A neurological care optimization method and system

Abstract

The present invention discloses a neurological nursing optimization method and system, which relates to the field of neurological nursing technology, obtains and stores detailed medical history data of patients, cleans the detailed medical history data, extracts key information from unstructured data groups, inputs a second structured data group into a preset nursing plan model and screens it, generates optimized nursing plan data, collects and analyzes patient medical history data, can fully understand health conditions and potential risks, formulate personalized and accurate nursing plans, process medical history data in a structured and unstructured manner, improve processing speed and accuracy, ensure that the plans are efficient and scientific, pay special attention to prohibited drugs, treatment methods and drug side effects, compare and exclude adverse plans, reduce nursing risks, optimize nursing plans, provide clear guidance for medical staff, enhance doctor-patient communication, and improve satisfaction and treatment compliance.

Description

Technical Field

[0001] The present invention relates to the field of nerve care technology, and in particular to a nerve care optimization method and system. Background Art

[0002] As an important branch of the medical field, neurological nursing focuses on the comprehensive care and treatment of patients with neurological diseases. With the aging of the population and changes in lifestyle, the incidence of neurological diseases has increased year by year, which has put forward higher requirements for neurological nursing work. Neurological nursing work not only involves the observation, care and treatment of the disease, but also requires nursing staff to have a high degree of professionalism and comprehensive ability to cope with complex and changing diseases, optimize neurological nursing methods, and improve nursing quality and efficiency, which has become an important topic in the current field of neurological nursing.

[0003] At present, a Chinese invention patent with application number CN202311531588.9 discloses a method and system for analyzing safety hazards in clinical nursing in neurology. The system collects the body characteristics of Parkinson's patients in real time through multiple sets of integrated sensor groups, and accurately analyzes the patient's condition through the muscle stiffness Jyd, tremor frequency Zcp, tremor amplitude Zcf and body balance Phd of Parkinson's patients. At the same time, long-term medication for Parkinson's patients will have an impact on the internal characteristics of the body. Through the internal characteristic data set, the blood pressure value Xyz, liver and kidney function parameters Gsg and trace element coefficient Wls of Parkinson's patients are observed in real time. By detecting these data, it is identified whether the blood pressure and liver and kidney function of Parkinson's patients are damaged when taking drugs for a long time, and the trace elements of patients are detected in order to provide accurate care for patients and adjust their diet to ensure balanced nutrition.

[0004] This invention cannot analyze and screen nursing methods based on the patient's medical history data and generate nursing plans suitable for different patients, which affects the quality and efficiency of nursing. Summary of the invention

[0005] The technical problem solved by the present invention is that in the related art, it is impossible to analyze and screen nursing methods based on the patient's medical history data and generate nursing plans suitable for different patients, which affects the quality and efficiency of nursing.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A method for optimizing nerve care comprises the following steps:

[0008] Step S1, obtaining and storing detailed medical history data of the patient;

[0009] Step S2, cleaning the detailed medical history data, performing structured data classification and unstructured data classification on the detailed medical history data, and outputting the data into a first structured data group and an unstructured data group;

[0010] Step S3, extracting key information from the unstructured data group, combining it with the first structured data and outputting it as a second structured data group;

[0011] Step S4, inputting the second structured data group into a preset nursing plan model and screening it, wherein the nursing plan model includes a plurality of nursing plans and side effect type data corresponding to the nursing plans, and outputting it as first nursing plan data;

[0012] Step S5, analyzing the first nursing plan data to generate optimized nursing plan data;

[0013] Step S1 includes the following sub-steps:

[0014] Step S101, collecting the patient's medical history, allergy history, medication records, surgical records, and family medical history;

[0015] Step S102, storing the patient's past medical history, allergy history, medication record, surgery record and family medical history as detailed medical history data;

[0016] The step S2 includes the following sub-steps:

[0017] Step S201, cleaning the detailed medical history data, and removing irrelevant data in the detailed medical history data according to a preset common disease set;

