Bidirectional referral method, system and equipment

Abstract

The invention relates to the technical field of medical information, in particular to a two-way referral method, system and equipment. The method comprises the following steps: screening each referral medical institution of which each referral measurement index value is greater than the minimum value of each referral measurement index required for receiving one patient in the current time period, and calculating the maximum number of patients capable of being received by each referral medical institution in the current time period; obtaining the importance score of each patient for each referral measurement index and each referral measurement index value of each patient for each referral medical institution in the current time period, and constructing a preference function of each patient for each referral medical institution; and determining a to-be-referral medical institution of each patient, counting the to-be-referral number of each referral medical institution, and realizing reasonable distribution of medical referral based on the to-be-referral number of each referral medical institution in the current time period and the maximum number of patients capable of being received. According to the invention, dynamic and efficient referral matching between the patient and the medical institution is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a two-way referral method, system and device. Background Art

[0002] Due to the diversification of patient needs, referral can optimize resource allocation, improve patient treatment outcomes, promote the development of medical technology exchanges, and enhance the coordination and integrity of the medical service system. In the medical field, the development of intelligent referral technology has gone through multiple stages. In the early days, referrals mainly relied on manual experience and judgment, and information communication between medical institutions was not smooth, resulting in inefficient referrals and failure to ensure that patients received timely and appropriate referral arrangements. With the gradual rise of information technology, some simple electronic referral systems began to appear, but these systems were relatively simple in function and could only achieve basic referral information transmission, lacking effective support for referral decisions.

[0003] In recent years, the rapid development of technologies such as big data and artificial intelligence has brought new opportunities for intelligent referral technology. With the gradual rise of information technology, some electronic referral systems have begun to appear. In order to improve the timeliness of emergency treatment, in patent CN114188001A, researchers use 5G technology and its low latency and large bandwidth characteristics to achieve high-speed real-time transmission of vital signs data, videos and other information of children, so as to improve referral efficiency. In order to make referral more efficient, in patent CN109637640A, researchers based on user feedback and historical data algorithms, analyzed the average satisfaction of users with medical questions and the first historical reply time, determined the preset time, and used this as the basis for judging whether to refer, so as to achieve more accurate referral decisions. In order to fully understand the resource distribution of medical institutions, in CN113628729A, researchers have developed a data layer and hospital resource database to store basic information of each hospital and doctor information, provide data support for referral matching, and ensure that the appropriate referral recipient is found accurately.

[0004] However, these systems have relatively simple functions and can only realize basic referral information transmission, lacking effective support for referral decisions. First, in the existing technology, there are defects in data fusion. For example, although patent CN113628729A has built a data layer and database, the data integration between the patent technologies is insufficient, and there is a lack of a comprehensive data fusion system. It is difficult to fully integrate multi-source data to achieve more efficient referral decisions, resulting in insufficient data fusion, and it is difficult to provide rich and accurate basis for referral decisions, which makes referral decisions prone to one-sidedness and other problems. Secondly, the consideration of patient needs is not comprehensive enough. Patient needs are subjective and time-varying, and existing systems such as patent CN109637640A are only based on the limited feedback and historical response time of users' responses to medical questions, ignoring the personalized preferences of patients at different stages of illness and different psychological states, as well as the dynamic changes in needs. It is difficult to adjust the referral strategy in time according to the real-time needs of patients, and it is impossible to truly provide referral services that meet patients' expectations. In addition, in the existing technology, matching algorithms often lack scientific and reasonable construction basis, and are mostly designed based on limited experience or local data, without fully considering the complex and changeable actual situation of medical referrals. This leads to frequent matching errors in the referral process, unreasonable allocation and waste of medical resources, and the patient's medical experience is greatly reduced due to the inaccurate and inefficient referral, making it impossible to achieve efficient use of medical resources and optimized medical services for patients. Summary of the invention

[0005] To this end, the technical problem to be solved by the present invention is to overcome the defects of the existing two-way referral method, such as insufficient data fusion, insufficient consideration of patient needs, and the lack of scientific and reasonable construction basis for the matching algorithm, which leads to insufficient matching accuracy and low referral efficiency.

