A traditional chinese medicine related drug-induced liver injury risk grading early warning platform and system

Abstract

This invention relates to the field of medical big data technology, and more particularly to a risk grading and early warning platform and system for drug-induced liver injury (HILI) related to traditional Chinese medicine. The invention includes a data input module, a data processing module, a risk prediction module, a grading and early warning module, and a result push module. The purpose of this invention is to provide a risk grading and early warning platform and system for drug-induced liver injury (HILI) related to traditional Chinese medicine, to accurately achieve risk grading and early warning, assist medical personnel in early risk identification, timely intervention, and reduce the incidence and progression risk of HILI.

Description

Technical Field

[0001] This invention relates to the field of medical big data technology, and in particular to a risk classification and early warning platform and system for drug-induced liver injury related to traditional Chinese medicine. Background Technology

[0002] Traditional Chinese medicine (TCM) is widely used in my country's healthcare system. However, due to its complex composition and significant individual differences in dosage, inappropriate combinations of TCM herbs and improper control of dosage duration are common in clinical practice. This has led to a year-on-year increase in the incidence of drug-induced liver injury (HILI) related to TCM, which has become a significant threat to patients' liver health. Furthermore, because the early symptoms of HILI are often atypical, if healthcare professionals fail to identify and intervene in a timely manner, it can easily progress to liver failure, increasing the difficulty of clinical treatment and placing a heavy burden on both patients and the healthcare system.

[0003] Therefore, designing a risk grading and early warning platform and system for drug-induced liver injury related to traditional Chinese medicine that can automatically receive and standardize multi-source clinical and medication data, accurately quantify patients' HILI risk and provide graded early warning, while providing interpretable predictive evidence and differentiated clinical intervention guidance, and solving the problems of cumbersome manual operation, inaccurate early warning, and poor clinical applicability of existing technologies, to help medical staff identify HILI risk early, take timely intervention measures, reduce the incidence of HILI and the risk of progression to liver failure, and reduce the burden on patients and the medical system, has become a key technical problem that urgently needs to be solved in the field of clinical pharmacy. Summary of the Invention

[0004] To address the aforementioned issues, the present invention aims to provide a risk grading and early warning platform and system for drug-induced liver injury related to traditional Chinese medicine, so as to accurately achieve risk grading and early warning of HILI, assist medical staff in early risk identification, timely intervention, and reduce the incidence and progression risk of HILI.

[0005] In a first aspect, the present invention provides a risk grading and early warning platform for drug-induced liver injury related to traditional Chinese medicine: the platform includes a data input module, a data processing module, a risk prediction module, a grading and early warning module, and a result push module. The data input module is used to receive clinical data of patients to be warned, information on the use of traditional Chinese medicine, and indicator data input by the user, providing data foundation support for the data processing module and the risk prediction module; The data processing module is used to standardize all the raw data received by the data input module; The risk prediction module is used to calculate the patient's HILI risk probability and provide data for the graded early warning module; The graded early warning module is used to classify and determine the risk of HILI in patients based on the HILI risk probability output by the risk prediction module, preset multiple early warning levels and corresponding thresholds, generate graded early warning information, and match corresponding clinical intervention recommendations. The graded early warning module includes a risk determination unit, an early warning generation unit, an intervention suggestion matching unit, and an early warning level dynamic adjustment unit. The risk determination unit is used to preset multiple early warning levels and corresponding thresholds, accurately determine the HILI risk probability output by the risk prediction module, and determine the patient's corresponding risk level. The early warning generation unit is used to generate graded early warning information based on the grading results of the risk assessment unit; wherein the risk early warning information includes an early warning identifier and an early warning prompt. The intervention recommendation matching unit is used to match appropriate clinical intervention recommendations based on the patient's corresponding risk level. The warning level dynamic adjustment unit is used to dynamically adjust the warning level threshold and corresponding intervention recommendations based on clinical feedback. The result push module is used to display the prediction results of the risk prediction module and the warning information of the graded warning module, and also supports pushing the information to the corresponding terminal.