[0018] Step S202, classifying the detailed medical history data into structured data and unstructured data, and outputting them into a first structured data group and an unstructured data group;

[0019] The first structured data group includes the names of past diseases in the past medical history, the names of allergens in the allergy history, the names of drugs in the medication records, the names of surgeries in the surgery records, and the names of family diseases in the family medical history;

[0020] The unstructured data set includes a doctor's medical record of past medical history, a description of allergic reactions of allergic history, a description of medication reactions of medication records, a postoperative recovery record of surgical records, and a description of family diseases of family medical history;

[0021] The step S3 includes the following sub-steps:

[0022] Step S301, segmenting the unstructured data group, removing stop words and extracting stems;

[0023] Step S302, extracting the preprocessed unstructured data set according to the preset medical entity library, including symptom extraction from doctor's medical records, allergen extraction from allergic reaction descriptions, side effect drug extraction from medication reaction descriptions, sequelae extraction from postoperative recovery records, and genetic disease extraction from family disease descriptions;

[0024] Step S303, combining the information extracted in step S302 with the first structured data and outputting them as a second structured data group;

[0025] The step S4 includes the following sub-steps:

[0026] Step S401, inputting the second structured data group into the unified medical language system, searching for the patient's prohibited drugs, drug side effects corresponding to the prohibited drugs, and prohibited treatment methods, and outputting them as prohibited nursing data;

[0027] Step S402, inputting the disabled nursing data into a preset nursing plan model, comparing the disabled treatment means with the nursing plan, comparing the drug side effects with the side effect type data, marking the nursing plans including the disabled treatment means and the nursing plans corresponding to the side effect type data including the drug side effects, and outputting the marked nursing plans as first nursing plan data;

[0028] The step S5 comprises the following sub-steps:

[0029] Step S501, analyzing the first nursing plan data, and if the first nursing plan data contains an unmarked nursing plan, outputting the unmarked nursing plan as an optimized nursing plan;

[0030] Step S502: If all nursing plans in the first nursing plan data are marked, the nursing plan with the least number of marks and the corresponding side effect type data are output as optimized nursing plan data.

[0031] A neurological care optimization system, which is applied to the above-mentioned neurological care optimization method, comprises a medical history data acquisition module, a medical history information extraction module and an optimization solution generation module:

[0032] The medical history data acquisition module is used to acquire and store the patient's detailed medical history data;

[0033] The medical history information extraction module is used to clean the detailed medical history data and output it as a first structured data group and an unstructured data group, extract key information from the unstructured data group and combine the extracted information with the first structured data and output it as a second structured data group;

[0034] The optimization plan generation module is used to search the second structured data group according to the unified medical language system and output the disabled nursing data, input the disabled nursing data into the nursing plan model for screening and output the first nursing plan data, analyze the first nursing plan data and generate optimized nursing plan data.

[0035] Preferably, the medical history data acquisition module includes a data collection unit and a data storage unit, wherein:

[0036] The data collection unit is used to collect the patient's past medical history, allergy history, medication record, surgical record and family medical history;

[0037] The data storage unit is used to store the patient's past medical history, allergy history, medication record, surgery record and family medical history as detailed medical history data.

[0038] Preferably, the medical history information extraction module includes a data cleaning and classification unit and an information extraction unit, wherein:

[0039] The data cleaning and classification unit is used to clean the detailed medical history data, classify the cleaned detailed medical history data and output them into a first structured data group and an unstructured data group;

[0040] The information extraction unit is used to extract key information from the unstructured data group, combine the extracted information with the first structured data, and output the information as a second structured data group.

[0041] Preferably, the optimization solution generation module includes a data screening unit and an analysis generation unit, wherein:

[0042] The data screening unit is used to search for the second structured data group and output the disabled nursing data, input the disabled nursing data into the nursing plan model for screening, mark the nursing plan containing the disabled nursing data in the nursing plan model and output the marked nursing plan model as the first nursing plan data;

[0043] The analysis generation unit is used to perform analysis based on the first nursing plan data. If the first nursing plan data contains unmarked nursing plans, the unmarked nursing plans are output as optimized nursing plans. If all nursing plans in the first nursing plan are marked, the nursing plan with the least number of marks is output as the optimized nursing plan.