[0006] In order to solve the above technical problems, the present invention provides a two-way referral method, comprising the following steps: Obtain the medical institution's admission metrics and patient referral metrics to medical institutions; Screen all referable medical institutions whose values ​​of various reception metrics are greater than the minimum values ​​of various reception metrics required to receive one patient in the current period, and calculate the maximum number of patients that each referable medical institution can receive in the current period; Obtain each patient's importance score for each referral metric and each patient's referral metric value for each referable medical institution in the current period, and construct each patient's preference function for each referable medical institution; The referable medical institution corresponding to each patient's maximum preference function value for each referable medical institution is used as the proposed referral medical institution for the patient; Count the medical institutions to which each patient is to be referred, and determine the number of proposed referrals to each medical institution that can be referred during the current period; If the maximum number of patients that the current referable medical institution can accept in the current period is greater than or equal to the number of patients it intends to refer, the current referable medical institution will accept all patients intended to be referred to the referable medical institution; if the maximum number of patients that the current medical institution can accept in the current period is less than the number of patients it intends to refer, the current medical institution will accept the maximum number of patients intended to be referred to the medical institution and provide a notification of refusal of referral to the patients who are not accepted.

[0007] Preferably, the medical institution's reception metrics are obtained, including: Obtain the initial admission measurement indicators of the medical institution, with the goal of quantifying the initial admission measurement indicators of the medical institution, construct a keyword thesaurus for each initial admission measurement indicator of the medical institution, collect data using the keyword of each initial admission measurement indicator as an index, and obtain the data corresponding to each initial admission measurement indicator of the medical institution; The data corresponding to each initial admission metric of the medical institution are keyword extracted and converted into the same mode, and the weight of each initial admission metric of the medical institution is determined by weighted analysis method; The weights of various initial consultation measurement indicators of the medical institution are sorted in descending order, and the first preset number of initial consultation measurement indicators are taken as the consultation measurement indicators of the medical institution.

[0008] Preferably, the patient's referral metrics to medical institutions are obtained, including: Confirm the initial referral metrics of patients to medical institutions, with the goal of quantifying the initial referral metrics of patients to medical institutions, build a keyword thesaurus for various initial referral metrics of patients to medical institutions, use the keywords of each initial referral metric as an index, collect data, and obtain the data corresponding to each initial referral metric of patients to medical institutions; The data corresponding to each initial referral metric of the patient to the medical institution are keyword extracted and converted into the same modality, and the weight of each initial referral metric of the patient to the medical institution is determined by weighted analysis; The weights of various initial referral metrics of the patient to the medical institution are sorted in descending order, and the first second preset number of initial referral metrics are taken as the referral metrics of the patient to the medical institution.

[0009] Preferably, the weighted analysis method is any one of AHP, entropy weight method and principal component analysis.

[0010] Preferably, the method for extracting keywords includes: any one of a TF-IDF keyword extraction algorithm and a TextRank algorithm.

[0011] Preferably, obtaining the importance score of each patient for each referral metric and each patient's referral metric for each referable medical institution in the current period, and constructing a preference function for each patient for each referable medical institution, includes: Based on each patient's importance score for each referral metric, obtain each patient's weight for each referral metric; According to the weight of each patient for each referral metric and the value of each patient's referral metric for each referable medical institution in the current period, the preference function of each patient for each referable medical institution is constructed. The formula is: , in, For the Patients in the current period The preference function value of the referral medical institutions, is the number of referral metrics, is the referral metric index, For the Patients for the The weight of the referral metric, For the Patients in the current period The first medical institution that can be referred Referral metric values.

