Artificial intelligence-based full-process supervision method and system for rehabilitation patients

Abstract

The present disclosure provides an artificial intelligence-based full-process supervision method and system for rehabilitation patients, comprising: obtaining medical-related data of all patients in a hospital, using a pre-built rule engine to obtain rehabilitation patient characterization data corresponding to each patient from the medical-related data, and constructing a temporary data set; based on the rehabilitation patient characterization data, by matching rules with the rule engine, each data in the temporary data set is classified into risk levels, and rehabilitation patients are pre-screened from the temporary data set according to the risk levels; the pre-screened rehabilitation patients are combined with their corresponding rehabilitation data, and the data are pushed to rehabilitation doctors; the rehabilitation doctors actively initiate consultations with rehabilitation patients, and formulate rehabilitation plans after creating files; and the above process is cyclically executed according to a preset cycle.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of rehabilitation patient supervision, and in particular relates to an artificial intelligence-based full-process supervision method and system for rehabilitation patients. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] With the increasing public awareness of rehabilitation, the public's demand for rehabilitation has become increasingly prominent. Rehabilitation medicine is of great significance to achieving universal health. In recent years, the number of beds in hospital rehabilitation departments has increased year by year. This shows that the public's awareness of rehabilitation is getting stronger and stronger, which in turn drives the patients' awareness of rehabilitation during their stay in the hospital. However, how can a non-rehabilitation patient enjoy the services of the rehabilitation department? There are still the following difficulties:

[0004] (1) The hospital has serious information silos. The information software of multiple manufacturers cannot be interconnected. Rehabilitation doctors, apart from the patients in their own department, have no idea about the conditions of patients in other departments and whether they need rehabilitation.

[0005] (2) Even if the connection with the rehabilitation doctors is established, with thousands of patients in the hospital, the rehabilitation doctors cannot determine which patients need their special attention. If they pay attention to all patients, it will be costly, complex and have poor performance.

[0006] (3) Apart from clinical departments actively inviting rehabilitation experts for consultation, the hospital lacks the ability to comprehensively perceive, analyze and manage patients in the hospital who are suspected of being eligible for rehabilitation treatment.

[0007] (4) The data of multiple health care institutions in the county cannot be interconnected, and patients cannot enjoy the three-level linkage rehabilitation services of the county, township and village. Since the information chain is broken, the service chain is also broken outside the hospital, and the full-process rehabilitation management of rehabilitation patients cannot be achieved. Summary of the Invention

[0008] In order to solve the above problems, the present disclosure provides an artificial intelligence-based full-process supervision method and system for rehabilitation patients. The solution integrates data from the patient's entire life cycle, breaks down information silos, and integrates various information. Rehabilitation doctors can easily obtain the vital signs information and previous medical records of all patients in the hospital, and then quickly and effectively identify which patients require rehabilitation treatment.

[0009] According to a first aspect of an embodiment of the present disclosure, a method for supervising the entire process of rehabilitation patients based on artificial intelligence is provided, comprising:

[0010] Obtain medical data of all patients in the hospital, and use a pre-built rule engine to obtain rehabilitation patient representation data corresponding to each patient from the medical data to construct a temporary data set;

[0011] Based on the characterization data of the rehabilitation patients, each piece of data in the temporary data set is classified into a risk level by matching the data with the rules in the rule engine, and rehabilitation patients are pre-screened from the temporary data set according to the risk level; wherein, the construction of the rule engine specifically comprises: based on the relevant data of the rehabilitation patients that have been determined to be rehabilitation patients, obtaining the common data of the rehabilitation patients and the individual data of rehabilitation patients of different categories as the rehabilitation patient determination rules;

[0012] Combine the pre-screened rehabilitation patients with their corresponding rehabilitation data and push them to the rehabilitation doctors;

[0013] Rehabilitation doctors will proactively initiate consultations with rehabilitation patients and develop rehabilitation plans after creating files;

[0014] The above process is cyclically executed according to the preset cycle.

