with drug-induced liver injury; The control group is randomly selected from the longitudinal data set according to a preset control ratio, and includes historical medical data of children with non-drug-induced liver injury who have used the target drug.

4. The method according to claim 1, characterized in that The relevant event phenotypes include symptom indicators, laboratory test indicators, demographic indicators, target drug use indicators and disease indicators; The symptom indicators include jaundice, nausea, vomiting, rash, itchy skin, abdominal discomfort, upper abdominal discomfort, right upper abdominal pain, fever, loss of appetite, decreased appetite, fatigue, weakness, mild jaundice, moderate jaundice, severe jaundice, and jaundice that has not completely subsided; The laboratory test indicators include alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, total bilirubin and glutamyl transferase; The demographic indicators include age, height, weight and gender; The target drug use indicators include dosage, dosage form, route of administration, whether to change medications, and combined medications; The disease indicators include discharge diagnoses and comorbidities.

5. The method according to claim 1, characterized in that The unstructured information includes the medical record homepage information, admission records, daily medical course, handover records, ward rounds records and the first postoperative medical course in the electronic medical record data of hospitalized children.

6. The method according to claim 1, characterized in that The MUIRFTI model includes a text correction module, a text structuring module, a medical fact and event extraction module and a time information extraction module which are arranged in sequence; The text correction module includes a correction strategy library for correcting spelling errors in the text according to regular strategies through natural language processing tools; The text structuring module includes a grammatical rule library, which is used to adjust grammatical errors in the text and segment sentences according to grammatical rules through natural language processing tools; the grammatical rule library includes symptom description rules for children's cases and terms related to drug-induced liver injury events; The medical fact and event extraction module includes a key value model, a time event description model, a medical research knowledge base and a marked corpus, which is used to extract medical facts and events in the text according to the time sequence mapping through a natural language processing tool to obtain a structured database of clinical events with drug-induced liver injury as the target outcome; The time information extraction module includes a time expression rule library, which is used to process the time expression in the clinical event structured database through natural language processing tools to construct a time development model of the child's condition.

7. The method according to claim 6, characterized in that The specific formula of the key value model includes: ； in, Indicates The key value extraction results of the statements; Indicates The key parameter name of the statement; Indicates The key parameter value of each statement; Indicates the number of keywords in a sentence; Represents a key value extraction result set; Indicates the project to which the key value belongs; Indicates the number of statements; The specific formula of the time event model includes: ； in, Indicates statements; Indicates The key time in a sentence; Indicates The key action in a sentence; Indicates The key effect in each sentence; Represents probability.

8. The method according to claim 1, characterized in that: The method for evaluating the training effect of the MUIRFTI model is to quantify the improvement of text uncertainty by calculating the change in information entropy between the unstructured text before the MUIRFTI model conversion and the structured text after the conversion, including: Step a1: Calculate the total text information entropy of unstructured text based on the training set , the specific formula is: ； in, Indicates the total number of phrases in the total text; Indicates the preset occurrence probability of a single phrase in a text; the total text is composed of sentences, the sentences are composed of segments, the segments are composed of phrases, and the phrases are composed of words; Step a2: Calculate the information entropy of the output stage of the text structuring module. The information entropy of the total text at this stage is equal to the sum of the information entropy of each sentence. The specific formula is: ； in, Indicates the number of sentences in the text; Indicates The first sentence of Sentences; Indicates The first sentence of The preset probability of occurrence of words; in this stage, equal ; Calculate the information entropy of this stage and the change in the information entropy in step a1 to evaluate the training effect of the text structuring module; Step a3: Calculate the information entropy of the output stage of the medical facts and events extraction module. Based on the formula in step a2, it also includes calculating the information entropy of phrases in the text. , the specific formula is: ； in, Indicates the frequency of occurrence of adjacent words. The specific calculation formula is: ； in, Indicates the length of the word; Calculate the change in information entropy between this stage and the information entropy in step a1 to evaluate the training effect of the text structuring module and the medical fact and event extraction module; Step a4: Calculate the information entropy of the output stage of the time information extraction module , the specific formula is: ； in, Indicated in The information entropy of the phrase at each time node; Indicates the preset probability of occurrence of the phrase in the text; The information entropy of this stage and the change in the information entropy in step a1 are calculated to evaluate the training effect of the MUIRFTI model.

9. The method according to claim 1, characterized in that: The independent event set strategy refers to calculating the total number of occurrences of each clinical event within a preset time period before the onset of drug-induced liver injury when calculating the number of clinical events; The bundled event set strategy refers to calculating the number of occurrences of each clinical event on each day before the onset of drug-induced liver injury when calculating the number of occurrences of the clinical event; The weighted event set strategy refers to calculating the number of each clinical event by assigning a weight of 1 to the day before the onset of drug-induced liver injury, and a weight of 1 / d to the day before the onset of drug-induced liver injury, and then calculating the total number of occurrences of the clinical event by weighted summation. The specific formula is: ； in, Indicates the preset statistical days before the onset of drug-induced liver injury; Indicates the number of occurrences of the clinical event on the previous d days.

10. A time series-based data fusion and prediction system for drug-induced liver injury in children, characterized in that: It includes a data receiving module, a data processing module and a result generating module; The data receiving module is used to receive the medical data of the tested child; The data processing module predicts whether the child will suffer from drug-induced liver injury based on the medical data of the child being tested by using the method described in any one of claims 1 to 9; The result generation module is used to send the prediction results externally.

Images