WO2021038969A1 - Procédé de mise à jour d'un modèle d'apprentissage pour une aide à la sélection de service clinique, système d'aide à la sélection de service clinique et programme d'aide à la sélection de service clinique - Google Patents

Procédé de mise à jour d'un modèle d'apprentissage pour une aide à la sélection de service clinique, système d'aide à la sélection de service clinique et programme d'aide à la sélection de service clinique Download PDF

Info

Publication number
WO2021038969A1
WO2021038969A1 PCT/JP2020/018678 JP2020018678W WO2021038969A1 WO 2021038969 A1 WO2021038969 A1 WO 2021038969A1 JP 2020018678 W JP2020018678 W JP 2020018678W WO 2021038969 A1 WO2021038969 A1 WO 2021038969A1
Authority
WO
WIPO (PCT)
Prior art keywords
clinical department
learning model
information
answer
clinical
Prior art date
Application number
PCT/JP2020/018678
Other languages
English (en)
Japanese (ja)
Inventor
知宏 中矢
大介 能登原
充宏 服部
寛章 本郷
智則 ▲崎▼本
和義 西野
太朗 高畑
Original Assignee
株式会社島津製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社島津製作所 filed Critical 株式会社島津製作所
Priority to JP2021542000A priority Critical patent/JP7276467B2/ja
Publication of WO2021038969A1 publication Critical patent/WO2021038969A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Definitions

