Information processing device, information processing method, and information processing program
The information processing device addresses the issue of inaccurate medical records by using biometric and input data to generate auxiliary medical information and derive examination methods, improving diagnostic accuracy through machine learning models.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-01-24
- Publication Date
- 2026-03-17
AI Technical Summary
Inaccurate or incomplete medical information recorded in electronic medical records due to patients' inability to clearly convey their symptoms, leading to difficulties in formulating appropriate examination methods.
An information processing device that acquires biometric information and input data from user terminals to generate auxiliary medical information and derive recommended examination methods using machine learning models, such as Generative Adversarial Networks and neural networks, to support accurate diagnosis.
Enhances the formulation of examination methods by providing supplementary medical information and recommended tests based on biometric and input data, ensuring a more accurate diagnosis process.
Smart Images

Figure 0007831999000001 
Figure 0007831999000002 
Figure 0007831999000003
Abstract
Description
Technical Field
[0001] The disclosed technology relates to an information processing apparatus, an information processing method, and an information processing program.
Background Art
[0002] As a technology related to the selection of test items for examining a patient's disease, the following technology is known. For example, in Patent Document 1, there are provided an onset probability calculation means for calculating the disease onset probability of a predetermined disease based on an individual's physical information, a criterion generation means for generating a selection criterion for test items for examining a predetermined disease according to the calculated disease onset probability, a test item database for associating in advance a plurality of types of test items capable of examining the predetermined disease with the attributes of these test items, and a search means for searching the test item database for test items having attributes that satisfy the selection criterion.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] Medical document data such as electronic medical records records medical information indicating symptoms and the like obtained through a patient interview. A doctor formulates an examination method for making a definite diagnosis based on this medical information recorded in the medical document data. However, there are cases where the patient does not clearly recognize their own symptoms or cannot correctly convey their symptoms to the doctor. In such cases, there is a risk that inaccurate information may be recorded in the medical document data or useful information may not be recorded in the medical document data, and as a result, it becomes difficult to formulate an appropriate examination method.
[0005] The disclosure technology aims to assist in the development of examination methods for diagnosing the physical condition of the user, who is a patient. [Means for solving the problem]
[0006] The information processing device relating to the disclosed technology comprises at least one processor. The processor acquires at least one of input information entered into a user terminal device used by the user and biometric information measured about the user, and derives a recommended examination method for diagnosing the user's body based on at least one of the acquired input information and biometric information. [Effects of the Invention]
[0007] The disclosed technology makes it possible to assist in developing examination methods for diagnosing a user's body compared to not acquiring at least one of the input information entered into a user terminal device used by the user and biometric information measured about the user. [Brief explanation of the drawing]
[0008] [Figure 1] This figure shows an example of the configuration of an information processing system according to an embodiment of the disclosed technology. [Figure 2] This figure shows an example of medical information recorded in an electronic medical record according to an embodiment of the disclosed technology. [Figure 3] This figure shows an example of the hardware configuration of an information processing device according to an embodiment of the disclosed technology. [Figure 4] This is a functional block diagram showing an example of the functional configuration of an information processing device according to an embodiment of the disclosed technology. [Figure 5] This figure shows an example of an analysis process according to an embodiment of the disclosed technology. [Figure 6] This figure shows an example of an analysis process according to an embodiment of the disclosed technology. [Figure 7] This diagram shows the functionality of an auxiliary medical information generation model according to an embodiment of the disclosed technology. [Figure 8] This figure shows an example of a learning method for an auxiliary medical information generation model according to an embodiment of the disclosed technology. [Figure 9] This figure shows an example of a generation process according to an embodiment of the disclosed technology. [Figure 10] This figure shows the functionality of the recommended inspection method derivation model according to the disclosed technology. [Figure 11] This figure shows an example of a derivation process according to an embodiment of the disclosed technology. [Figure 12] This figure shows an example of a display format for a recommended inspection method according to an embodiment of the disclosed technology. [Figure 13] This flowchart shows an example of the processing flow performed by executing an information processing program according to an embodiment of the disclosed technology. [Figure 14] This is a functional block diagram showing an example of the functional configuration of an information processing device according to an embodiment of the disclosed technology. [Figure 15] This figure shows an example of a screen for receiving inspection orders according to an