[0044] The beneficial effects of the present invention are as follows: by collecting and analyzing the medical history data of patients, a comprehensive understanding of health conditions and potential risks can be obtained, personalized and precise nursing plans can be formulated, and structured and unstructured medical history data can be processed to improve processing speed and accuracy, ensure that the plans are efficient and scientific, pay special attention to prohibited drugs, treatment methods and drug side effects, compare and eliminate adverse plans, reduce nursing risks, optimize nursing plans, provide clear guidance for medical staff, enhance doctor-patient communication, and improve satisfaction and treatment compliance. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method for optimizing nerve care provided by one embodiment of the present invention;

[0046] Figure 2 A basic flow chart of a neurological care optimization system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0048] Embodiment 1, refer to Figure 1 , provides a method for optimizing neurological care, comprising the following steps:

[0049] Step S1, obtaining and storing the patient's detailed medical history data.

[0050] Step S2, cleaning the detailed medical history data, performing structured data classification and unstructured data classification on the detailed medical history data, and outputting the first structured data group and the unstructured data group.

[0051] Step S3, extract key information from the unstructured data group, combine it with the first structured data and output it as a second structured data group.

[0052] By comprehensively acquiring and storing detailed medical history data of patients, including structured and unstructured data, a rich and accurate information basis is provided for nursing decisions, helping medical staff to have a more comprehensive understanding of the patient's health status and thus develop more accurate and personalized nursing plans.

[0053] Cleaning, classifying and extracting key information from detailed medical history data effectively improves the efficiency and accuracy of data processing, which not only reduces the errors that may be caused by human intervention, but also speeds up the process of generating nursing plans, allowing patients to receive appropriate care more quickly.

[0054] Step S4, inputting the second structured data group into a preset nursing plan model and screening it, wherein the nursing plan model includes a plurality of nursing plans and side effect type data corresponding to the nursing plans, and outputting the first nursing plan data.

[0055] Inputting the processed data into the preset nursing plan model for screening can automatically exclude nursing plans that are not suitable for patients or may cause side effects. This not only improves the scientific nature of nursing plan selection, but also reduces the workload of medical staff, allowing them to focus more on the actual nursing needs of patients.

[0056] Step S5, analyzing the first nursing plan data to generate optimized nursing plan data.

[0057] The generated optimized nursing plan data is based on scientific analysis of the patient's specific situation and nursing plan model, so it is more in line with the patient's actual needs, can improve the quality of nursing and promote the patient's recovery process.

[0058] Step S1 includes the following sub-steps:

[0059] Step S101, collecting the patient's medical history, allergy history, medication records, surgical records and family medical history.

[0060] By collecting the patient's medical history, allergy history, medication records, surgical records, and family medical history, we ensure that we can obtain the patient's comprehensive health background information, which is crucial for assessing the patient's current health status, predicting potential risks, and developing personalized care plans.

[0061] Step S102, storing the patient's past medical history, allergy history, medication record, surgery record and family medical history as detailed medical history data.

[0062] Storing the collected medical history data as detailed medical history data realizes the systematic and standardized management of the data, facilitates the long-term preservation, rapid retrieval and sharing of the data, and improves the convenience and efficiency of data use.

[0063] Step S2 includes the following sub-steps:

[0064] Step S201, cleaning the detailed medical history data, and removing irrelevant data in the detailed medical history data according to a preset common disease set.

[0065] By cleaning detailed medical history data and removing irrelevant, redundant or erroneous information for nursing decisions, the accuracy and efficiency of subsequent data processing and analysis can be significantly improved.

[0066] Step S202, classifying the detailed medical history data into structured data and unstructured data, and outputting the data into a first structured data group and an unstructured data group.