[0015] Furthermore, lightweight rehabilitation patient characterization data is obtained from the medical-related data, wherein the rehabilitation patient characterization data includes common data of rehabilitation patients and individual data of different types of rehabilitation patients.

[0016] Furthermore, the preset rule engine is used to classify the risk level of each data in the temporary data set, and pre-screen rehabilitation patients from the temporary data set according to the risk level. Specifically, a semantic analysis algorithm is used to calculate the similarity between each data item in each data in the temporary data set and each rule in the rule engine, and the risk level of each data is classified based on the similarity.

[0017] Furthermore, the pre-screening of recovered patients from the temporary data set according to the risk level is specifically as follows:

[0018] For each data item in each piece of data in the temporary data set, obtain its corresponding risk level; wherein each piece of data corresponds to the rehabilitation patient representation data of a patient;

[0019] If the risk levels of all data items of each data are empty, it is determined that the patient does not need rehabilitation treatment and is removed from the temporary data set, and finally the pre-screened rehabilitation patients are obtained.

[0020] Furthermore, the pre-screened rehabilitation patients are combined with their corresponding rehabilitation data and pushed to the rehabilitation doctors, specifically:

[0021] For each pre-screened rehabilitation patient, the corresponding rehabilitation data is set with an identifier of whether it has been processed; the processed mark is 0, and the unprocessed mark is 1;

[0022] Based on the sum of the identification results of all rehabilitation data corresponding to each rehabilitation patient, determine the current rehabilitation patient status information, wherein the status information includes processed, newly discovered, and rediscovered;

[0023] Newly discovered and re-discovered rehabilitation patients and their corresponding rehabilitation data will be pushed to rehabilitation doctors for follow-up processing.

[0024] Furthermore, for rehabilitation patients who have completed rehabilitation and are discharged from the hospital, if the rehabilitation patients have the need to continue rehabilitation treatment at the next-level medical institution, the relevant information of the rehabilitation patients will be stored and sent to the information system of the next-level medical institution and synchronized to the terminal device of the rehabilitation patients.

[0025] Furthermore, for rehabilitation patients who need to continue rehabilitation treatment at the next level of medical institutions, the next level of medical institutions will match the diagnosis and treatment plans of patients with similar conditions and basic vital signs to the current rehabilitation patients based on the relevant information of the rehabilitation patients and the preset regional rule engine, and store them.

[0026] According to a second aspect of an embodiment of the present disclosure, a full-process monitoring system for rehabilitation patients based on artificial intelligence is provided, comprising:

[0027] A data acquisition unit is used to acquire medical-related data of all patients in the hospital, and use a pre-built rule engine to obtain the rehabilitation patient representation data corresponding to each patient from the medical-related data to construct a temporary data set;

[0028] a pre-screening unit configured to classify each piece of data in the temporary data set into a risk level based on the characterization data of the rehabilitation patients and by matching the data with the rules in the rule engine, and to pre-screen rehabilitation patients from the temporary data set according to the risk level; wherein the construction of the rule engine specifically comprises: based on the relevant data of the rehabilitation patients that have been determined to be rehabilitation patients, obtaining common data of rehabilitation patients and individual data of rehabilitation patients of different categories as rehabilitation patient determination rules;

[0029] A push unit, which is used to combine the pre-screened rehabilitation patients with their corresponding rehabilitation data and push them to the rehabilitation doctors;

[0030] The rehabilitation treatment unit is used by rehabilitation doctors to initiate consultations with rehabilitation patients and develop rehabilitation plans after creating files;

[0031] The cyclic execution unit is used to cyclically execute the above process according to a preset period.

[0032] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored and running on the memory, wherein when the processor executes the program, the method for full-process supervision of rehabilitation patients based on artificial intelligence is implemented.

[0033] According to a fourth aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for full-process supervision of rehabilitation patients based on artificial intelligence is implemented.