  • the present invention relates to a learning model update method for clinical department selection support, a clinical department selection support system, and a clinical department selection support program.
  • the above-mentioned Japanese Patent Application Laid-Open No. 2019-101491 discloses a diagnostic support method for receiving input information regarding an answer to a medical inquiry by a user terminal.
  • this diagnosis support method display information of a plurality of inquiry items is displayed on the user terminal. Then, the answer to the interview is input to the user terminal. After that, the answer information, which is the answer information for the interview, is transmitted from the user terminal to the medical care support device. Then, the answer information is registered as medical record information in the medical care support device.
  • the diagnosis table is referred to, and the name of the disease suspected to correspond to the answer information and the clinical department to be consulted are estimated. Then, the information on the suspicious disease name and the information on the clinical department to be examined are acquired by the user terminal, and the suspicious disease name and the clinical department to be examined are output as display information on the user terminal.
  • doctor needs to reselect the correct clinical department for each response information of a certain content and guide the patient to the correct clinical department. Therefore, the diagnostic support method described in Japanese Patent Application Laid-Open No. 2019-101491 cannot improve the accuracy of estimation of the clinical department based on the response information, so that the work of guiding the doctor to the correct clinical department is not reduced. It is considered that there are cases.
  • doctor means a medical worker including a doctor and a dentist.
  • the present invention has been made to solve the above-mentioned problems, and one object of the present invention is to select a clinical department capable of reducing the work load of a doctor guiding a correct clinical department. It is to provide a learning model update method for support, a clinical department selection support system, and a clinical department selection support program.
  • the method of updating the learning model for supporting the selection of clinical departments in the first aspect of the present invention obtains a medical inquiry answer, which is an answer to the medical inquiry for determining the clinical department to be examined by the patient.
  • the step of acquiring the clinical department selection result information indicating the clinical department in which the patient is examined, the acquired interview answer, and the clinical department It includes a step of updating the learning model by associating with the selection result information and performing machine learning again.
  • the clinical department selection support system includes a medical inquiry answer acquisition unit that acquires a medical inquiry answer, which is an answer to a medical inquiry for determining a clinical department to be examined by a patient, an inquiry answer, and a patient to receive a medical examination.
  • the clinical department information estimation unit that estimates the clinical department information corresponding to the acquired interview answers based on the learning model for clinical department selection support that is machine-learned in association with the clinical department information indicating the clinical department to be selected.
  • the machine again associates the clinical department selection result information acquisition unit that acquires the clinical department selection result information indicating the clinical department in which the patient is examined, the acquired inquiry answer, and the clinical department selection result information. It is provided with a learning model update unit that updates the learning model by learning.
  • the clinical department selection support program controls the acquisition of the clinical department answer, which is the answer to the clinical department for determining the clinical department to be examined by the patient, the clinical department answer, and the medical treatment that the patient should receive.
  • the clinical department answer which is the answer to the clinical department for determining the clinical department to be examined by the patient, the clinical department answer, and the medical treatment that the patient should receive.
  • control to estimate clinical department information corresponding to the acquired clinical department information and medical examination for the patient Control to acquire clinical department selection result information indicating the clinical department in which the department is performed, control to update the learning model by re-machine learning by associating the acquired clinical department selection result information with the clinical department selection result information.
  • the clinical department where the patient is examined means both the department where the patient is scheduled to be examined and the department where the patient is actually examined. To do.
  • the obtained interview answers and the clinical department selection results are obtained.
  • the learning model is updated by associating with the information and performing machine learning again.
  • the learning model can be updated based on the appropriate department selected by the doctor even if the department estimated based on the interview response is incorrect. Therefore, by updating the learning model, the accuracy of the estimation of the clinical department can be improved, and the chance of making an incorrect estimation of the clinical department can be reduced. As a result, the chances of the doctor correcting the wrong clinical department are reduced, and the work load of the doctor guiding the correct clinical department can be reduced.
  • the patient P receives a medical examination based on the answer of the inquiry Q to the patient P at a medical institution (for example, a hospital) having a plurality of clinical departments. It is a system for supporting medical examinations and work by medical staff such as doctors and nurses and work by receptionists (clerks) by estimating the department to be treated.
  • the clinical department selection support system 100 includes an electronic medical record device 10, an inquiry terminal 20, a hospital terminal 30, an examination terminal 40, an inquiry server 50, and a learning model generation device 60.
  • the electronic medical record device 10, the plurality of hospital terminals 30, and the plurality of medical examination terminals 40 constitute an electronic medical record system.
  • the electronic medical record system is a system for electronically storing and managing the medical examination information R by a medical worker such as a doctor and the inquiry answer Dq described later as an electronic medical record information Dk collectively as a database. That is, the electronic medical record system is a system for improving the efficiency of office work of medical staff and receptionists of medical institutions and centralizing information management.
  • the inquiry terminal 20 is an example of a "portable information terminal" in the claims.
  • the hospital terminal 30 is an example of a "medical institution terminal" in the claims.
  • the plurality of inquiry terminals 20, the plurality of hospital terminals 30, and the inquiry server 50 are connected via the network N.
  • the network N is, for example, the Internet.
  • the electronic medical record device 10 is a device that manages the electronic medical record information Dk generated for each patient.
  • the electronic medical record device 10 includes a control unit 11, an electronic medical record server 12, an operation unit 13, a display unit 14, and a communication unit 15.
  • the control unit 11 is configured to control the operation of the electronic medical record device 10 by executing the electronic medical record program 12a (hereinafter referred to as "program 12a").
  • the control unit 11 includes an arithmetic processing circuit such as a CPU (Central Processing Unit) and a storage circuit such as a RAM (Random Access Memory).
  • the control unit 11 is configured to control to update or generate the electronic medical record information Dk when the electronic medical record input information Dki described later is generated and when the medical examination information R is input.
  • the electronic medical record server 12 includes, for example, a non-volatile storage medium such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive).
  • the electronic medical record server 12 stores the program 12a. Then, the electronic medical record server 12 stores the electronic medical record information Dk corresponding to each of the plurality of patients P. That is, an electronic medical record database is constructed on the electronic medical record server 12. Further, the electronic medical record information Dk is updated in response to the input (stored) of the electronic medical record input information Dki to the electronic medical record server 12.
  • the operation unit 13 is configured to receive input operations of a medical worker or an employee (receptionist) of a medical institution.
  • the operation unit 13 is composed of at least one of a keyboard, a mouse, and a touch panel.
  • the operation unit 13 is configured to receive medical examination information R by a doctor.
  • the display unit 14 is configured to display (output) the electronic medical record information Dk based on an input operation to the operation unit 13 and a command from the control unit 11.
  • the display unit 14 includes a liquid crystal display.
  • the electronic medical record information Dk includes, for example, basic patient information such as patient ID, patient name, medical history and allergies, treatment history and prescription history information, medical inquiry answer Dq, and medical examination information R.