[0067] Dividing detailed medical history data into structured data groups and unstructured data groups helps to achieve orderly management and analysis of data. Structured data is easy for computers to process, while unstructured data contains more details.

[0068] The first structured data group includes the names of past diseases in past medical history, the names of allergens in allergy history, the names of drugs in medication records, the names of surgeries in surgical records, and the names of family diseases in family medical history;

[0069] The unstructured data set includes physician medical records for past medical history, allergic reaction descriptions for allergy history, medication reaction descriptions for medication records, postoperative recovery records for surgical records, and family disease descriptions for family medical history.

[0070] By dividing medical history data into structured and unstructured groups, we can have a more comprehensive and in-depth understanding of the patient's health status, thereby making more scientific and reasonable nursing decisions.

[0071] Step S3 includes the following sub-steps:

[0072] Step S301, segmenting the unstructured data group, removing stop words and extracting stems.

[0073] By performing word segmentation, stop word removal and stemming on unstructured data groups, the format of text data can be optimized to make it more suitable for subsequent text analysis and information extraction processes. Word segmentation helps to divide continuous text into meaningful vocabulary units, and removing stop words reduces the interference of irrelevant vocabulary. Stem extraction helps to merge words with similar morphological changes and improve the accuracy of information extraction.

[0074] Step S302, extracting the preprocessed unstructured data set according to the preset medical entity library, including symptom extraction from doctor's medical records, allergen extraction from allergic reaction descriptions, side effect drug extraction from medication reaction descriptions, sequelae extraction from postoperative recovery records, and genetic disease extraction from family disease descriptions.

[0075] Based on the preset medical entity library, accurate information extraction is performed on the pre-processed unstructured data group, which can automatically identify and extract key information such as symptoms in medical records, allergens in allergic reaction descriptions, side effect drugs in medication reaction descriptions, sequelae in postoperative recovery records, and genetic diseases in family disease descriptions.

[0076] Step S303: Combine the information extracted in step S302 with the first structured data and output them as a second structured data group.

[0077] The information extracted in step S302 is combined with the first structured data and output as a second structured data group, thereby achieving data integration and unification, so that information originally scattered in different data sources can be presented in a centralized manner, facilitating subsequent data analysis and nursing decision-making.

[0078] Step S4 includes the following sub-steps:

[0079] Step S401, input the second structured data group into the unified medical language system, search for the patient's prohibited drugs, drug side effects corresponding to the prohibited drugs, and prohibited treatment methods, and output them as prohibited nursing data.

[0080] The Unified Medical Language System (UMLS) is a giant medical terminology system that has been developed by the U.S. National Library of Medicine for more than 20 years. It covers clinical, basic, pharmacy, biology, medical management and other medical and medical-related disciplines, and includes approximately 2 million medical concepts and more than 5 million medical terms.

[0081] UMLS can be used to design information retrieval or medical record systems, to facilitate communication between different systems, or to develop systems that can parse biomedical literature.

[0082] By inputting the second structured data group into the unified medical language system, it is possible to accurately find the patient's prohibited drugs, the corresponding drug side effects and prohibited treatment methods, ensuring the important link of nursing safety, and helping to avoid the use of drugs or treatment methods that are harmful to patients during the nursing process. The output prohibited nursing data provides a personalized reference basis for subsequent nursing decisions. Medical staff can use these data to avoid prescribing drugs that may cause adverse reactions to patients or using inappropriate treatment methods.

[0083] Step S402, input the disabled nursing data into a preset nursing plan model, compare the disabled treatment means with the nursing plan, compare the drug side effects with the side effect type data, mark the nursing plans corresponding to the nursing plans containing the disabled treatment means and the side effect type data containing the drug side effects, and output the marked nursing plan model as the first nursing plan data.

[0084] After inputting the disabled nursing data into the preset nursing plan model, by comparing the disabled treatments with the nursing plans, the drug side effects with the side effect type data, the nursing plans containing disabled treatments and the nursing plans that may cause drug side effects can be automatically marked. This helps to screen out safe and effective nursing plans, optimize the nursing plan selection process, reduce the errors and omissions that may be caused by human judgment, and improve the accuracy and reliability of nursing decisions.