[0012] Preferably, the maximum number of patients that each referable medical institution can receive during the current period is calculated using the formula: , in, for Time period The maximum number of patients that a referral medical institution can receive, To obtain the minimum value, is the number of patient admissions metrics, is the index of the admissions metric, For Time period The first medical institution that can be referred The value of the admissions metric, The first The lowest value of the admissions metric.

[0013] Preferably, patients who are not accepted by referable medical institutions in the current period and patients who withdraw their referral requests will enter the two-way referral process of the next period together with patients to be referred in the next period.

[0014] The present invention also provides a two-way referral system, comprising: The metric acquisition module is used to confirm the medical institution's admission metric and the patient's referral metric to the medical institution; A screening module is used to screen all referable medical institutions whose values ​​of various reception metrics are greater than the minimum values ​​of various reception metrics required to receive one patient in the current period, and calculate the maximum number of patients that each referable medical institution can receive in the current period; The preference function design module is used to obtain the importance score of each patient for each referral metric and the referral metric values ​​of each patient for each referable medical institution in the current period, and to construct a preference function for each patient for each referable medical institution; A module for determining a proposed referral medical institution is used to use the referable medical institution corresponding to the maximum preference function value of each patient for each referable medical institution as the proposed referral medical institution for the patient; The referral number determination module is used to count the proposed referral medical institutions for each patient and determine the proposed referral number of each referable medical institution in the current period; The referral module is used to: if the maximum number of patients that the current referable medical institution can accept in the current period is greater than or equal to the number of patients it intends to refer, the current referable medical institution accepts all patients to be referred to the referable medical institution; if the maximum number of patients that the current medical institution can accept in the current period is less than the number of patients it intends to refer, the current medical institution accepts the maximum number of patients to be referred to the medical institution, and provides a notification of rejection of referral to the patients who are unable to receive the referral.

[0015] The present invention also provides a two-way referral device, comprising: The memory is used to store computer programs; the processor is used to implement the steps of the above-mentioned two-way referral method when executing the computer program.

[0016] The above technical solution of the present invention has the following beneficial effects compared with the prior art: The two-way referral method, system and device described in the present invention obtain the initial admission measurement indicators of medical institutions and the initial referral measurement indicators of patients to medical institutions. The initial measurement indicators can comprehensively cover all key links between medical institutions and patients, avoiding the one-sidedness of data collection. With the goal of quantifying the initial measurement indicators, a keyword thesaurus for each initial admission measurement indicator of medical institutions and a keyword thesaurus for each initial referral measurement indicator of patients to medical institutions are respectively constructed, and the data are collected with the keyword of each initial measurement indicator as the index, thereby ensuring the breadth and accuracy of the data source and collecting detailed and rich information from multiple dimensions. Keywords are extracted and converted into the same modality. The weights of each initial measurement indicator of medical institutions and patients for medical institutions are determined through weighted analysis, and the reception measurement indicators of medical institutions and the referral measurement indicators of patients to medical institutions are obtained. Modal unification converts data from different sources and formats into the same type of expression, which enhances the comparability and consistency of data. Weighted analysis assigns corresponding weights according to the actual importance of each indicator, highlighting the influence of key factors. Through the above-mentioned multidisciplinary data fusion strategy based on weighted analysis, the deep integration of multi-faceted data of medical institutions and patients is achieved, providing a rich and accurate basis for referral decisions.

[0017] The present invention constructs a preference function for each patient for each referable medical institution based on the importance score of each patient for each referral metric indicator and the value of each patient for each referable medical institution in the current time period; the referable medical institution corresponding to the maximum preference function value of each patient for each referable medical institution is used as the patient's proposed referral medical institution. This method fully considers the subjectivity and time-varying nature of patient needs. The preference function of each patient for each referable medical institution in the current time period can fully reflect the degree of matching between the patient's personal needs and each medical institution, so as to determine the proposed referral medical institution, thereby improving the matching accuracy between the patient and the medical institution.