  • the control unit 11 causes the display unit 14 to display an image E1 showing basic patient information, an image E2 showing information on treatment history and prescription history, and an image E3 showing medical inquiry answer Dq and medical examination information R. It is configured to provide control.
  • the inquiry answer Dq is information indicating an answer to the inquiry Q described later.
  • the medical examination information R is information including the medical examination result and the clinical department of the patient P.
  • the medical examination information R includes, for example, findings by a doctor, results of clinical examinations, and clinical department selection result information Sa, which is information indicating the clinical department in which the medical examination was performed.
  • the communication unit 15 is configured to perform wired communication or wireless communication with the hospital terminal 30 and the medical examination terminal 40.
  • the communication unit 15 is configured to be able to communicate with the hospital terminal 30 and the medical examination terminal 40 by a wired LAN (Local Area Network) or a wireless LAN.
  • the communication unit 15 is configured to send and receive the electronic medical record input information Dki and the medical examination information R to and from the hospital terminal 30 and the medical examination terminal 40.
  • the electronic medical record input information Dki (and medical examination information R) includes, for example, data in a character (text) format.
  • the electronic medical record input information Dki and the medical examination information R are data in a format conforming to HL7 (Health Level 7).
  • the medical inquiry terminal 20 is configured as a mobile information terminal provided separately from the electronic medical record device 10.
  • the interview terminal 20 is a mobile information terminal owned by the patient P.
  • the inquiry terminal 20 is composed of a computer such as a smartphone (mobile phone device), a tablet-type information terminal, or a laptop computer.
  • the inquiry terminal 20 includes a control unit 21, a touch panel 22, a communication unit 23, and a storage unit 24.
  • the control unit 21 is configured to control the operation of the interview terminal 20 by executing a control program.
  • the control unit 21 is configured to execute an application program 24a for answering a question (hereinafter referred to as “program 24a”).
  • program 24a an application program 24a for answering a question
  • the control unit 21 includes an arithmetic processing circuit such as a CPU and a storage circuit such as a RAM.
  • the touch panel 22 is configured to accept an input operation by the patient P and display an image in response to a command from the control unit 21.
  • the touch panel 22 is configured to transmit the received input operation information to the control unit 21.
  • the communication unit 23 is configured as an interface for wireless communication via the network N.
  • the communication unit 23 is configured to connect to the network N by Wi-Fi or Bluetooth®, or to the network N by wireless mobile communication technology (eg, IMT-Advanced: 4G). ing.
  • the storage unit 24 includes a non-volatile storage medium such as an HDD or SSD.
  • the storage unit 24 stores the program 24a.
  • the inquiry terminal 20 (touch panel 22) is configured to receive the inquiry answer Dq, which is the answer to the inquiry Q.
  • Interview Q is composed of interview contents common to a plurality of clinical departments. That is, the interview Q is a comprehensive (basic) interview.
  • the interview Q is an interview for determining the clinical department to be examined by the patient P.
  • the question Q a question for asking the site where the symptom appears, a question for asking the type of symptom, and a question for asking when the symptom appeared are shown.
  • the control unit 21 displays an image E11 on the touch panel 22 for receiving an answer to the inquiry Q.
  • the image E11 includes an interview Q with at least one of a figure and a letter.
  • the image E11 includes an image of the characters "Which part has the symptom?"
  • the operation unit image E11a is an image imitating a human body, an image for answering "whole body", and an image for answering "mood".
  • the control unit 21 is configured to acquire the touch coordinates in the touch panel 22 based on the touch input operation of the patient P.
  • the control unit 21 is configured to acquire the answer result (in the case of the above example, the information of the symptom site) based on the touch coordinates.
  • the control unit 21 controls to transmit the received inquiry answer Dq to the inquiry server 50.
  • the inquiry terminal 20 is configured to acquire the clinical department guidance information Sb, which is information for guiding the clinical department to be examined by the patient P.
  • the medical inquiry terminal 20 acquires the clinical department guidance information Sb from the medical inquiry server 50 via the network N after the medical department to be examined is determined by the hospital terminal 30.
  • the control unit 21 of the inquiry terminal 20 causes the touch panel 22 to display a display informing the patient P of the clinical department to be examined in response to the acquisition of the clinical department guidance information Sb.
  • the hospital terminal 30 is provided separately from the interview terminal 20.
  • the hospital terminal 30 is, for example, a computer provided at a general reception in a medical institution (hospital). Further, the hospital terminal 30 is configured as a consultation clinical department estimation device that estimates the clinical department that the patient P should receive from a plurality of clinical departments based on the inquiry response Dq. Further, the hospital terminal 30 includes a control unit 31, a display unit 32, an operation unit 33, a storage unit 34, and a communication unit 35.
  • the control unit 31 is configured to control the operation of the hospital terminal 30 by executing a control program.
  • the control unit 31 is configured to execute an application program 34a for a hospital terminal (hereinafter, referred to as “program 34a”).
  • program 34a an application program for a hospital terminal
  • the control unit 31 includes an arithmetic processing circuit such as a CPU and a storage circuit such as a RAM.
  • the control unit 31 includes a medical inquiry answer acquisition unit 31a, a clinical department information estimation unit 31b, a clinical department selection result information acquisition unit 31c, and an information generation unit 31d.
  • the medical inquiry answer acquisition unit 31a, the clinical department information estimation unit 31b, the clinical department selection result information acquisition unit 31c, and the information generation unit 31d are functional by executing the program 34a by the control unit 31. It is shown as a configuration. Further, in FIG.
  • the interview answer acquisition unit 31a, the clinical department information estimation unit 31b, the clinical department selection result information acquisition unit 31c, and the information generation unit 31d are described as functional blocks, but the interview answer acquisition unit 31a and the clinical department
  • the department information estimation unit 31b, the clinical department selection result information acquisition unit 31c, and the information generation unit 31d may be configured as integrated hardware, or may be configured by individual dedicated hardware (dedicated CPU). Good.
  • the inquiry response acquisition unit 31a is configured to acquire the inquiry answer Dq received by the inquiry terminal 20 from the inquiry server 50 via the communication unit 35.
  • the clinical department information estimation unit 31b is configured to estimate the clinical department information S based on the acquired inquiry response Dq.
  • the clinical department information estimation unit 31b is provided with a learning model M for supporting the selection of clinical departments, which is machine-learned by associating the questionnaire answer Dq with the clinical department information S indicating the clinical department to be examined by the patient P. There is. Then, when the clinical department information estimation unit 31b inputs the clinical department information Dq, the clinical department information S corresponding to the acquired clinical department information Dq is estimated based on the learning model M. Then, the clinical department information estimation unit 31b is configured to output the clinical department candidate information Sc, which is the estimated clinical department information S. As shown in FIG.
  • the clinical department information estimation unit 31b is configured to display the image E21 showing the clinical department candidate information Sc on the display unit 32. Further, the clinical department information estimation unit 31b is configured to display an operation unit display E21a for receiving a decision of the clinical department to be examined by the receptionist on the display unit 32. The details of the learning model M will be described later.
  • the clinical department selection result information acquisition unit 31c acquires the clinical department selection result information Sa indicating the clinical department in which the patient P is examined. That is, the clinical department selection result information acquisition unit 31c acquires the information of the clinical department in which the patient P is actually examined as the clinical department selection result information Sa. Specifically, the clinical department selection result information Sa is acquired based on the input of the medical examination information R to the electronic medical record system included in the medical examination terminal 40 described later. That is, the clinical department selection result information acquisition unit 31c examines the patient P by a doctor, and based on the medical examination information R input to the electronic medical record system, the clinical department is used as information on the clinical department in which the medical examination is actually performed. Acquire selection result information Sa. For example, as shown in FIG. 11, when the patient P is examined, the clinical department selection result information acquisition unit 31c includes the medical examination information R (clinical department selection result information Sa) and the inquiry answer Dq in the display unit 32. The electronic medical record information Dk is displayed.