embodiment of the disclosed technology. [Figure 16] This figure shows an example of how the comparison results are displayed by the comparison unit according to an embodiment of the disclosed technology. [Figure 17] This figure shows an example of a recommended testing method and a display format for supplementary medical information according to an embodiment of the disclosed technology. [Figure 18] This figure shows an example of a recommended testing method and a display format for supplementary medical information according to an embodiment of the disclosed technology. [Figure 19] This flowchart shows an example of the processing flow performed by executing an information processing program according to an embodiment of the disclosed technology. [Figure 20] This is a functional block diagram showing an example of the functional configuration of an information processing device according to an embodiment of the disclosed technology. [Figure 21] This figure shows the functionality of the recommended inspection method derivation model according to the disclosed technology. [Figure 22] This figure shows an example of an integrated process according to an embodiment of the disclosed technology. [Figure 23]A diagram showing an example of a display form of a recommended examination method according to an embodiment of the disclosed technology [Figure 24] A flowchart showing an example of a process flow implemented by executing an information processing program according to an embodiment of the disclosed technology. [Figure 25] A diagram showing an example of a display form of a recommended examination method according to an embodiment of the disclosed technology. [Figure 26] A functional block diagram showing an example of a functional configuration of an information processing apparatus according to an embodiment of the disclosed technology.
Embodiments for Carrying Out the Invention
[0009] Hereinafter, an example of an embodiment of the disclosed technology will be described while referring to the drawings. In each drawing, the same or equivalent components and parts are given the same reference numerals, and duplicate descriptions are omitted.
[0010] [First Embodiment] FIG. 1 is a diagram showing an example of the configuration of an information processing system 1 according to an embodiment of the disclosed technology. The information processing system 1 includes an information processing apparatus 10, a medical data server 50, a user terminal device 30, and a biological information measuring device 31.
[0011] The medical data server 50 is a computer that manages medical data of patients. Electronic medical records 51 for each patient are stored in the medical data server 50. The electronic medical record 51 is medical document data in which medical information obtained by examining a user who is a patient is recorded.
[0012] The information processing device 10 is connected to the medical data server 50 via a network 41, enabling communication and access to the electronic medical records 51 stored in the medical data server 50. The information processing device 10 can view, create, and edit the electronic medical records 51. The information processing device 10 and the medical data server 50 may be installed in a medical institution such as a hospital, in which case the network 41 may be a LAN (Local Area Network) built within the medical institution. The medical data server 50 may also be a so-called cloud server. In this case, the network 41 may be a WAN (Wide Area Network).
[0013] The user terminal device 30 is a computer used by a user who is a patient whose medical information is recorded in the electronic medical record 51. The user terminal device 30 may be, for example, a personal computer or smartphone used personally by the user (patient). The user terminal device 30 can be connected to the information processing device 10 via the network 42. The network 42 may be at least one of a LAN (Local Area Network) or a WAN (Wide Area Network), or a combination thereof.
[0014] The user terminal device 30 has various applications installed, such as a web browser, email application, messenger application, and SNS application, and users can use these applications. For example, a user can use the user terminal device 30 to perform a web search by entering search keywords into a search engine. Furthermore, a user can use the email application, messenger application, SNS (Social Networking Service) application, etc., installed on the user terminal device 30 to send or transmit messages or information to specific or unspecified recipients. Although only one user terminal device 30 is shown in Figure 1, the information processing system 1 may include multiple user terminal devices 30.
[0015] The biometric information measuring device 31 measures the user's (patient's) biometric information. This biometric information may include, for example, information indicating at least one of the following: body temperature, heart rate, electrocardiogram, electromyogram, blood pressure, arterial blood oxygen saturation (SpO2), blood glucose level, and lipid level. The biometric information may also include the rate of change of these measured values over any given period. The biometric information measuring device 31 may be a wearable device such as a smartwatch equipped with sensors to measure this biometric information. The biometric information measuring device 31 has the function of continuously measuring the user's biometric information according to a predetermined time schedule and transmitting the measured values to the user terminal device 30. The biometric information measuring device 31 may perform measurements for various measurement items, for example, once or twice daily. The measurement frequency may differ for each measurement item. Furthermore, the measurement time schedule may be set by the user at any time. The connection between the user terminal device 30 and the biometric information measuring device 31 may be wireless or wired. Furthermore, the user terminal device 30 and the biological information measuring device 31 may be connected via a network consisting of at least one of a LAN (Local Area Network) or a WAN (Wide Area Network), or a combination thereof.