[0006] Furthermore, the data input module includes a data entry unit, a multi-source import unit, and a data verification unit; The multi-source import unit is used for manual data entry, batch import of data from Excel spreadsheets, and import of data through interface with electronic medical record systems. The data entry unit is used to manually enter detailed data on the clinical information, traditional Chinese medicine usage information, and laboratory indicators of patients awaiting early warning. The data verification unit is used to verify the integrity, logic, and standardization of the data.

[0007] Furthermore, the data processing module includes a data cleaning unit and a format conversion unit; The data cleaning unit is used to remove abnormal, duplicate, and logically contradictory data samples and delete meaningless redundant fields. The format conversion unit is used to convert unstructured text into structured text.

[0008] Furthermore, the risk prediction module includes a model embedding unit, a SHAP parsing unit, and a prediction result verification unit; The model embedding unit uses model serialization embedding technology to embed the optimal prediction model, thereby enabling automatic input of standardized datasets, automatic model invocation, and automatic calculation of risk probability. The SHAP parsing unit calculates the SHAP value of each input feature using the SHAP algorithm, thereby ranking the feature importance and labeling the influence of individual sample features; it also generates visual explanatory charts. The prediction result verification unit uses threshold and logic verification, presets a HILI risk probability range, and checks whether the prediction result exceeds the threshold range.

[0009] Furthermore, the risk assessment unit includes low-risk, medium-risk, and high-risk warning levels.

[0010] Secondly, the present invention provides a risk grading and early warning system for drug-induced liver injury related to traditional Chinese medicine: the system includes the aforementioned risk grading and early warning system and a multi-terminal device that is communicatively connected to the platform; the multi-terminal device includes a doctor's terminal, a patient's terminal, and a management terminal. The doctor's terminal is used to receive graded early warning information, view complete patient data and predictive interpretation results, modify intervention opinions, and record intervention measures and follow-up data; The patient terminal is used to receive personal warning information and intervention suggestions, view medication guidance, upload medication feedback and follow-up results, and interact with the doctor's terminal. The administrator interface is used to manage user permissions, collect statistics on early warnings and intervention effects, and generate tables and charts.

[0011] The present invention has the following beneficial effects: 1-This invention employs a data input module to achieve multi-channel reception and accurate entry of clinical data, traditional Chinese medicine medication information, and laboratory indicator data of patients awaiting early warning. Through a multi-source import unit, it supports manual entry, batch import from Excel, and import via interface with electronic medical record systems, reducing redundant data entry. At the same time, through a data verification unit, it verifies the integrity, logic, and standardization of the data, eliminating invalid and erroneous data input, thereby providing a complete, compliant, and accurate data foundation for subsequent data processing and risk prediction.

[0012] 2. This invention employs a graded early warning module. A risk assessment unit presets low, medium, and high warning levels and corresponding thresholds to accurately grade and determine the risk of HILI in patients. An early warning generation unit generates graded early warning information with unique visual identifiers and warning prompts, ensuring clear and identifiable warning information. An intervention suggestion matching unit matches clinical intervention suggestions appropriate to the risk level, achieving precise alignment between risk grading and intervention guidance. A dynamic early warning level adjustment unit adjusts the warning thresholds and intervention suggestions based on clinical feedback, achieving clinical adaptation of the early warning mechanism. Ultimately, this invention achieves the effect of graded early warning and precise intervention guidance for HILI risk, improving the targeted nature of clinical risk prevention and control. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of Embodiment 2 of the present invention. Detailed Implementation