[0034] Compared with the prior art, the present invention has the following advantages:

[0035] (1) The present disclosure provides a method and system for monitoring the entire process of rehabilitation patients based on artificial intelligence. The solution integrates the data of the patient's entire life cycle (including integrated data during the hospital stay), breaks the information island, and integrates various information. Rehabilitation doctors can easily obtain the vital signs information and previous medical records of all patients in the hospital.

[0036] (2) The solution disclosed in this disclosure can truly realize one bed for the entire hospital, allowing all patients in the hospital to be truly exposed to the supervision of the rehabilitation department; at the same time, the solution is based on artificial intelligence technology to screen out patients in the hospital who meet the rehabilitation requirements and present them to the doctors of the rehabilitation department for focused attention, thereby accurately radiating patients through information technology.

[0037] (3) The solution disclosed in this disclosure provides a complete management mechanism from screening, confirmation, intervention treatment, to effect evaluation, and closed-loop management of all links, truly solving the problem of patient circulation within the hospital.

[0038] (4) The solution disclosed in this disclosure, with the help of the medical community platform, breaks through the boundaries of health care institutions at all levels in counties, towns and villages, and can track the entire process of patients who have undergone rehabilitation in the entire county. Within the entire rehabilitation plan, patients can enjoy full-process rehabilitation services in county-level medical institutions, township medical institutions, and community / village clinics.

[0039] Advantages of additional aspects of the present disclosure will be given in part in the following description and in part will become apparent from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which constitute a part of the present disclosure, are used to provide a further understanding of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure.

[0041] Figure 1This is a flow chart of a method for full-process supervision of rehabilitation patients based on artificial intelligence described in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] The present disclosure will be further described below with reference to the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present disclosure belongs.

[0044] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0045] In the absence of conflict, the embodiments of the present disclosure and the features thereof may be combined with each other.

[0046] Explanation of English abbreviations:

[0047] RP:rehabilitate patients

[0048] RPC: rehabilitate patients consultate

[0049] HRP:handle rehabilitate patients

[0050] BID: basic information data

[0051] DRP: data rehabilitate patients

[0052] DBP:databasic rehabilitate patients

[0053] RPPT: rehabilitation patient plan treatment

[0054] Example 1:

[0055] The purpose of this embodiment is to provide an artificial intelligence-based full-process supervision method for rehabilitation patients.

[0056] An AI-based method for monitoring the entire rehabilitation process, including:

[0057] Obtain medical data of all patients in the hospital, and use a pre-built rule engine to obtain rehabilitation patient representation data corresponding to each patient from the medical data to construct a temporary data set;

[0058] Based on the characterization data of the rehabilitation patients, each piece of data in the temporary data set is classified into a risk level by matching the data with the rules in the rule engine, and rehabilitation patients are pre-screened from the temporary data set according to the risk level; wherein, the construction of the rule engine specifically comprises: based on the relevant data of the rehabilitation patients that have been determined to be rehabilitation patients, obtaining the common data of the rehabilitation patients and the individual data of rehabilitation patients of different categories as the rehabilitation patient determination rules;

[0059] Combine the pre-screened rehabilitation patients with their corresponding rehabilitation data and push them to the rehabilitation doctors;

[0060] Rehabilitation doctors will proactively initiate consultations with rehabilitation patients and develop rehabilitation plans after creating files;

[0061] The above process is cyclically executed according to the preset cycle.

[0062] In a specific embodiment, lightweight rehabilitation patient characterization data is obtained from the medical-related data, wherein the rehabilitation patient characterization data includes common data of rehabilitation patients and individual data of different types of rehabilitation patients.

[0063] The method utilizes a preset rule engine to classify each piece of data in the temporary data set into a risk level, and pre-screens rehabilitation patients from the temporary data set according to the risk level. Specifically, a semantic analysis algorithm is used to calculate the similarity between each data item in each piece of data in the temporary data set and each rule in the rule engine, and the risk level of each piece of data is classified based on the similarity.