[0018] The present invention fully considers the complex actual situation of medical referral through a multidisciplinary data fusion strategy based on weighted analysis, a perfect patient preference function construction, and an accurate method for calculating the number of intended referrals and the number of received referrals. This effectively reduces matching errors, ensures the rational allocation of medical resources, avoids waste, and at the same time optimizes the patient's medical process and experience, achieving a dual improvement in the efficient use of medical resources and the quality of patient medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein: Figure 1 It is a flow chart of the steps of a two-way referral method of the present invention.

[0020] Figure 2 It is a structural diagram of a two-way referral method of the present invention.

[0021] Figure 3 It is a flow chart for obtaining the measurement indicators of medical institution admissions and the measurement indicators of patients' referrals to medical institutions. DETAILED DESCRIPTION

[0022] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0023] like Figure 1 , 2 As shown, Figure 1 is a flow chart of steps of a two-way referral method of the present invention, Figure 2 This is a structural diagram of a two-way referral method of the present invention.

[0024] Embodiment 1 of the present invention provides a bidirectional referral method, comprising the following steps: Step S1: Obtain the medical institution's admission measurement indicators and the patient's referral measurement indicators to the medical institution; like Figure 3 As shown, Figure 3 Flowchart for obtaining the metrics of medical institution admissions and patient referrals to medical institutions.

[0025] In this embodiment, preferably, obtaining the measurement indicators of the medical institution includes: Step S11: Acquire the initial admission measurement indicators of the medical institution, with the goal of quantifying the initial admission measurement indicators of the medical institution, construct a keyword thesaurus for each initial admission measurement indicator of the medical institution, collect data with the keyword of each initial admission measurement indicator as the index, and obtain the data corresponding to each initial admission measurement indicator of the medical institution; Step S12: extract keywords from the data corresponding to each initial admission metric indicator of the medical institution and convert them into the same mode, and determine the weight of each initial admission metric indicator of the medical institution by weighted analysis; Step S13: sort the weights of various initial patient admission metrics of the medical institution in descending order, and take the first preset number of initial patient admission metrics as the patient admission metrics of the medical institution.

[0026] In this embodiment, preferably, obtaining the patient's referral metric for a medical institution includes: Step S14: confirming the initial referral metric indicators of the patient to the medical institution, with the goal of quantifying the initial referral metric indicators of the patient to the medical institution, constructing a keyword thesaurus of various initial referral reception metric indicators of the patient to the medical institution, using the keyword of each initial referral metric indicator as an index, collecting data, and obtaining data corresponding to each initial referral metric indicator of the patient to the medical institution; Step S15: extract keywords from the data corresponding to each initial referral metric indicator of the patient to the medical institution and convert them into the same modality, and determine the weight of each initial referral metric indicator of the patient to the medical institution through a weighted analysis method; Step S16: sorting the weights of the various initial referral metrics of the patient to the medical institution in descending order, and taking the first second preset number of initial referral metrics as the referral metrics of the patient to the medical institution; In this embodiment, specifically, the weighted analysis method is any one of the AHP hierarchical analysis method, the entropy weight method, and the principal component analysis method.

[0027] In this embodiment, specifically, the reception measurement indicators of the medical institution include: medical resource usage information related to the medical staff themselves, bed status, drug and equipment reserves, and referral vehicle usage; among them, the medical resource usage information related to the medical staff themselves includes: medical resource usage information related to the doctor themselves and medical resource usage information related to the nurse themselves; the medical resource usage information related to the doctor himself includes: the doctor's work shift, professional level, appointment and consultation arrangement, and the medical resource usage information related to the nurse himself includes: the number of patients and shift arrangement of the nurse; The referral measurement indicators of patients to medical institutions include: direct costs, indirect costs, referral distance and comprehensive service evaluation indicators; among them, direct costs include: medical treatment expenses, medical expenses, examination expenses and nursing expenses, indirect costs include: absenteeism costs, quality of life loss costs, family care costs, and comprehensive service evaluation indicators include: medical accident rate, average length of stay, and disease recurrence rate.