  • the information generation unit 31d generates an information data set J for updating the learning model. Specifically, an information data set J in which the patient P's inquiry response Dq and the clinical department selection result information Sa for the patient P are associated with each other is generated.
  • the display unit 32 is configured as, for example, a liquid crystal display.
  • the operation unit 33 is configured to receive an input operation by a receptionist of a medical institution.
  • the operation unit 33 includes at least one of a keyboard, a mouse, and a touch panel.
  • the storage unit 34 is composed of a non-volatile memory such as an HDD or an SDD. Further, the storage unit 34 stores the program 34a, the learning model M, and the information data set J.
  • the communication unit 35 is configured as an interface for wireless communication via the network N.
  • the communication unit 35 is configured to connect to the network N by Wi-Fi or Brutooth (registered trademark). Further, the communication unit 35 is configured to communicate with the inquiry terminal 20 and the inquiry server 50 via the network N. Further, the communication unit 35 is configured to communicate with the electronic medical record device 10, the medical examination terminal 40, and the learning model generation device 60 via a wired LAN or a wireless LAN.
  • the medical examination terminal 40 is a terminal used by a doctor separately from the hospital terminal 30 for medical examination.
  • the examination terminal 40 is, for example, a computer provided in the examination room.
  • the medical examination terminal 40 also includes an electronic medical record system. Further, the medical examination terminal 40 includes a control unit 41, a display unit 42, an operation unit 43, a storage unit 44, and a communication unit 45.
  • the control unit 41 is configured to control the operation of the medical examination terminal 40 by executing a control program.
  • the control unit 41 is configured to execute an application program 44a for a medical examination terminal (hereinafter, referred to as “program 44a”).
  • the control unit 41 includes an arithmetic processing circuit such as a CPU and a storage circuit such as a RAM.
  • the control unit 41 is configured to store the electronic medical record input information Dki and the medical examination information R in the electronic medical record server 12 of the electronic medical record device 10.
  • the display unit 42 is configured as, for example, a liquid crystal display. Then, similarly to the hospital terminal 30, as shown in FIG. 11, the display unit 32 is configured to display the electronic medical record information Dk based on the command of the control unit 31.
  • the operation unit 43 is configured to receive input operations of a medical worker or an employee (receptionist) of a medical institution.
  • the operation unit 43 is composed of at least one of a keyboard, a mouse, and a touch panel.
  • the operation unit 43 is configured to receive the medical examination information R including the clinical department selection result information Sa as the result of the medical examination of the patient P by the doctor.
  • the storage unit 44 is composed of a non-volatile memory such as an HDD or an SDD. Further, the program 44a is stored in the storage unit 44.
  • the communication unit 45 is configured to communicate with the electronic medical record device 10 and the hospital terminal 30 via a wired LAN or a wireless LAN.
  • the inquiry server 50 is configured separately from the hospital terminal 30 and is configured as a server (information storage device) in which the inquiry answer Dq is stored (stored).
  • the interview server 50 is built on the cloud (cloud computing).
  • the inquiry server 50 is configured to communicate with the plurality of inquiry terminals 20 and the plurality of hospital terminals 30 via the network N. Further, the inquiry server 50 acquires the inquiry answer Dq from the inquiry terminal 20. Then, the inquiry server 50 is configured to transmit the acquired inquiry answer Dq to the hospital terminal 30 and to transmit the acquired clinical department guidance information Sb information to the inquiry terminal 20.
  • the learning model generation device 60 includes a control unit 61, a storage unit 62, and a communication unit 63.
  • the control unit 61 is configured to control the operation of the learning model generation device 60 by executing the control program 62a (hereinafter, referred to as “program 62a”). Further, the control unit 61 includes an arithmetic circuit such as a CPU and a storage circuit such as a RAM.
  • the storage unit 62 is composed of a non-volatile memory such as an HDD or an SDD. Further, the program 62a is stored in the storage unit 62.
  • the communication unit 63 is configured to be able to communicate with the hospital terminal 30.
  • the control unit 61 includes a learning model generation unit 61a and a learning model update unit 61b.
  • the learning model generation unit 61a and the learning model update unit 61b are shown as functional configurations that function by executing the program 62a by the control unit 61. Further, in FIG. 14, the learning model generation unit 61a and the learning model update unit 61b are described as functional blocks, but the learning model generation unit 61a and the learning model update unit 61b are configured as integrated hardware. Alternatively, it may be configured by individual dedicated hardware (dedicated CPU).
  • the learning model generation unit 61a performs machine learning by machine learning using the information data set J0 which uses the interview answer Dq as the input teacher data and the medical department information S as the output teacher data.
  • a learning model M for selection support is generated.
  • the learning model M is a neural network, and learns the weighting of the intermediate layer by performing machine learning.
  • the learning model generation unit 61a sets the learning model M so as to correspond to the selection of the clinical department of the medical institution (hospital) to be examined by the patient P among the plurality of medical institutions (hospitals) based on the interview answer Dq. Generate. That is, the learning model M is generated so as to correspond to the distribution of clinical departments for each hospital.
  • the learning model update unit 61b actually refers to the clinical department candidate information Sc estimated by the clinical department information estimation unit 31b and the patient P included in the electronic medical record information Dk. Even if the clinical department selection result information Sa indicating the clinical department where the medical examination was performed is different, the learning model M is updated in order to estimate the correct clinical department for the acquired clinical department answer Dq. Specifically, as shown in FIG. 16, the control unit 61 re-machine-learns the acquired learning model M by associating the acquired inquiry answer Dq with the clinical department selection result information Sa. It is configured to update. The control unit 61 acquires the information data set J from the hospital terminal 30 via the communication unit 63. Then, the learning model M is updated by performing machine learning using the interview answer Dq as the input teacher data and the clinical department selection result information Sa as the output teacher data.
  • the control unit 61 updates the learning model M at predetermined intervals. Further, the control unit 61 acquires the plurality of clinical department selection result information Sa by the hospital terminal 30, and then updates the learning model M by the acquired plurality of clinical department selection result information Sa. For example, the control unit 61 is configured to update the learning model M every 24 hours. In the hospital terminal 30, the inquiry answer Dq and the clinical department selection result information Sa for the plurality of patients P who have been examined within 24 hours are stored as the information data set J. Then, the control unit 61 acquires the stored information data set J via the communication unit 63, so that the plurality of inquiry answer Dqs are input teacher data and the plurality of medical department selection result information Sa is output. The learning model M is updated by performing machine learning as teacher data.
  • the information data set J for all the patients P may be acquired and the learning model M may be updated, or the information data set J for the randomly selected patient P may be acquired and the learning model M may be updated. May be done. Further, by acquiring the information data set J only when the clinical department candidate information Sc, which is the clinical department information S estimated by the clinical department information estimation unit 31b, is determined to be incorrect by a medical worker or the like.
  • the learning model M may be updated.
  • the control unit 61 updates the learning model M provided in the hospital terminal 30 by transmitting the updated learning model M to the hospital terminal 30 via the communication unit 63.
  • Step 101 is executed by the control unit 21 of the interview terminal 20.
  • Steps 102 to 104 are executed by the control unit 31 of the hospital terminal 30.
  • Step 105 is executed by the control unit 61 of the learning model generation device 60.
  • step 101 the interview answer Dq is received by the inquiry terminal 20.