[0085] Step S5 includes the following sub-steps:

[0086] Step S501: Analyze the first nursing plan data. If the first nursing plan data contains an unmarked nursing plan, output the unmarked nursing plan as an optimized nursing plan.

[0087] By analyzing the data of the first care plan, those unmarked care plans are screened out as candidates for optimized care plans. These plans neither contain prohibited treatments nor involve known drug side effects. Therefore, they are feasible and relatively safe under the current information. This can ensure that the selected plan can provide effective care measures for the patient's specific situation without adding additional risks or burdens.

[0088] Step S502: If all nursing plans in the first nursing plan data are marked, the nursing plan with the least number of marks and the corresponding side effect type data are output as optimized nursing plan data.

[0089] When all nursing plans in the first nursing plan data are marked, it means that each plan has some degree of potential risk, such as prohibited treatment methods or drug side effects. At this time, the nursing plan with the least number of marks is selected as the optimized nursing plan data, aiming to find a balance between risk and benefit. By comparing the number of marks of each nursing plan, the plan with the least marks is selected, which means that the plan may cause relatively fewer side effects or adverse effects, thereby minimizing the potential threat to the patient's health to a certain extent.

[0090] Example 2, refer to Figure 2 , provides a neurological care optimization system, including a medical history data acquisition module, a medical history information extraction module and an optimization solution generation module:

[0091] The medical history data acquisition module is used to acquire and store the patient's detailed medical history data.

[0092] The medical history data acquisition module is responsible for acquiring and storing the patient's detailed medical history data, including past medical history, allergy history, medication records, surgical records and family medical history. These data provide comprehensive and accurate basic information for subsequent nursing decisions.

[0093] By cleaning the detailed medical history data and removing irrelevant or redundant information, the quality of the data is improved, laying a solid foundation for subsequent information extraction and analysis. Dividing the cleaned data into structured data groups and unstructured data groups helps to achieve orderly management and efficient processing of data, extract key information from unstructured data groups, and further enrich the patient's health records.

[0094] The medical history information extraction module is used to clean the detailed medical history data and output it as a first structured data group and an unstructured data group, extract key information from the unstructured data group and combine the extracted data with the first structured data and output it as a second structured data group.

[0095] The optimization plan generation module is used to search for and output disabled nursing data for the second structured data group according to the unified medical language system, input the disabled nursing data into the nursing plan model for screening and output the first nursing plan data, analyze the first nursing plan data and generate optimized nursing plan data, input the disabled nursing data into the nursing plan model for screening, and automatically exclude nursing plans that contain disabled treatment methods or may cause drug side effects, thereby improving the scientificity and safety of nursing decisions.

[0096] The medical history data acquisition module includes a data collection unit and a data storage unit, wherein:

[0097] The data collection unit is used to collect the patient's medical history, allergy history, medication records, surgical records, and family medical history.

[0098] The data collection unit is responsible for extensive and in-depth collection of various types of medical history information of patients, which is an important basis for formulating personalized care plans. Comprehensive collection helps ensure the accuracy and effectiveness of subsequent care decisions.

[0099] The data storage unit is used to store the patient's past medical history, allergy history, medication record, surgery record and family medical history as detailed medical history data.

[0100] The data storage unit stores various types of collected medical history information as detailed medical history data, realizing persistent preservation of the data, which helps to review the patient's medical history information at any time when needed and provides support for nursing decisions.

[0101] The medical history information extraction module includes a data cleaning and classification unit and an information extraction unit, wherein:

[0102] The data cleaning and classification unit is used to clean the detailed medical history data, classify the cleaned detailed medical history data and output them into a first structured data group and an unstructured data group.

[0103] The data cleaning and classification unit ensures the quality and consistency of the data by removing noise, redundancy and errors in the detailed medical history data. At the same time, it classifies the cleaned data into structured data groups and unstructured data groups, making subsequent information processing more targeted and efficient, laying a solid foundation for extracting valuable medical information and converting it into structured data that can be used for nursing decisions.