[0028] This embodiment reads a large amount of literature, sorts out the referral standard requirements of medical institutions and the referral needs of patients, obtains the initial admission measurement indicators of medical institutions and the initial referral measurement indicators of patients to medical institutions, so as to quantify and characterize the referral standard and referral demand information. On this basis, with the goal of quantifying the initial measurement indicators, a keyword thesaurus for each initial measurement indicator is established, and multiple methods such as web page search, literature reading, and book query are used to collect multimodal indicator data such as text, image, audio, video, and sensor to improve the efficiency and breadth of data collection. Keywords are extracted from the data and converted into the same modality. The weight of each initial measurement indicator of the medical institution and the patient is determined through weighted analysis. The measurement indicators of the medical institution and the patient are determined according to the weight of each initial referral measurement indicator of the medical institution by the medical institution and the patient respectively. Modal unification converts data from different sources and formats into the same type of expression, which enhances the comparability and consistency of the data. Weighted analysis assigns corresponding weights according to the actual importance of each indicator, highlighting the influence of key factors. Through the above-mentioned multidisciplinary data fusion strategy based on weighted analysis, the deep integration of various data of medical institutions and patients is realized, providing a rich and accurate basis for referral decisions.

[0029] Step S2: screening each referable medical institution whose values ​​of each reception metric index are greater than the minimum values ​​of each reception metric index required to receive one patient in the current period, and calculating the maximum number of patients that each referable medical institution can receive in the current period; In this embodiment, specifically, calculating the maximum number of patients that each referable medical institution can receive during the current period includes: , in, for Time period The maximum number of patients that a referral medical institution can receive, To obtain the minimum value, is the number of patient admissions metrics, is the index of the admissions metric, For Time period The first medical institution that can be referred The value of the admissions metric, The first The lowest value of the admissions metric.

[0030] Many traditional screening methods may be too complicated and rely on a lot of subjective judgments or vague criteria, which not only makes the screening process time-consuming and laborious, but also the results are often not accurate and reliable. This method is based on clear and unambiguous comparison of metric values ​​and is highly objective and operational.

[0031] Step S3: Obtain the importance score of each patient for each referral metric and the value of each patient's referral metric for each referable medical institution in the current period, and construct a preference function for each patient for each referable medical institution; In this embodiment, specifically, when the referral measurement indicators are medical cost, referral distance and medical accident rate, the referral measurement indicator values ​​of each patient for each referable medical institution in the current time period are obtained, including: the medical cost required for each patient for each referable medical institution in the current time period, the actual distance of each patient to each referable medical institution in the current time period, and the medical accident rate of each patient for each referable medical institution in the current time period.

[0032] In this embodiment, preferably, the obtaining of the importance score of each patient for each referral metric and the value of each patient for each referral metric for each referable medical institution in the current period, and the construction of a preference function for each patient for each referable medical institution, includes: Based on each patient's importance score for each referral metric, obtain each patient's weight for each referral metric; According to the weight of each patient for each referral metric and the value of each patient's referral metric for each referable medical institution in the current period, the preference function of each patient for each referable medical institution is constructed. The formula is: , in, For the Patients in the current period The preference function value of the referral medical institutions, is the number of referral metrics, is the referral metric index, For the Patients for the The weight of the referral metric, For the Patients in the current period The first medical institution that can be referred Referral metric values.

[0033] This embodiment takes into account the subjectivity of each patient, so each patient has his or her own preference function. is a weight value in the range [0,1]. The smaller the distance from 1, the The referral metric is The more important the patient, the The set of preference functions of each patient for each referable medical institution is: ,in, is the total number of medical institutions that can be referred in the current period, It is a collection of medical institutions that can provide referrals during the current period.