  • step 102 the hospital terminal 30 acquires the inquiry answer Dq received by the inquiry terminal 20.
  • step 103 the hospital terminal 30 estimates the clinical department information S corresponding to the acquired inquiry answer Dq based on the learning model M.
  • step 104 the hospital terminal 30 acquires information on the clinical department in which the patient P was actually examined as the clinical department selection result information Sa.
  • step 105 the learning model M is updated by performing machine learning again by associating the acquired inquiry answer Dq with the clinical department selection result information Sa by the learning model generator 60.
  • the learning model is performed by associating the acquired inquiry answer Dq with the clinical department selection result information Sa and performing machine learning again. Update M.
  • the learning model M can be updated based on the appropriate clinical department selected by the doctor. Therefore, by updating the learning model M, the accuracy of the estimation of the clinical department can be improved, and the chance of making an incorrect estimation of the clinical department can be reduced. As a result, the chances of the doctor correcting the wrong clinical department are reduced, and the work load of the doctor guiding the correct clinical department can be reduced.
  • the clinical department selection support system 100 and the clinical department selection support programs 24a, 34a, 44a, and 62a of the present embodiment can obtain the following effects.
  • the acquired questionnaire answer Dq and the clinical department selection result information Sa correspond to each other.
  • the learning model M is updated by attaching and performing machine learning again. Thereby, even if the clinical department estimated based on the interview answer Dq is incorrect, the learning model M can be updated based on the appropriate clinical department selected by the doctor. Therefore, by updating the learning model M, the accuracy of the estimation of the clinical department can be improved, and the chance of making an incorrect estimation of the clinical department can be reduced. As a result, the chances of the doctor correcting the wrong clinical department are reduced, so that the clinical department selection support system 100 or the computer (learning model generator 60) is reduced so that the doctor can reduce the work load of guiding the correct clinical department. ) Can perform the process.
  • the step 104 of acquiring the clinical department selection result information Sa is the step 104 of acquiring the information of the clinical department in which the patient P is actually examined as the clinical department selection result information Sa. ..
  • the receptionist (clerk) of the medical institution should acquire the clinical department (the clinical department to be examined) instructed to receive the medical examination for the patient P as the clinical department selection result information Sa.
  • the guided clinical department may be changed at the discretion of the doctor. As described above, if the information of the clinical department where the medical examination was actually performed is configured to be acquired as the clinical department selection result information Sa, even if the guided clinical department is changed, the doctor will finally obtain it.
  • the clinical department where the medical examination was actually performed can be acquired as the clinical department selection result information Sa.
  • the learning model M can be updated by associating the acquired inquiry answer Dq with the clinical department actually examined by the doctor and performing machine learning again.
  • the learning model M can be updated so that the clinical department to be examined is output more correctly with respect to the acquired questionnaire answer Dq, so that the work burden of the doctor guiding the correct clinical department is burdensome. Can be reduced.
  • the step 104 of acquiring the clinical department selection result information Sa is a step of acquiring the clinical department selection result information Sa by the medical institution terminal (hospital terminal 30) arranged in the medical institution. 104.
  • the question-and-answer Dq for the plurality of patients P and the clinical department selection result information Sa can be acquired by the hospital terminal 30 arranged at the medical institution (hospital). Therefore, since machine learning can be performed by associating a plurality of inquiry answer Dqs with a plurality of clinical department selection result information Sa, the learning model M should be updated so as to correspond to various types of inquiry answer Dqs. Can be done. As a result, it is possible to estimate the clinical department to be correctly examined for various types of inquiry response Dq, so that the work load of the doctor guiding the correct clinical department can be further reduced.
  • the step 104 for acquiring the clinical department selection result information Sa is a terminal used by the doctor separately from the medical institution terminal (hospital terminal 30) at the time of medical examination.
  • the doctor can examine the patient P and input the examination information R to the electronic medical record system to acquire the clinical department selection result information Sa. Therefore, the doctor does not have to input the clinical department selection result information Sa to the hospital terminal 30 in addition to inputting the medical examination information R to the electronic medical record system. Can be acquired by the hospital terminal 30.
  • step 105 for updating the learning model M after acquiring a plurality of clinical department selection result information Sa by the medical institution terminal (hospital terminal 30), a plurality of acquired medical treatments are performed.
  • This is a step 105 of updating the learning model M by the department selection result information Sa.
  • the learning model M can be updated by a certain number of clinical department selection result information Sa without updating the learning model M each time the clinical department selection result information Sa is acquired.
  • the number of times the learning model M is updated can be reduced, so that an increase in the processing load required for the updating process can be suppressed.
  • the step 101 of receiving the inquiry answer Dq by the mobile information terminal (interview terminal 20) is further provided, and the step 102 of acquiring the inquiry answer Dq is the inquiry answer received by the inquiry terminal 20.
  • Step 102 of acquiring Dq by the medical institution terminal (hospital terminal 30), and step 103 of estimating the medical department information S is step 103 of estimating the medical department information S corresponding to the medical inquiry answer Dq received by the medical inquiry terminal 20.
  • the inquiry terminal 20 is configured to receive the inquiry answer Dq, the inquiry terminal 20 can input the inquiry answer Dq and convert it into electronic data, so that the work load of the receptionist of the medical institution is increased. Can be suppressed from increasing.
  • the step 105 for updating the learning model M is the step 105 for updating the learning model M at predetermined intervals.
  • the learning model M can be updated at a fixed time such as at night, which is outside the consultation hours of the medical institution. Therefore, it is possible to prevent the work of updating the learning model M from interfering with the work of dealing with the patient P by the receptionist of the doctor and the medical institution.
  • the step 105 for updating the learning model M is the learning generated so as to correspond to the selection of the clinical department of the medical institution to be examined by the patient P among the plurality of medical institutions.
  • Step 105 to update the model M it is conceivable that the clinical departments to be examined may differ depending on each of the plurality of medical institutions for the same inquiry answer Dq.
  • the learning model M generated so as to correspond to the selection of the clinical department of the medical institution to be examined by the patient P the clinical department to be examined so as to correspond to the medical institution to be examined by the patient P. Can be estimated. As a result, it is possible to accurately estimate the clinical department to be consulted corresponding to each of the plurality of medical institutions.
  • the interview terminal 20 is a mobile information terminal owned by the patient P
  • the medical inquiry terminal 20 may not be a mobile information terminal owned by the patient P, but may be a mobile information terminal provided in the medical institution (owned by the medical institution).
  • a medical inquiry server 50 is provided in the clinical department selection support system 100, and the medical inquiry terminal 20 and the hospital terminal 30 send and receive the medical inquiry answer Dq via the medical inquiry server 50.
  • the present invention is not limited to this.
  • the inquiry answer Dq may be directly transmitted from the inquiry terminal 20 to the hospital terminal 30 without providing the inquiry server 50 in the clinical department selection support system 100.
  • a clinical department to be examined is determined from one clinical department candidate information Sc based on an input operation to the operation unit 33 of the hospital terminal 30, but the present invention is not limited to this. ..
  • the clinical department to be examined may be determined from a plurality of clinical department candidate information Scs estimated by the clinical department information estimation unit 31b of the hospital terminal 30, or one estimated clinical department may be automatically examined. It may be decided as a clinical department to be treated.
  • the electronic medical record input information Dki may be generated by any of the medical inquiry terminal 20, the medical examination terminal 40, the medical inquiry server 50, or the electronic medical record device 10.