[0064] The pre-screening of rehabilitation patients from the temporary data set according to the risk level is specifically as follows:

[0065] For each data item in each piece of data in the temporary data set, obtain its corresponding risk level; wherein each piece of data corresponds to the rehabilitation patient representation data of a patient;

[0066] If the risk levels of all data items of each data are empty, it is determined that the patient does not need rehabilitation treatment and is removed from the temporary data set, and finally the pre-screened rehabilitation patients are obtained.

[0067] The pre-screened rehabilitation patients are combined with their corresponding rehabilitation data and pushed to the rehabilitation doctors, specifically:

[0068] For each pre-screened rehabilitation patient, the corresponding rehabilitation data is set with an identifier of whether it has been processed; the processed mark is 0, and the unprocessed mark is 1;

[0069] Based on the sum of the identification results of all rehabilitation data corresponding to each rehabilitation patient, determine the current rehabilitation patient status information, wherein the status information includes processed, newly discovered, and rediscovered;

[0070] Newly discovered and re-discovered rehabilitation patients and their corresponding rehabilitation data will be pushed to rehabilitation doctors for follow-up processing.

[0071] For rehabilitation patients who have completed rehabilitation and are discharged from the hospital, if they have a need to continue rehabilitation treatment at the next level of medical institutions, the relevant information of the rehabilitation patients will be stored and sent to the information system of the next level of medical institutions and synchronized to the terminal devices of the rehabilitation patients. For rehabilitation patients who have a need to continue rehabilitation treatment at the next level of medical institutions, the next level of medical institutions will match the diagnosis and treatment plans of patients with similar conditions and basic vital signs to the current rehabilitation patients based on the relevant information of the rehabilitation patients and the preset regional rule engine, and store the plans.

[0072] For ease of understanding, as shown in the figure, the following describes the full-process monitoring of rehabilitation patients within the hospital and within the county. The steps for monitoring the full-process of rehabilitation patients within the hospital are as follows:

[0073] Step 1: Based on the rehabilitation patients' medical records, rehabilitation assessment records, rating scales, and various nursing document data, the data is integrated, converted, cleaned, and sorted to form a new data set A. The data is further abstracted to form our rule library for rehabilitation patient screening and establish a rule engine B for supervising patients throughout the hospital.

[0074] Specifically, step 1 includes the following processing steps:

[0075] Step 101: Actively acquire data from confirmed rehabilitation patients (using direct connections to the electronic medical record (EMR), rehabilitation system, and nursing document rehabilitation record database to directly read data from other systems). Using an ETL data extraction tool and a scheduled task, collect data within a scheduled time T (the shorter the time, the more timely it is, but the higher the data processing speed requirement, generally 10 minutes) and store it in data set table A1.

[0076] Step 102: Convert, clean, and sort the data in dataset table A1 to form a dataset A that includes but is not limited to the patient's unique identifier, patient's hospitalization number, patient's name, patient's department ID, patient's department name, test item code, test item name, test item detail code, test item detail name, test unique identifier, test result, test time, and test source (medical record EMR, rehabilitation, various record sheets).

[0077] Step 103: Analyze and abstract Dataset A, mainly to obtain common data of rehabilitation patients and form our rule base. Basic basis:

[0078] a) Starting from the admission records, medical records, and surgical records of all inpatients in the hospital's clinical departments, we sorted out specific disease keywords: coughing when drinking water, dysphagia, drinking water test, tracheotomy, and tube feeding.

[0079] b) In the rehabilitation assessment record sheet, for patients whose assessment scores are above the standard score, their assessment items will be listed.

[0080] Specifically, the purpose of step 103 is to obtain the common data of all rehabilitation patients from data set A based on expert analysis and evaluation, as well as the individual data of each category of rehabilitation patients, wherein the categories of rehabilitation patients can be divided according to age, gender, whether the surgery is completed, whether the hospitalization lasts for more than 30 days, etc. The specific category division can be adjusted according to actual needs; the common data refers to the indicator data shared by rehabilitation patients of different categories, and the individual data refers to the indicator data unique to a certain category of rehabilitation patients.