[0104] The information extraction unit is used to extract key information from the unstructured data group, combine the extracted information with the first structured data, and output them as a second structured data group.

[0105] The information extraction unit focuses on extracting key medical information from unstructured data groups. This key information is then merged with the first structured data group to generate a more comprehensive and accurate second structured data group, which not only enriches the patient's health records, but also improves the data's structuring level, facilitating the formulation and optimization of subsequent care plans.

[0106] The optimization solution generation module includes a data screening unit and an analysis generation unit, wherein:

[0107] The data screening unit is used to search for and output the disabled nursing data for the second structured data group, input the disabled nursing data into the nursing plan model for screening, mark the nursing plan containing the disabled nursing data in the nursing plan model and output the marked nursing plan model as the first nursing plan data.

[0108] The data screening unit first conducts an in-depth search of the second structured data group, accurately identifies and outputs the patient's disabled nursing data. Subsequently, the disabled nursing data is automatically input into the nursing plan model for a strict screening process. Any nursing plan containing disabled nursing data will be clearly marked to ensure that it is excluded or specially considered in subsequent steps. Finally, the data screening unit outputs a strictly screened and marked nursing plan model, namely the first nursing plan data, which provides a solid foundation for subsequent optimization analysis.

[0109] The analysis generation unit is used to perform analysis based on the first nursing plan data. If the first nursing plan data contains unmarked nursing plans, the unmarked nursing plans are output as optimized nursing plans. If all nursing plans in the first nursing plan are marked, the nursing plan with the least number of marks is output as the optimized nursing plan.

[0110] The analysis generation unit first reviews all care plans and looks for those that are not marked, that is, those that do not contain prohibited care data. If such plans exist, they will be directly regarded as optimized care plans and output, because these plans may provide the best care effects for patients while ensuring safety. However, if all care plans are marked, the analysis generation unit will further analyze the number of marks of these plans and select the care plan with the least number of marks as the optimized care plan, which reflects the delicate balance between risks and benefits and aims to provide patients with the safest and most effective care plans possible.

[0111] By collecting and analyzing the patient's medical history data in detail, we can have a more comprehensive understanding of the patient's health status and potential risks, so as to develop more personalized and accurate care plans to meet the specific needs of different patients.

[0112] By screening and marking nursing plans, medical institutions can allocate medical resources more reasonably, give priority to nursing plans with low risks and good effects, avoid unnecessary waste of medical resources, improve the overall efficiency and quality of medical services, and provide strong data support for clinical decision-making, so that medical staff can make more reasonable and scientific nursing decisions based on a full understanding of the patient's condition, thereby improving the overall level of medical services.