  • the data format of the electronic medical record input information Dki is configured as a text format
  • the present invention is not limited to this.
  • the data format of the electronic medical record input information Dki may be configured as an image format.
  • the inquiry server 50 is constructed on the cloud (cloud computing), but the present invention is not limited to this.
  • the interview server 50 may be built on one piece of hardware.
  • the learning model generation device 60 has shown an example including a control unit 61, a storage unit 62, and a communication unit 63, but the present invention is not limited to this.
  • the learning model generator 60 may be configured on the cloud (cloud computing).
  • the electronic medical record device 10 has a configuration separate from that of the medical examination terminal 40, but the present invention is not limited to this.
  • the medical examination terminal 40 may be configured to include the functions of the electronic medical record device 10 such as the electronic medical record server 12.
  • the hospital terminal 30 may be configured to have the function of the electronic medical record device 10.
  • the step 104 of acquiring the clinical department selection result information Sa is the step 104 of acquiring the information of the clinical department in which the patient P is actually examined as the clinical department selection result information Sa.
  • the present invention is not limited to this.
  • it may be configured to acquire the clinical department guidance information Sb, which is information for guiding the clinical department to be examined by the patient P, as the clinical department selection result information Sa.
  • the step 104 of acquiring the clinical department selection result information Sa is an example of step 104 of acquiring the clinical department selection result information Sa by the medical institution terminal (hospital terminal 30) arranged in the medical institution.
  • the present invention is not limited to this.
  • the clinical department selection result information Sa may be configured to be directly acquired by the learning model generation device 60.
  • the step 104 for acquiring the clinical department selection result information Sa is included in the medical examination terminal 40, which is a terminal used by the doctor for the medical examination, which is provided separately from the medical institution terminal (hospital terminal 30).
  • the present invention is not limited to this.
  • the hospital terminal 30 may be configured to input the clinical department selection result information Sa based on the examination information R.
  • step 105 of updating the learning model M after acquiring a plurality of clinical department selection result information Sa by the medical institution terminal (hospital terminal 30), the acquired plurality of clinical department selection result information Sa
  • the learning model M may be updated every time the clinical department selection result information Sa for the patient P is acquired.
  • the mobile information terminal further includes step 101 for receiving the question and answer Dq
  • step 102 for acquiring the question and answer Dq is a medical institution terminal that receives the question and answer Dq received by the inquiry terminal 20.
  • Step 102 acquired by (hospital terminal 30), and step 105 of updating the learning model M is to perform machine learning again by associating the medical inquiry answer Dq received by the medical inquiry terminal 20 with the medical department selection result information Sa.
  • the present invention is not limited to this, although the example of step 105 for updating the learning model M is shown.
  • the hospital terminal 30 provided in the medical facility (hospital) may be used to accept the inquiry answer Dq.
  • the step 105 for updating the learning model M is an example of step 105 for updating the learning model M at predetermined intervals, but the present invention is not limited to this.
  • the learning model M may be updated every time the clinical department selection result information Sa for a predetermined number of people is acquired.
  • the step 105 of updating the learning model M updates the learning model M generated so as to correspond to the selection of the clinical department of the medical institution to be examined by the patient P among the plurality of medical institutions.
  • the present invention is not limited to this.
  • the clinical department information S may be estimated based on the same learning model M.
  • the steps to obtain the interview answer which is the answer to the inquiry to determine the department to be examined by the patient
  • the answer to the inquiry corresponds to the acquired answer to the inquiry based on a learning model for supporting the selection of the clinical department, which is machine-learned by associating the answer to the inquiry with the information on the department indicating the department to be examined by the patient.
  • Steps to estimate clinical department information After the step of estimating the clinical department information, there is a step of acquiring clinical department selection result information indicating the clinical department in which the patient is examined.
  • a method of updating a learning model for clinical department selection support comprising a step of updating the learning model by re-machine learning by associating the acquired inquiry answer with the clinical department selection result information.
  • (Item 2) The clinical department selection according to item 1, wherein the step of acquiring the clinical department selection result information is a step of acquiring information on the clinical department in which the patient was actually examined as the clinical department selection result information. How to update the learning model for assistance.
  • the step of acquiring the clinical department selection result information is a step of acquiring the clinical department selection result information by a medical institution terminal arranged in the medical institution, and is an update of the learning model for supporting the clinical department selection according to item 1.
  • the step of acquiring the clinical department selection result information is to examine the patient with respect to the electronic medical examination system included in the medical examination terminal, which is a terminal used by the doctor for the medical examination, which is provided separately from the medical institution terminal.
  • the step of updating the learning model is a step of acquiring the plurality of the clinical department selection result information by the medical institution terminal and then updating the learning model with the acquired plurality of clinical department selection result information.
  • the method of updating the learning model for supporting the selection of clinical departments according to 3.
  • the step of acquiring the questionnaire answer is a step of acquiring the inquiry answer received by the mobile information terminal by the medical institution terminal.
  • the step of updating the learning model is a step of updating the learning model by re-machine learning by associating the questionnaire response received by the mobile information terminal with the clinical department selection result information.
  • the method of updating the learning model for supporting the selection of clinical departments according to 3.
  • the step of updating the learning model is the step of updating the learning model generated so as to correspond to the selection of the clinical department of the medical institution to be examined by the patient among the plurality of medical institutions, according to item 1. How to update the learning model to support the selection of clinical departments.
  • the Questionnaire Answer Acquisition Department which obtains the interview answer, which is the answer to the inquiry to determine the clinical department to be examined by the patient,
  • the answer to the inquiry corresponds to the acquired answer to the inquiry based on a learning model for supporting the selection of the clinical department, which is machine-learned by associating the answer to the inquiry with the information on the department indicating the department to be examined by the patient.
  • the clinical department information estimation department that estimates clinical department information
  • a clinical department selection result information acquisition unit that acquires clinical department selection result information indicating the clinical department in which the patient is examined, and a clinical department selection result information acquisition unit.
  • a clinical department selection support system including a learning model update unit that updates the learning model by associating the acquired inquiry response with the clinical department selection result information and performing machine learning again.
  • the answer to the inquiry corresponds to the acquired answer to the inquiry based on a learning model for supporting the selection of the clinical department, which is machine-learned by associating the answer to the inquiry with the information on the department indicating the department to be examined by the patient.
  • a clinical department selection support program that causes a computer to execute control for updating the learning model by re-machine learning by associating the acquired questionnaire answer with the clinical department selection result information.
  • Clinical department selection support system 20
  • Questionnaire terminal mobile information terminal
  • Hospital terminal medical institution terminal
  • 31a Question answer acquisition department
  • Clinical department information estimation department 31c
  • Clinical department selection result information acquisition department 40
  • Medical examination terminal 61b Learning model update department