[0081] Step 104: The rule base formed in step 103 is timed to form a rule engine B for screening rehabilitation patients.

[0082] Step 2: Based on rule engine B, monitor all patients in the hospital, filter and screen their data, and store the screening results in the rehabilitation patient pre-screening table RP (with a unique identifier).

[0083] Specifically, step 2 includes the following processing steps:

[0084] Step 201: The rules engine for rehabilitation patient screening is activated in real time. All patients in the hospital are monitored in real time. Based on the rules and processes of the previously generated dataset A, the patient-specific data is extracted in a lightweight manner to form a temporary dataset D1.

[0085] Step 202: Traverse each piece of data I in the data set D1, match it with each rule in the rule engine B, and mark the risk level of this piece of data (1. Common, 2. Medium, 3. Suspected, 4. Confirmed) according to the matching rules, until all matching rules in the rule engine B are matched, forming a risk level set R; wherein the matching rules are specifically: based on the semantic analysis algorithm, each attribute in each piece of data I (which corresponds to a patient) is calculated to perform similarity calculation with the corresponding rule in the rule engine B to obtain the risk identification of this piece of data. Specifically, the risk identification is divided into four levels based on the similarity value and preset thresholds (including the first threshold, the second threshold, the third threshold, and the fourth threshold):

[0086] When the similarity value is less than the first threshold: the risk level is null (i.e., no rehabilitation is required);

[0087] When the similarity value is greater than or equal to the first threshold and less than the second threshold: the risk level is 1. Normal;

[0088] When the similarity value is greater than or equal to the second threshold and less than the third threshold: the risk level is 2. Medium;

[0089] When the similarity value is greater than or equal to the third threshold and less than the fourth threshold: the risk level is 3. Suspected;

[0090] When the similarity value is greater than or equal to the fourth threshold: the risk level is 4. Confirm.

[0091] Step 203: For each data I in the temporary data set D1, if the risk level set R in the data I is empty, remove the data I in the data set D1. If the risk level is not empty, sort the risk level set R from high to low according to the risk level, take the data set with the highest risk level, take its risk level field and matching rule unique identification field and merge them into the data I. After the risk content is added to the data I, the data set changes from D1 to DS1.

[0092] Step 204: The data set DS1 is stored in the data table RP. The unique identifier in the data set DS1 is used as the primary key of the data table RP. Therefore, there will be no duplicate rehabilitation data in the data table RP. At the same time, the DS1 data set is cleared.

[0093] Step 3: Combine the data from the Rehabilitation Patient Pre-screening Table (RP) and notify the rehabilitation physician to process it. The physician will mark the patient as eligible for rehabilitation and initiate a mandatory consultation. The data will be stored in the Rehabilitation Patient Consultation Table (RPC). A mandatory consultation is a mandatory consultation initiated by the rehabilitation physician for eligible patients, meaning that the patient must attend. It should be noted that currently, consultations are initiated by the patient. If the patient does not initiate the consultation or the physician fails to process the consultation, no valid data will be generated, and the patient will not be effectively monitored.

[0094] Wherein, the step 3 specifically includes the following processing steps:

[0095] Step 301: A processing flag is added to each piece of rehabilitation data for each patient in the rehabilitation patient pre-screening table RP. When suspected data is added to the data table RP, the high-risk data list is linked to the treatment information table HRP to form a data set BID. Data that exists in the treatment information table HRP is marked as 0, while data that does not exist is marked as 1.

[0096] Among them, suspected data information: real-time monitoring and continuous improvement of rules will continuously discover new data based on the original data of suspected recovered patients to prove that the patient is infinitely close to being confirmed as a recovered patient; high-risk data list: during the setting process of the rule engine, there are some mandatory options. If these mandatory options are triggered in the patient's data, the data will be marked as high-risk data and linked to the detailed treatment information table;

[0097] Disposal information details table HRP: mainly includes the table primary key, main fields include the table primary key, handler, processing time, processing method (1. Writing opinions 2. Exclusion), patient unique identifier, patient name, patient risk level (1 common 2 medium 3 suspected, 4 confirmed) and RP primary key.