[0014] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments: Example 1 See Figure 1 As shown, it includes a data input module, a data processing module, a risk prediction module, a tiered early warning module, and a result push module: The data input module is used to receive clinical data of patients to be warned, information on the use of traditional Chinese medicine, and indicator data input by the user, providing data foundation support for the data processing module and the risk prediction module; The data processing module is used to standardize all the raw data received by the data input module; The risk prediction module is used to calculate the patient's HILI risk probability and provide data for the graded early warning module; The graded early warning module is used to classify and determine the risk of HILI in patients based on the HILI risk probability output by the risk prediction module, preset multiple early warning levels and corresponding thresholds, generate graded early warning information, and match corresponding clinical intervention recommendations. The graded early warning module includes a risk determination unit, an early warning generation unit, an intervention suggestion matching unit, and an early warning level dynamic adjustment unit. The risk determination unit is used to preset multiple early warning levels and corresponding thresholds, accurately determine the HILI risk probability output by the risk prediction module, and determine the patient's corresponding risk level. The early warning generation unit is used to generate graded early warning information based on the grading results of the risk assessment unit; wherein the risk early warning information includes an early warning identifier and an early warning prompt. The intervention recommendation matching unit is used to match appropriate clinical intervention recommendations based on the patient's corresponding risk level. The warning level dynamic adjustment unit is used to dynamically adjust the warning level threshold and corresponding intervention recommendations based on clinical feedback. The result push module is used to display the prediction results of the risk prediction module and the warning information of the graded warning module, and also supports pushing the information to the corresponding terminal.

[0015] Furthermore, the data input module includes a data entry unit, a multi-source import unit, and a data verification unit; The multi-source import unit is used for manual data entry, batch import of data from Excel spreadsheets, and import of data through interface with electronic medical record systems. The data entry unit is used to manually enter detailed data on the clinical information, traditional Chinese medicine usage information, and laboratory indicators of patients awaiting early warning. The data verification unit is used to verify the integrity, logic, and standardization of the data.

[0016] Furthermore, the data processing module includes a data cleaning unit and a format conversion unit; The data cleaning unit is used to remove abnormal, duplicate, and logically contradictory data samples and delete meaningless redundant fields. The format conversion unit is used to convert unstructured text into structured text.

[0017] Furthermore, the risk prediction module includes a model embedding unit, a SHAP parsing unit, and a prediction result verification unit; The model embedding unit uses model serialization embedding technology to embed the optimal prediction model, thereby enabling automatic input of standardized datasets, automatic model invocation, and automatic calculation of risk probability. The SHAP parsing unit calculates the SHAP value of each input feature using the SHAP algorithm, thereby ranking the feature importance and labeling the influence of individual sample features; it also generates visual explanatory charts. The prediction result verification unit uses threshold and logic verification, presets a HILI risk probability range, and checks whether the prediction result exceeds the threshold range.

[0018] Furthermore, the risk assessment unit includes low-risk, medium-risk, and high-risk warning levels. Specifically, each warning level is assigned a unique identifier (green, yellow, red), warning message, and clinical intervention suggestions; a warning threshold adjustment interface is also provided, allowing administrators to adjust the threshold and intervention suggestions based on clinical feedback.

[0019] Example 2 See Figure 2 As shown, the solution includes the aforementioned risk grading and early warning system and a multi-terminal device that communicates with the platform; the multi-terminal device includes a doctor's terminal, a patient's terminal, and a management terminal; The doctor's terminal is used to receive graded early warning information, view complete patient data and predictive interpretation results, modify intervention opinions, and record intervention measures and follow-up data; The patient terminal is used to receive personal warning information and intervention suggestions, view medication guidance, upload medication feedback and follow-up results, and interact with the doctor's terminal. The administrator interface is used to manage user permissions, collect statistics on early warnings and intervention effects, and generate tables and charts.