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

Le procédé de mise à jour d'un modèle d'apprentissage pour une aide à la sélection de service clinique selon la présente invention comprend : une étape (103) consistant à estimer, sur la base d'un modèle d'apprentissage (M) pour une aide à la sélection de service clinique qui a été soumis à un apprentissage machine et dans lequel des réponses d'entretien médical (Dq) et des informations de service clinique (S) sont associées les unes aux autres, les informations de service clinique (S) correspondant aux réponses d'entretien médicales (Dq) acquises; et une étape (105) consistant à mettre à jour le modèle d'apprentissage (M) en associant les réponses d'entretien médical (Dq) acquises à des informations de résultat de sélection de service clinique (Sa) et à réaliser à nouveau l'apprentissage machine.
PCT/JP2020/018678 2019-08-27 2020-05-08 Procédé de mise à jour d'un modèle d'apprentissage pour une aide à la sélection de service clinique, système d'aide à la sélection de service clinique et programme d'aide à la sélection de service clinique WO2021038969A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2021542000A JP7276467B2 (ja) 2019-08-27 2020-05-08 診療科選択支援用の学習モデルの更新方法、診療科選択支援システム、および、診療科選択支援プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019-154575 2019-08-27
JP2019154575 2019-08-27

Publications (1)

Publication Number Publication Date
WO2021038969A1 true WO2021038969A1 (fr) 2021-03-04

Family

ID=74685433

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/018678 WO2021038969A1 (fr) 2019-08-27 2020-05-08 Procédé de mise à jour d'un modèle d'apprentissage pour une aide à la sélection de service clinique, système d'aide à la sélection de service clinique et programme d'aide à la sélection de service clinique