[0098] Step 302: Merge each piece of rehabilitation data in the dataset BID based on the patient, classify the dataset BID according to the patient, and form a patient rehabilitation information set DRP. The dataset DRP should include basic fields such as patient information and a rehabilitation information set DBP (DBP mainly includes other information in BID in addition to the basic patient information).

[0099] Step 303: Identify the risk level and risk source information for each patient in the dataset DRP. Specifically, analyze the dataset DBP one by one, take the highest risk level in DBP as the patient's rehabilitation risk level, merge the matching results in DBP, and simultaneously identify the risk source information for each result during the merging. The risk source information is the information in the medical record, including but not limited to: 1. Chief complaint: the description of the condition in the patient's chief complaint, such as choking while drinking water, dysphagia, water swallowing test, tracheotomy, and tube feeding, and the physical examination findings; 2. The patient's physical sign scores in various record sheets: information in the Barton score, Fugl-Meyer balance function assessment, and Berg balance scale).

[0100] Step 304: Identify whether each patient in the dataset DRP has been processed. Sum the processed identification fields of the data in DBP (the number of data is C), and the result value is S:

[0101] a) If the sum of the patient data processing identifications is 0, it indicates that all the rehabilitation information of this patient has been processed, and it is marked as "processed".

[0102] b) If the number of data C is equal to the result value S, it indicates that all the rehabilitation information of this patient has not been processed, and it is a newly discovered patient, marked as "newly discovered".

[0103] c) If the result is 0 < S < C, it indicates that new risky rehabilitation information has been discovered after processing this patient, and it is marked as "rediscovered".

[0104] Step 305: Use the webSocket method to promptly notify the users of the patients who meet the rehabilitation conditions and are marked as "newly discovered" and "rediscovered" in Step 304 to the user interface.

[0105] The rehabilitation doctors perform operations such as diagnosis and treatment, billing, etc. through consultation and store the data in the rehabilitation patient consultation form RPC. And file the patients. Only the filed patients can establish a rehabilitation plan and conduct a closed-loop rehabilitation management.

[0106] Step 4: Develop a rehabilitation plan, form a rehabilitation diagnosis and treatment plan for the rehabilitation patients during their hospitalization, store it in the rehabilitation diagnosis and treatment plan table RPPT, and execute it in a loop.

[0107] Specifically, the said Step 4 includes the following processing procedures:

[0108] Step 401: Develop a rehabilitation plan based on the filed patients. When developing the rehabilitation plan, perform an intelligent matching of this patient based on the rule engine B, and match the diagnosis and treatment plans of patients with similar conditions and basic vital signs. The diagnosis and treatment plans are stored in the rehabilitation diagnosis and treatment plan table RPPT.

[0109] Step 402: Based on the rule engine B, the RPPT table is monitored in real time, and the rehabilitation treatment plan is constantly updated. The rehabilitation doctor is notified in advance through the medical information mobile terminal. The patient is notified in advance through the patient intelligent service system until the patient is discharged after recovery.

[0110] In specific implementation, the steps for monitoring the entire process of rehabilitation patients within the county are as follows:

[0111] Step 1: For patients discharged from the hospital after rehabilitation, the doctor will ask the patient whether to continue rehabilitation treatment in a community, township, or other medical institution based on their condition. If the patient agrees, the doctor will select community rehabilitation. This patient information is stored in the community rehabilitation pre-selection table CBR_T.

[0112] Step 2: Through the regional rehabilitation system in the close-knit medical community platform, the data in the in-hospital community rehabilitation pre-selection form CBR_T has been downloaded in real time to the information system of the patient's community or township health center, and simultaneously pushed to the patient's mobile phone.