[0016] The user terminal device 30 transmits the biometric information measured by the biometric information measuring device 31 to the information processing device 10. The user terminal device 30 also transmits the input information entered into the user terminal device 30 to the information processing device 10. The input information may be information entered on various applications installed on the user terminal device 30. The input information may include, for example, search keywords entered into a search engine for searching information on a network. The input information may also include, for example, words sent or transmitted to a specific or unspecified recipient, such as in outgoing emails, messages on messenger applications, posts on social networking services (SNS), weblog entries, or chat conversations.
[0017] The user terminal device 30 may immediately transmit the biological information and input information to the information processing device 10 after they have been measured, or it may transmit them to the information processing device 10 at a predetermined time. Alternatively, the user terminal device 30 may transmit the biological information and input information to the information processing device 10 based on a transmission instruction for these two pieces of information. The transmission instruction for the biological information and input information may be transmitted from the information processing device 10. The information processing device 10 uses the biological information and input information transmitted from the user terminal device 30 to perform information processing to support the creation of the electronic medical record 51. The timing of transmission to the information processing device 10 may also be set by the user at any time.
[0018] Figure 2 shows an example of medical information recorded in the electronic medical record 51. The medical information recorded in the electronic medical record 51 includes "subjective information," "objective information," "evaluation," and "plan." "Subjective information" is information obtained through interviews with the patient and includes, for example, information on the patient's self-reported symptoms, onset date, present illness, past medical history, family history, and lifestyle.
[0019] "Objective information" refers to objective information obtained by examining and testing a patient. "Objective information" includes data showing the results of various tests performed on the patient. Testing methods include various methods such as imaging tests, specimen tests, and physiological function tests, and are typically formulated by a physician considering subjective information, etc. Based on the formulated testing methods, a test order is created, and the tests are performed according to the test order. The test order may be recorded as medical information in the electronic medical record 51.
[0020] "Evaluation" refers to information that shows a comprehensive assessment based on the physician's diagnosis, subjective information, and objective information, which has been analyzed or interpreted. "Plan" refers to information that shows the treatment policy, content, and lifestyle guidance decided based on the "Evaluation." The electronic medical record 51 can be viewed, created, and edited by a physician, for example, using the information processing device 10. The created electronic medical record 51 is stored and kept on the medical data server 50.
[0021] As described above, examination methods for diagnosing a patient's physical condition are typically formulated based on subjective information obtained through patient interviews. However, there are cases where patients do not clearly recognize their symptoms or are unable to accurately communicate their symptoms to a doctor. In such cases, inaccurate information may be recorded in the electronic medical record 51, or useful information may not be recorded in the electronic medical record 51. If the medical information recorded in the electronic medical record 51 is inaccurate or incomplete, it becomes difficult to formulate appropriate examination methods. The information processing device 10 has a function to support the formulation of examination methods.
[0022] Figure 3 shows an example of the hardware configuration of the information processing device 10. The information processing device 10 includes a CPU (Central Processing Unit) 101, RAM (Random Access Memory) 102, non-volatile memory 103, input device 104, display 105, and network interface 106. These hardware components are connected to a bus 107.
[0023] The display 105 is, for example, a liquid crystal display or an LED (Light Emitting Diode) display. The input device 104 may include, for example, a keyboard and a mouse, and may also include proximity input devices such as a touch panel display, audio input devices such as a microphone, and non-contact input devices such as a camera and sensors. The network interface 106 is an interface for the information processing device 10 to connect to networks 41 and 42.
[0024] The non-volatile memory 103 is a non-volatile storage medium such as a hard disk or flash memory. The non-volatile memory 103 stores an information processing program 110, an auxiliary medical information generation model 120, and a recommended examination method derivation model 130. The RAM 102 is work memory for the CPU 101 to execute processing. The CPU 101 loads the information processing program 110 stored in the non-volatile memory 103 into the RAM 102 and executes processing according to the information processing program 110. The CPU 101 is an example of a "processor" in the disclosed technology. Details of the auxiliary medical information generation model 120 and the recommended examination method derivation model 130 will be described later.