[0034] This embodiment constructs a preference function for each patient for each referable medical institution based on the importance score of each patient for each referral metric indicator and the value of each patient for each referable medical institution in the current time period; the referable medical institution corresponding to the maximum preference function value of each patient for each referable medical institution is used as the patient's proposed referral medical institution. This method fully considers the subjectivity and time-varying nature of patient needs. The preference function of each patient for each referable medical institution in the current time period can fully reflect the degree of match between the patient's personal needs and each medical institution, thereby determining the proposed referral medical institution, thereby improving the matching accuracy between the patient and the medical institution.

[0035] Step S4: taking the referable medical institution corresponding to the maximum preference function value of each patient for each referable medical institution as the proposed referral medical institution for the patient; Step S5: Count the medical institutions to which each patient is to be referred, and determine the number of intended referrals to each medical institution that can be referred during the current period; Step S6: If the maximum number of patients that the current referable medical institution can accept in the current time period is greater than or equal to its intended referral number, the current referable medical institution accepts all patients intended to be referred to the referable medical institution; if the maximum number of patients that the current medical institution can accept in the current time period is less than its intended referral number, the current medical institution accepts the maximum number of patients intended to be referred to the medical institution, and provides a notification of refusal of referral to the patients who are unable to receive the referral.

[0036] In this embodiment, preferably, if the maximum number of patients that the current referable medical institution can accept in the current period is less than the number of patients to be referred, the patients with the maximum number of patients accepted by the current medical institution are randomly screened and accepted, or the preference function values ​​of each patient for the current referable medical institutions are sorted in descending order, and the patients with the maximum number of patients accepted by the current medical institution are accepted; After completing the initial two-way referral, the maximum number of patients that each referable medical institution can accept is recalculated. For each patient who cannot be accepted, the preference function value between the patient and each referable medical institution whose maximum number of patients can be accepted is greater than 0 is calculated as the patient's proposed referral medical institution, until the number of patients accepted by each referable medical institution reaches the maximum number that it can currently accept or every patient in the current period is accepted for referral.

[0037] In this embodiment, specifically, patients who are not accepted by referable medical institutions in the current period and patients who withdraw their referral requests will enter the two-way referral process of the next period together with patients to be referred in the next period.

[0038] The two-way referral method proposed in the present invention significantly optimizes the referral process, improves matching efficiency and accuracy, and is more optimized and closer to actual medical needs than the traditional referral model. The present invention provides patients with more personalized referral options by carefully dividing and comprehensively considering multiple referral metrics and reception metrics, such as medical costs, referral distance, and comprehensive services.

[0039] Through the computer simulation experimental environment, the bidirectional referral method proposed in the present invention can be deployed on the intelligent bidirectional referral technology platform. In practical applications, taking the medical system in a certain region as an example: For medical institutions, the reception metrics of each medical institution are updated regularly, such as the medical staff scheduling, bed usage, drug and equipment inventory, etc. For example, a tertiary hospital updates bed usage data at 10 a.m. every day, including the number of inpatients, the number of empty beds, the expected discharge time, etc., monitors the inventory level of drugs and equipment in real time through sensors, and automatically issues replenishment reminders when the inventory is below the warning line. At the same time, these data are uploaded to the platform.

[0040] For patients, when referral is needed, they input the referral metric values ​​of the medical institutions through the platform, such as the expected referral distance range, the ability to bear medical costs (such as whether there is medical insurance and the upper limit of out-of-pocket expenses that can be borne), and the requirements for comprehensive services (such as whether special nursing services are needed), etc., as well as each patient's importance score for each referral metric.