[0113] Step 3: Develop a rehabilitation plan. When developing a rehabilitation plan, the regional rule engine C_B is used to intelligently match the patient to treatment plans of patients with similar conditions and basic vital signs. The treatment plans are stored in the rehabilitation treatment plan table C_RPPT.

[0114] Step 4: The regional rule engine C_B monitors the C_RPPT table in real time, issues real-time reminders about the rehabilitation treatment plan, and notifies the rehabilitation doctor in advance via the medical information mobile app. The patient is also notified in advance via the patient intelligent service system until the patient's recovery is complete.

[0115] Among them, the regional rule engine C_B here adopts the same processing mechanism as the above-mentioned rule engine B, so it will not be repeated here.

[0116] Example 2:

[0117] The purpose of this embodiment is to provide an artificial intelligence-based full-process monitoring system for rehabilitation patients.

[0118] An AI-based full-process monitoring system for rehabilitation patients, including:

[0119] A data acquisition unit is used to acquire medical-related data of all patients in the hospital, and use a pre-built rule engine to obtain the rehabilitation patient representation data corresponding to each patient from the medical-related data to construct a temporary data set;

[0120] a pre-screening unit configured to classify each piece of data in the temporary data set into a risk level based on the characterization data of the rehabilitation patients and by matching the data with the rules in the rule engine, and to pre-screen rehabilitation patients from the temporary data set according to the risk level; wherein the construction of the rule engine specifically comprises: based on the relevant data of the rehabilitation patients that have been determined to be rehabilitation patients, obtaining common data of rehabilitation patients and individual data of rehabilitation patients of different categories as rehabilitation patient determination rules;

[0121] A push unit, which is used to combine the pre-screened rehabilitation patients with their corresponding rehabilitation data and push them to the rehabilitation doctors;

[0122] The rehabilitation treatment unit is used by rehabilitation doctors to initiate consultations with rehabilitation patients and develop rehabilitation plans after creating files;

[0123] The cyclic execution unit is used to cyclically execute the above process according to a preset period.

[0124] Furthermore, the system described in this embodiment corresponds to the method described in Example 1, and its technical details have been described in detail in Example 1, so they will not be repeated here.

[0125] In further embodiments, there is also provided:

[0126] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed by the processor. When the computer instructions are executed by the processor, the method described in Example 1 is performed. For the sake of brevity, no further details are given here.

[0127] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0128] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0129] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in embodiment 1 is performed.

[0130] The method in Example 1 can be directly implemented as being executed by a hardware processor, or by a combination of hardware and software modules within the processor. The software module can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not given here.

[0131] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in this embodiment can be implemented using electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0132] The above-mentioned embodiment provides an artificial intelligence-based full-process supervision method and system for rehabilitation patients, which can be implemented and has broad application prospects.

[0133] The foregoing description is merely a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present disclosure shall be included within the scope of protection of the present disclosure.

Claims

1. A full-process supervision method for rehabilitation patients based on artificial intelligence, characterized in that: include: Obtain medical data of all patients in the hospital, and use a pre-built rule engine to obtain rehabilitation patient representation data corresponding to each patient from the medical data to construct a temporary data set; Based on the characterization data of the rehabilitation patients, each piece of data in the temporary data set is classified into a risk level by matching the rules with the rule engine, and rehabilitation patients are pre-screened from the temporary data set according to the risk level, specifically by using a semantic analysis algorithm to calculate the similarity between each data item in each piece of data in the temporary data set and each rule in the rule engine, and implementing the risk level classification of each piece of data based on the similarity; wherein, the construction of the rule engine specifically comprises: based on the relevant data that has been determined to be rehabilitation patients, obtaining the common data of rehabilitation patients and the individual data of rehabilitation patients of different categories as the judgment rules for rehabilitation patients; Combine the pre-screened rehabilitation patients with their corresponding rehabilitation data and push them to the rehabilitation doctors, specifically: For each pre-screened rehabilitation patient, the corresponding rehabilitation data is set with an identifier of whether it has been processed; the processed mark is 0, and the unprocessed mark is 1; Based on the sum of the identification results of all rehabilitation data corresponding to each rehabilitation patient, determine the current rehabilitation patient status information, wherein the status information includes processed, newly discovered, and rediscovered; Push newly discovered and re-discovered rehabilitation patients and their corresponding rehabilitation data to rehabilitation doctors for follow-up processing; Rehabilitation doctors will proactively initiate consultations with rehabilitation patients and develop rehabilitation plans after creating files; The above process is cyclically executed according to the preset cycle.