[0113] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0114] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing nerve care, characterized in that: The steps include: Step S1, obtaining and storing detailed medical history data of the patient; Step S2, cleaning the detailed medical history data, performing structured data classification and unstructured data classification on the detailed medical history data, and outputting the data into a first structured data group and an unstructured data group; Step S3, extracting key information from the unstructured data group, combining it with the first structured data and outputting it as a second structured data group; Step S4, inputting the second structured data group into a preset nursing plan model and screening it, wherein the nursing plan model includes a plurality of nursing plans and side effect type data corresponding to the nursing plans, and outputting it as first nursing plan data; Step S5, analyzing the first nursing plan data to generate optimized nursing plan data; Step S1 includes the following sub-steps: Step S101, collecting the patient's medical history, allergy history, medication records, surgical records, and family medical history; Step S102, storing the patient's past medical history, allergy history, medication record, surgery record and family medical history as detailed medical history data; The step S2 includes the following sub-steps: Step S201, cleaning the detailed medical history data, and removing irrelevant data in the detailed medical history data according to a preset common disease set; Step S202, classifying the detailed medical history data into structured data and unstructured data, and outputting them into a first structured data group and an unstructured data group; The first structured data group includes the names of past diseases in the past medical history, the names of allergens in the allergy history, the names of drugs in the medication records, the names of surgeries in the surgery records, and the names of family diseases in the family medical history; The unstructured data set includes a doctor's medical record of past medical history, a description of allergic reactions of allergic history, a description of medication reactions of medication records, a postoperative recovery record of surgical records, and a description of family diseases of family medical history; The step S3 includes the following sub-steps: Step S301, segmenting the unstructured data group, removing stop words and extracting stems; Step S302, extracting the preprocessed unstructured data set according to the preset medical entity library, including symptom extraction from doctor's medical records, allergen extraction from allergic reaction descriptions, side effect drug extraction from medication reaction descriptions, sequelae extraction from postoperative recovery records, and genetic disease extraction from family disease descriptions; Step S303, combining the information extracted in step S302 with the first structured data and outputting them as a second structured data group; The step S4 includes the following sub-steps: Step S401, inputting the second structured data group into the unified medical language system, searching for the patient's prohibited drugs, drug side effects corresponding to the prohibited drugs, and prohibited treatment methods, and outputting them as prohibited nursing data; Step S402, inputting the disabled nursing data into a preset nursing plan model, comparing the disabled treatment means with the nursing plan, comparing the drug side effects with the side effect type data, marking the nursing plans including the disabled treatment means and the nursing plans corresponding to the side effect type data including the drug side effects, and outputting the marked nursing plans as first nursing plan data; The step S5 includes the following sub-steps: Step S501, analyzing the first nursing plan data, and if the first nursing plan data contains an unmarked nursing plan, outputting the unmarked nursing plan as an optimized nursing plan; Step S502: If all nursing plans in the first nursing plan data are marked, the nursing plan with the least number of marks and the corresponding side effect type data are output as optimized nursing plan data.

2. A nerve care optimization system, applied to a nerve care optimization method as claimed in claim 1, characterized in that: The system includes a medical history data acquisition module, a medical history information extraction module and an optimization solution generation module: The medical history data acquisition module is used to acquire and store the patient's detailed medical history data; The medical history information extraction module is used to clean the detailed medical history data and output it as a first structured data group and an unstructured data group, extract key information from the unstructured data group and combine the extracted information with the first structured data and output it as a second structured data group; The optimization plan generation module is used to search the second structured data group according to the unified medical language system and output the disabled nursing data, input the disabled nursing data into the nursing plan model for screening and output the first nursing plan data, analyze the first nursing plan data and generate optimized nursing plan data.

3. A neural care optimization system as claimed in claim 2, characterized in that: The medical history data acquisition module includes a data collection unit and a data storage unit, wherein: The data collection unit is used to collect the patient's past medical history, allergy history, medication record, surgical record and family medical history; The data storage unit is used to store the patient's past medical history, allergy history, medication record, surgery record and family medical history as detailed medical history data.

4. A neural care optimization system as claimed in claim 3, characterized in that: The medical history information extraction module includes a data cleaning and classification unit and an information extraction unit, wherein: The data cleaning and classification unit is used to clean the detailed medical history data, classify the cleaned detailed medical history data and output them into a first structured data group and an unstructured data group; The information extraction unit is used to extract key information from the unstructured data group, combine the extracted information with the first structured data, and output the information as a second structured data group.

5. A neural care optimization system as claimed in claim 4, characterized in that: The optimization solution generation module includes a data screening unit and an analysis generation unit, wherein: The data screening unit is used to search for the second structured data group and output the disabled nursing data, input the disabled nursing data into the nursing plan model for screening, mark the nursing plan containing the disabled nursing data in the nursing plan model and output the marked nursing plan as the first nursing plan data; The analysis generation unit is used to perform analysis based on the first nursing plan data. If the first nursing plan data contains unmarked nursing plans, the unmarked nursing plans are output as optimized nursing plans. If all nursing plans in the first nursing plan are marked, the nursing plan with the least number of marks is output as the optimized nursing plan.

Images