[0025] Figure 4 is a functional block diagram showing an example of the functional configuration of the information processing device 10. The information processing device 10 includes a user information acquisition unit 11, a recording processing unit 12, an analysis unit 13, an auxiliary medical information generation unit 14, a recommended examination method derivation unit 15, and a display processing unit 16. When the CPU 101 executes the information processing program 110, the CPU 101 functions as the user information acquisition unit 11, the recording processing unit 12, the analysis unit 13, the auxiliary medical information generation unit 14, the recommended examination method derivation unit 15, and the display processing unit 16.
[0026] The user information acquisition unit 11 acquires the user's (patient's) biometric information and input information transmitted from the user terminal device 30. The user information acquisition unit 11 acquires the biometric information and input information, for example, once or twice a day.
[0027] The recording processing unit 12 records (saves) the biometric information acquired by the user information acquisition unit 11 in the non-volatile memory 103, adding metadata including date and time information indicating the measurement date and time of the biometric information and a user ID (identification). The recording processing unit 12 also performs a selection process to select input information from the input information acquired by the user information acquisition unit 11 that contains specific words related to the user's (patient's) physical condition. The recording processing unit 12 then records (saves) the selected input information in the non-volatile memory 103, adding metadata including date and time information indicating the input date and time of that input information and a user ID.
[0028] Examples of specific words related to the user's (patient's) physical condition include "fever," "cough," "headache," "stomach ache," "dizziness," "cold," "insomnia," "anxiety," "depressed mood," "lethargy," "irritability," "influenza," "novel coronavirus," and "COVID-19." Such specific words related to the user's (patient's) physical condition may be registered in advance. In this case, the recording processing unit 12 may select input information that includes the pre-registered words from the input information acquired by the user information acquisition unit 11 and record it in the non-volatile memory 103. By performing the above selection process on the input information, input information unrelated to the user's (patient's) physical condition is excluded from processing. Biometric information and input information transmitted daily from the user terminal device 30 are stored in the non-volatile memory 103 of the information processing device 10.
[0029] The analysis unit 13 performs analysis on the biometric information and input information recorded in the non-volatile memory 103 and extracts information from the biometric information and input information that indicates an abnormality in the user's physical condition. Figures 5 and 6 show examples of the analysis process performed by the analysis unit 13. As shown in Figure 5, the analysis unit 13 acquires biometric information recorded in the non-volatile memory 103. Figure 5 shows time-series data of heart rate as an example of biometric information. Based on the time-series data of heart rate, the analysis unit 13 calculates the average value of the resting heart rate over the past few days. If the time-series data of heart rate contains data where the difference or rate of variation from the resting heart rate is greater than a predetermined value, the analysis unit 13 determines that there is an abnormality in the heart rate and extracts the data indicating that abnormal value. Figure 5 shows an example where the measured values (120 and 115) at 15:30 and 15:45 on November 10th are extracted as data indicating an abnormality.
[0030] Furthermore, as shown in Figure 6, the analysis unit 13 acquires the input information recorded in the non-volatile memory 103. Figure 6 shows an example of input information, specifically a message sent by a user and entered into a messenger application. The analysis unit 13 extracts words from the input information that indicate an abnormality in the user's physical condition. Figure 6 shows an example where the words "chest pressure" and "difficulty breathing" are extracted from a message entered at 3:35 PM on November 10th, and the word "not feeling well, going to the hospital" is extracted from a message entered at 4:45 PM on the same day. The analysis unit 13 derives the information extracted from the biological information and input information as the analysis result.
[0031] The auxiliary medical information generation unit 14 generates auxiliary medical information based on the analysis results derived by the analysis unit 13. Auxiliary medical information is supplementary information to the medical information (subjective information and objective information) recorded in the electronic medical record 51, and is information indicating the user's physical condition based on biological information and input information. The auxiliary medical information generation unit 14 generates auxiliary medical information that is written in the same format as the medical information recorded in the electronic medical record 51.