[0020] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0021] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0022] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0023] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0024] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A risk grading and early warning platform for drug-induced liver injury related to traditional Chinese medicine, characterized in that, It includes a data input module, a data processing module, a risk prediction module, a tiered early warning module, and a result push module: The data input module is used to receive clinical data of patients to be warned, information on the use of traditional Chinese medicine, and indicator data input by the user, providing data foundation support for the data processing module and the risk prediction module; The data processing module is used to standardize all the raw data received by the data input module; The risk prediction module is used to calculate the patient's HILI risk probability and provide data for the graded early warning module; The graded early warning module is used to classify and determine the risk of HILI in patients based on the HILI risk probability output by the risk prediction module, preset multiple early warning levels and corresponding thresholds, generate graded early warning information, and match corresponding clinical intervention recommendations. The graded early warning module includes a risk determination unit, an early warning generation unit, an intervention suggestion matching unit, and an early warning level dynamic adjustment unit. The risk determination unit is used to preset multiple early warning levels and corresponding thresholds, accurately determine the HILI risk probability output by the risk prediction module, and determine the patient's corresponding risk level. The early warning generation unit is used to generate graded early warning information based on the grading results of the risk assessment unit. The risk warning information includes warning signs and warning messages; The intervention recommendation matching unit is used to match appropriate clinical intervention recommendations based on the patient's corresponding risk level. The warning level dynamic adjustment unit is used to dynamically adjust the warning level threshold and corresponding intervention recommendations based on clinical feedback. The result push module is used to display the prediction results of the risk prediction module and the warning information of the graded warning module, and also supports pushing the information to the corresponding terminal.

2. The risk grading and early warning platform for drug-induced liver injury related to traditional Chinese medicine as described in claim 1, characterized in that, The data input module includes a data entry unit, a multi-source import unit, and a data verification unit. The multi-source import unit is used for manual data entry, batch import of data from Excel spreadsheets, and import of data through interface with electronic medical record systems. The data entry unit is used to manually enter detailed data on the clinical information, traditional Chinese medicine usage information, and laboratory indicators of patients awaiting early warning. The data verification unit is used to verify the integrity, logic, and standardization of the data.

3. The risk grading and early warning platform for drug-induced liver injury related to traditional Chinese medicine as described in claim 1, characterized in that, The data processing module includes a data cleaning unit and a format conversion unit; The data cleaning unit is used to remove abnormal, duplicate, and logically contradictory data samples and delete meaningless redundant fields. The format conversion unit is used to convert unstructured text into structured text.

4. The risk grading and early warning platform for drug-induced liver injury related to traditional Chinese medicine as described in claim 1, characterized in that, The risk prediction module includes a model embedding unit, a SHAP parsing unit, and a prediction result verification unit. The model embedding unit uses model serialization embedding technology to embed the optimal prediction model, thereby enabling automatic input of standardized datasets, automatic model invocation, and automatic calculation of risk probability. The SHAP parsing unit calculates the SHAP value of each input feature using the SHAP algorithm, thereby ranking the feature importance and labeling the influence of individual sample features; it also generates visual explanatory charts. The prediction result verification unit uses threshold and logic verification, presets a HILI risk probability range, and checks whether the prediction result exceeds the threshold range.

5. The risk grading and early warning platform for drug-induced liver injury related to traditional Chinese medicine as described in claim 1, characterized in that, The risk assessment unit includes low-risk, medium-risk, and high-risk warning levels.

6. A risk grading and early warning system for drug-induced liver injury related to traditional Chinese medicine: characterized in that: The system includes the risk classification and early warning system as described in any one of claims 1-5, and a multi-terminal device that is communicatively connected to the platform; the multi-terminal device includes a doctor's terminal, a patient's terminal, and a management terminal. The doctor's terminal is used to receive graded early warning information, view complete patient data and predictive interpretation results, modify intervention opinions, and record intervention measures and follow-up data; The patient terminal is used to receive personal warning information and intervention suggestions, view medication guidance, upload medication feedback and follow-up results, and interact with the doctor's terminal. The administrator interface is used to manage user permissions, collect statistics on early warnings and intervention effects, and generate tables and charts.

Images