[0041] The intelligent two-way referral technology platform recommends appropriate referral medical institutions for patients based on the collected data, according to the above-mentioned weighted analysis, threshold screening and preference function calculation. If it is calculated that the current patient has the highest comprehensive match with a certain specialist hospital in terms of medical resources, distance, cost, etc., the platform will recommend the hospital to the patient and assist the patient in completing the referral process. If the specialist hospital finds that resources are tight when receiving the referred patients and cannot meet all referral needs, the platform will notify the patients who have not been received, and the patients who have not been received will enter the two-way referral process of the next time period together with the patients to be referred in the next time period. The theoretical logic is successfully and efficiently converted into computer logic, and by finely setting the relevant parameters, the feasibility and superiority of the matching algorithm proposed in the present invention in the practice of two-way referral are effectively verified, and the scientificity and accuracy of the referral decision are greatly improved.

[0042] The second embodiment provides a two-way referral system, including: The metric acquisition module is used to confirm the medical institution's admission metric and the patient's referral metric to the medical institution; A screening module is used to screen all referable medical institutions whose values ​​of various reception metrics are greater than the minimum values ​​of various reception metrics required to receive one patient in the current period, and calculate the maximum number of patients that each referable medical institution can receive in the current period; The preference function design module is used to obtain the importance score of each patient for each referral metric and the referral metric values ​​of each patient for each referable medical institution in the current period, and to construct a preference function for each patient for each referable medical institution; A module for determining a proposed referral medical institution is used to use the referable medical institution corresponding to the maximum preference function value of each patient for each referable medical institution as the proposed referral medical institution for the patient; The referral number determination module is used to count the proposed referral medical institutions for each patient and determine the proposed referral number of each referable medical institution in the current period; The referral module is used to: if the maximum number of patients that the current referable medical institution can accept in the current period is greater than or equal to the number of patients it intends to refer, the current referable medical institution accepts all patients to be referred to the referable medical institution; if the maximum number of patients that the current medical institution can accept in the current period is less than the number of patients it intends to refer, the current medical institution accepts the maximum number of patients to be referred to the medical institution, and provides a notification of rejection of referral to the patients who are unable to receive the referral.

[0043] The third embodiment provides a bidirectional referral device, including: The memory is used to store computer programs; the processor is used to implement the steps of the above-mentioned two-way referral method when executing the computer program.

[0044] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0045] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0046] 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.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0048] Obviously, the above embodiments are merely examples for the purpose of clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. A two-way referral method, characterized in that: The following steps are involved: Obtain the medical institution's admission metrics and patient referral metrics to medical institutions; Screen all referable medical institutions whose values ​​of various reception metrics are greater than the minimum values ​​of various reception metrics required to receive one patient in the current period, and calculate the maximum number of patients that each referable medical institution can receive in the current period; Obtain each patient's importance score for each referral metric and each patient's referral metric value for each referable medical institution in the current period, and construct each patient's preference function for each referable medical institution; The referable medical institution corresponding to each patient's maximum preference function value for each referable medical institution is used as the proposed referral medical institution for the patient; Count the medical institutions to which each patient is to be referred, and determine the number of proposed referrals to each medical institution that can be referred during the current period; If the maximum number of patients that the current medical institution can accept for referral during the current period is greater than or equal to its intended number of referrals, the current medical institution will accept all patients intended to be referred to the medical institution; if the maximum number of patients that the current medical institution can accept for referral during the current period is less than its intended number of referrals, the current medical institution will accept the maximum number of patients intended to be referred to the medical institution and provide a notification of refusal of referral to the patients who are not accepted.

2. A two-way referral method according to claim 1, characterized in that: Obtain the medical institution's admissions metrics, including: Obtain the initial admission measurement indicators of the medical institution, with the goal of quantifying the initial admission measurement indicators of the medical institution, construct a keyword thesaurus for each initial admission measurement indicator of the medical institution, collect data using the keyword of each initial admission measurement indicator as an index, and obtain the data corresponding to each initial admission measurement indicator of the medical institution; The data corresponding to each initial admission metric of the medical institution are keyword extracted and converted into the same mode, and the weight of each initial admission metric of the medical institution is determined by weighted analysis method; The weights of various initial consultation measurement indicators of the medical institution are sorted in descending order, and the first preset number of initial consultation measurement indicators are taken as the consultation measurement indicators of the medical institution.