[0032] As shown in Figure 7, the auxiliary medical information generation unit 14 generates auxiliary medical information using the auxiliary medical information generation model 120 stored in the non-volatile memory 103. The auxiliary medical information generation model 120 is a mathematical model that takes input information and the results of analysis of biological information as inputs and outputs auxiliary medical information, and is constructed using machine learning.
[0033] Figure 8 shows an example of a learning method for the auxiliary medical information generation model 120. The auxiliary medical information generation model 120 is trained using, for example, a so-called Generative Adversarial Network (GAN). That is, a classifier 140 is used to train the auxiliary medical information generation model 120. The classifier 140 determines whether the auxiliary medical information input to it is generated by the auxiliary medical information generation model 120 (fake) or created by a doctor (real). The auxiliary medical information generation model 120 is trained by backpropagation of errors based on the determination result by the classifier 140. The auxiliary medical information generation model 120 is trained until the auxiliary medical information generated by the auxiliary medical information generation model 120 (fake) is incorrectly determined by the classifier 140 as having been created by a doctor (real). On the other hand, the classifier 140 is trained to correctly determine whether the supplementary medical information input to it is generated by the supplementary medical information generation model 120 (fake) or created by a doctor (genuine). The supplementary medical information generation model 120 may be constructed by machine learning using multiple combinations of training data, such as the results of analyzing training input information and biometric information, and training supplementary medical information.
[0034] Figure 9 shows an example of the generation process performed by the auxiliary medical information generation unit 14. Figure 9 illustrates a case in which auxiliary medical information is generated based on the analysis results by the analysis unit 13, as illustrated in Figures 5 and 6. As illustrated in Figure 9, the auxiliary medical information may include auxiliary subjective information generated based on input information and auxiliary objective information generated based on biological information.
[0035] The recommended examination method derivation unit 15 derives a recommended examination method for diagnosing the user's physical condition based on the auxiliary medical information generated by the auxiliary medical information generation unit 14. As shown in Figure 10, the recommended examination method derivation unit 15 derives the recommended examination method using the recommended examination method derivation model 130 stored in the non-volatile memory 103. The recommended examination method derivation unit 15 is a mathematical model such as a neural network that takes auxiliary medical information as input and outputs the recommended examination method. The recommended examination method derivation model 130 is constructed, for example, by machine learning using multiple combinations of learning auxiliary medical information and learning recommended examination methods as training data. The learning recommended examination method may be, for example, one selected by an experienced and skilled physician who estimates the cause, disease name, and abnormal location from the symptoms indicated by the corresponding learning auxiliary medical information, and deems it necessary to make a definitive diagnosis.
[0036] Figure 11 shows an example of the derivation process performed by the recommended examination method derivation unit 15. Figure 11 illustrates the case in which a recommended examination method is derived based on the supplementary medical information illustrated in Figure 9. As illustrated in Figure 9, the recommended examination method may include examination items (e.g., X-ray, electrocardiogram) and specific techniques (e.g., standing chest test, resting 12-lead electrocardiogram, exercise test).
[0037] The display processing unit 16 displays the recommended examination method derived by the recommended examination method derivation unit 15 on the display 105. The display processing unit 16 may, for example, display the recommended examination method for a patient when creating an examination order using the information processing device 10. The display processing unit 16 may also display the recommended examination method on the display 105 together with the corresponding supplementary medical information.
[0038] Figure 12 shows an example of the display format for recommended examination methods. As illustrated in Figure 12, when creating an examination order, the display processing unit 16 displays an input field 220 for the examination methods to be included in the examination order on the display screen 200 of the display 105. In addition, the display processing unit 16 displays the recommended examination methods 300 derived by the recommended examination method derivation unit 15 and the auxiliary medical information 400 generated by the auxiliary medical information generation unit 14 on the display screen 200 along with the input field 220 for the examination methods. The physician can input the examination methods to be included in the examination order in the input field 220 by referring not only to the medical information recorded in the electronic medical record 51 but also to the recommended examination methods 300 and auxiliary medical information 400 displayed on the display screen 200. The method of inputting the examination methods may be by directly entering text, or by selecting one or more examination methods from multiple examination methods included in a pull-down menu.
[0039] Figure 13 is a flowchart illustrating an example of the processing flow performed by the CPU 101 when it executes the information processing program 110. The information processing program 110 is executed, for example, when a user instructs the start of processing by operating the input device 104.