Country Status (2)

Country Link
JP (1) JP7276467B2 (fr)
WO (1) WO2021038969A1 (fr)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11338920A (ja) * 1998-05-22 1999-12-10 Hitachi Ltd 新規患者受付装置による新規患者受付処理システム
JP2011128855A (ja) * 2009-12-17 2011-06-30 Toshiba Corp 病院受付システム、及び診療科振分装置
JP2014098946A (ja) * 2012-11-13 2014-05-29 Knowledge Creation Technology Co Ltd 診療業務支援システムおよびプログラム
JP2016024600A (ja) * 2014-07-18 2016-02-08 トヨタ自動車株式会社 質疑応答装置および質疑応答装置の制御方法
JP2016177461A (ja) * 2015-03-19 2016-10-06 株式会社リコー 情報処理システム、情報処理方法、携帯端末、及び情報処理プログラム
JP2017068479A (ja) * 2015-09-29 2017-04-06 日本電気株式会社 個人医療情報処理システム
US20180046773A1 (en) * 2016-08-11 2018-02-15 Htc Corporation Medical system and method for providing medical prediction
JP2018067137A (ja) * 2016-10-19 2018-04-26 株式会社Ｎｔｔドコモ 情報処理装置
JP2019087196A (ja) * 2017-11-10 2019-06-06 富士通株式会社 診療科推奨プログラム、診療科推奨方法及び情報処理装置

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11338920A (ja) * 1998-05-22 1999-12-10 Hitachi Ltd 新規患者受付装置による新規患者受付処理システム
JP2011128855A (ja) * 2009-12-17 2011-06-30 Toshiba Corp 病院受付システム、及び診療科振分装置
JP2014098946A (ja) * 2012-11-13 2014-05-29 Knowledge Creation Technology Co Ltd 診療業務支援システムおよびプログラム
JP2016024600A (ja) * 2014-07-18 2016-02-08 トヨタ自動車株式会社 質疑応答装置および質疑応答装置の制御方法
JP2016177461A (ja) * 2015-03-19 2016-10-06 株式会社リコー 情報処理システム、情報処理方法、携帯端末、及び情報処理プログラム
JP2017068479A (ja) * 2015-09-29 2017-04-06 日本電気株式会社 個人医療情報処理システム
US20180046773A1 (en) * 2016-08-11 2018-02-15 Htc Corporation Medical system and method for providing medical prediction
JP2018067137A (ja) * 2016-10-19 2018-04-26 株式会社Ｎｔｔドコモ 情報処理装置
JP2019087196A (ja) * 2017-11-10 2019-06-06 富士通株式会社 診療科推奨プログラム、診療科推奨方法及び情報処理装置

Also Published As

Publication number Publication date
JPWO2021038969A1 (fr) 2021-03-04
JP7276467B2 (ja) 2023-05-18

Similar Documents

Publication Publication Date Title
Amin et al. Association of same-day discharge after elective percutaneous coronary intervention in the United States with costs and outcomes
Wenger et al. The quality of medical care provided to vulnerable community-dwelling older patients
Oulton The global nursing shortage: an overview of issues and actions
Berti et al. A proposal for interdisciplinary, nurse-coordinated atrial fibrillation expert programmes as a way to structure daily practice
Blöndal et al. Attitudes of registered and licensed practical nurses about the importance of families in surgical hospital units: Findings from the Landspitali University Hospital Family Nursing Implementation Project
Reckrey et al. The critical role of social workers in home-based primary care
JP6145160B2 (ja) 患者情報インターフェース
Blumenthal et al. Association between treatment by locum tenens internal medicine physicians and 30-day mortality among hospitalized Medicare beneficiaries
Clarke et al. Determining differences in user performance between expert and novice primary care doctors when using an electronic health record (EHR)
Stukenborg et al. Cancer patient-reported outcomes assessment using wireless touch screen tablet computers
Nasarwanji et al. Identifying challenges associated with the care transition workflow from hospital to skilled home health care: perspectives of home health care agency providers
Al-Hawamdih et al. Examining the relationship between nursing informatics competency and the quality of information processing
Werner et al. A new strategy to improve quality: rewarding actions rather than measures
Cutilli et al. Case studies in geriatric health literacy
Hughes et al. A preliminary qualitative analysis on the feasibility of using gaming technology in caregiver assessment
Moshood et al. Efficiency of medical technology in measuring service quality in the Nigerian healthcare sector
JP6775203B2 (ja) 診療支援装置、診療支援方法、診療支援プログラムおよび診療支援システム
Clifford-Rashotte et al. Assessing the potential for nurse-led HIV pre-and postexposure prophylaxis in Ontario
Goodman et al. Patient and staff perspective of a nurse-led support programme for patients waiting for cardiac surgery: participant perspective of a cardiac support programme
JP2023080373A (ja) 問診システム
JP7259972B2 (ja) 電子カルテ入力方法、電子カルテ入力システム、および、電子カルテ入力プログラム
Brook Continuing medical education: let the guessing begin
WO2021038969A1 (fr) Procédé de mise à jour d'un modèle d'apprentissage pour une aide à la sélection de service clinique, système d'aide à la sélection de service clinique et programme d'aide à la sélection de service clinique
JP2014199557A (ja) 診療支援装置
Kunadian et al. Impact of implementation of evidence-based strategies to reduce door-to-balloon time in patients presenting with STEMI: continuous data analysis and feedback using a statistical process control plot

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20859337

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021542000

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20859337

Country of ref document: EP

Kind code of ref document: A1