3. A two-way referral method according to claim 1, characterized in that: Obtain patient referral metrics for healthcare providers, including: Confirm the initial referral metrics of patients to medical institutions, with the goal of quantifying the initial referral metrics of patients to medical institutions, build a keyword thesaurus for various initial referral metrics of patients to medical institutions, use the keywords of each initial referral metric as an index, collect data, and obtain the data corresponding to each initial referral metric of patients to medical institutions; The data corresponding to each initial referral metric of the patient to the medical institution are keyword extracted and converted into the same modality, and the weight of each initial referral metric of the patient to the medical institution is determined by weighted analysis; The weights of various initial referral metrics of the patient to the medical institution are sorted in descending order, and the first second preset number of initial referral metrics are taken as the referral metrics of the patient to the medical institution.

4. A two-way referral method according to claim 2 or 3, characterized in that: The weighted analysis method is any one of the AHP hierarchical analysis method, the entropy weight method, and the principal component analysis method.

5. A two-way referral method according to claim 2 or 3, characterized in that: The keyword extraction method includes: any one of the TF-IDF keyword extraction algorithm and the TextRank algorithm.

6. A two-way referral method according to claim 1, characterized in that: The obtaining of each patient's importance score for each referral metric and each patient's value of each referral metric for each referable medical institution in the current period, and the construction of each patient's preference function for each referable medical institution, include: Based on each patient's importance score for each referral metric, obtain each patient's weight for each referral metric; According to the weight of each patient for each referral metric and the value of each patient's referral metric for each referable medical institution in the current period, the preference function of each patient for each referable medical institution is constructed. The formula is: ， in, For the Patients in the current period The preference function value of the referral medical institutions, is the number of referral metrics, is the referral metric index, For the Patients for the The weight of the referral metric, For the Patients in the current period The first medical institution that can be referred Referral metric values.

7. A two-way referral method according to claim 1, characterized in that: Calculate the maximum number of patients that each referral medical institution can accept during the current period. The formula is: ， in, for Time period The maximum number of patients that a referral medical institution can receive, To obtain the minimum value, is the number of patient admissions metrics, is the index of the admissions metric, For Time period The first medical institution that can be referred The value of the admissions metric, The first The lowest value of the admissions metric.

8. A two-way referral method according to claim 1, characterized in that: Patients who are not accepted by the referable medical institutions in the current period and patients who withdraw their referral requests will enter the two-way referral process in the next period together with the patients waiting to be referred in the next period.

9. A two-way referral system, characterized in that: include: The metric acquisition module is used to confirm the medical institution's admission metric and the patient's referral metric to the medical institution; A screening module is used to screen all referable medical institutions whose values ​​of various reception metrics are greater than the minimum values ​​of various reception metrics required to receive one patient in the current period, and calculate the maximum number of patients that each referable medical institution can receive in the current period; The preference function design module is used to obtain the importance score of each patient for each referral metric and the referral metric values ​​of each patient for each referable medical institution in the current period, and to construct a preference function for each patient for each referable medical institution; A module for determining a proposed referral medical institution is used to use the referable medical institution corresponding to the maximum preference function value of each patient for each referable medical institution as the proposed referral medical institution for the patient; The referral number determination module is used to count the proposed referral medical institutions for each patient and determine the proposed referral number of each referable medical institution in the current period; The referral module is used to: if the maximum number of patients that the current referable medical institution can accept in the current period is greater than or equal to the number of patients it intends to refer, the current referable medical institution accepts all patients to be referred to the referable medical institution; if the maximum number of patients that the current medical institution can accept in the current period is less than the number of patients it intends to refer, the current medical institution accepts the maximum number of patients to be referred to the medical institution, and provides a notification of rejection of referral to the patients who are unable to receive the referral.

10. A two-way referral device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of a bidirectional referral method as described in any one of claims 1 to 8 when executing the computer program.

Images