2. The method for monitoring the entire process of rehabilitation patients based on artificial intelligence according to claim 1, characterized in that: The pre-screening of rehabilitation patients from the temporary data set according to the risk level is specifically as follows: For each data item in each piece of data in the temporary data set, obtain its corresponding risk level; wherein each piece of data corresponds to the rehabilitation patient representation data of a patient; If the risk levels of all data items of each data are empty, it is determined that the patient does not need rehabilitation treatment and is removed from the temporary data set, and finally the pre-screened rehabilitation patients are obtained.

3. The method for monitoring the entire process of rehabilitation patients based on artificial intelligence according to claim 1, characterized in that: For rehabilitation patients who have completed rehabilitation and are discharged from the hospital, if they need to continue rehabilitation treatment at the next level of medical institutions, the relevant information of the rehabilitation patients will be stored and sent to the information system of the next level of medical institutions and synchronized to the terminal devices of the rehabilitation patients.

4. The method for monitoring the entire process of rehabilitation patients based on artificial intelligence according to claim 1, characterized in that: For rehabilitation patients who need to continue rehabilitation treatment at the next level of medical institutions, the next level of medical institutions will match the diagnosis and treatment plans of patients with similar conditions and basic vital signs to the current rehabilitation patients based on the relevant information of the rehabilitation patients and the preset regional rule engine, and store them.

5. An artificial intelligence-based full-process monitoring system for rehabilitation patients, characterized by: include: A data acquisition unit is used to acquire medical-related data of all patients in the hospital, and use a pre-built rule engine to obtain the rehabilitation patient representation data corresponding to each patient from the medical-related data to construct a temporary data set; A pre-screening unit is used to classify the risk level of each data in the temporary data set based on the characterization data of the rehabilitation patients by matching the rules with the rule engine, and pre-screen the rehabilitation patients from the temporary data set according to the risk level, specifically by using a semantic analysis algorithm to calculate the similarity between each data item in each data item in the temporary data set and each rule in the rule engine, and based on the similarity, implement the risk level classification of each data item; wherein, the construction of the rule engine is specifically: based on the relevant data that has been determined to be rehabilitation patients, obtain the common data of rehabilitation patients and the individual data of rehabilitation patients of different categories as the judgment rules for rehabilitation patients; The push unit is used to combine the pre-screened rehabilitation patients with their corresponding rehabilitation data and push them to the rehabilitation doctors. Specifically: For each pre-screened rehabilitation patient, the corresponding rehabilitation data is set with an identifier of whether it has been processed; the processed mark is 0, and the unprocessed mark is 1; Based on the sum of the identification results of all rehabilitation data corresponding to each rehabilitation patient, determine the current rehabilitation patient status information, wherein the status information includes processed, newly discovered, and rediscovered; Push newly discovered and re-discovered rehabilitation patients and their corresponding rehabilitation data to rehabilitation doctors for follow-up processing; The rehabilitation treatment unit is used by rehabilitation doctors to initiate consultations with rehabilitation patients and develop rehabilitation plans after creating files; The cyclic execution unit is used to cyclically execute the above process according to a preset period.

6. An electronic device comprising a memory, a processor, and a computer program stored and running on the memory, characterized in that: When the processor executes the program, it implements an artificial intelligence-based full-process supervision method for rehabilitation patients as described in any one of claims 1-4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a full-process supervision method for rehabilitation patients based on artificial intelligence as described in any one of claims 1 to 4.

Images