[0040] In step S1, the CPU 101 functions as a user information acquisition unit 11 and acquires the user's (patient's) biometric information and input information transmitted from the user terminal device 30. The CPU 101 acquires the biometric information and input information, for example, once or twice a day.
[0041] In step S2, the CPU 101 functions as a recording processing unit 12 and records (saves) the biometric information acquired in step S1 in non-volatile memory 103, adding metadata including date and time information indicating the measurement date and time and a user ID. The CPU 101 also performs a selection process to select input information from the input information acquired in step S1 that contains specific words related to the user's (patient's) physical condition, and records (saves) the selected input information in non-volatile memory 103, adding metadata including date and time information indicating the input date and time and a user ID. The biometric information and input information transmitted daily from the user terminal device 30 are stored in the non-volatile memory 103 of the information processing device 10.
[0042] In step S3, the CPU 101 functions as an analysis unit 13 and performs analysis processing on the biometric information and input information recorded in the non-volatile memory 103, and extracts information from the biometric information and input information that indicates that there is an abnormality in the user's physical condition. The analysis unit 13 derives the information extracted from the biometric information and input information as the analysis result.
[0043] In step S4, the CPU 101 functions as an auxiliary medical information generation unit 14 and generates auxiliary medical information based on the analysis results derived in step S3. The CPU 101 generates auxiliary medical information by inputting the analysis results of the input information and biological information into the auxiliary medical information generation model 120 stored in the non-volatile memory 103. The auxiliary medical information may include auxiliary subjective information generated based on the input information and auxiliary objective information generated based on the biological information.
[0044] In step S5, the CPU 101 functions as a recommended examination method derivation unit 15 and derives a recommended examination method for diagnosing the user's physical condition based on the auxiliary medical information generated in step S4. The CPU 101 derives the recommended examination method by inputting the auxiliary medical information into the recommended examination method derivation model 130 stored in the non-volatile memory 103.
[0045] In step S6, the CPU 101 functions as a display processing unit 16 and displays the recommended examination method derived in step S5 on the display screen 200 of the display 105. The CPU 101 may, for example, display the recommended examination method for a patient when recording an examination order in the electronic medical record 51 using the information processing device 10. The display processing unit 16 may also display the recommended examination method on the display 105 together with the corresponding auxiliary medical information generated in step S4.
[0046] As described above, the information processing device 10 acquires input information entered into a user terminal device used by the user (patient) and biological information measured about the user (patient), and derives a recommended examination method for diagnosing the user's physical condition based on the biological information and input information. For example, the information processing device 10 presents a recommended examination method when creating an examination order for the user (patient).
[0047] As described above, inaccurate information may be recorded in the electronic medical record 51, or useful information may not be recorded in the electronic medical record 51. In such cases, it becomes difficult to formulate appropriate examination methods. According to the information processing device 10 of the disclosed technology embodiment, recommended examination methods are derived based on biological information and input information. Biological information and input information are information obtained on a daily basis about the user and may include supplementary information to the medical information recorded in the electronic medical record 51. Recommended examination methods derived based on such biological information and input information can be said to have a certain degree of validity. In other words, according to the information processing device 10 of the disclosed technology embodiment, it is possible to support the formulation of examination methods for diagnosing the user's body.
[0048] In this embodiment, we have illustrated the case where a recommended testing method is derived based on both biological information and input information. However, it is also possible to acquire only one of the biological information or input information and derive a recommended testing method based on the acquired biological information or input information.
[0049] Furthermore, in this embodiment, the example given is that the information processing device 10 acquires biometric information and input information transmitted from the user terminal device 30. However, if the biometric information and input information are stored on a predetermined server, the information processing device 10 may access the server to acquire the biometric information and input information.
[0050] Furthermore, while the example given illustrates a case where the information processing device 10 includes the functions of the recording processing unit 12, the analysis unit 13, the auxiliary medical information generation unit 14, and the recommended examination method derivation unit 15, the user terminal device 30 may include at least some of these functions.
[0051] [Second Embodiment] Figure 14 is a functional block diagram showing an example of the functional configuration of an information processing device 10A according to a second embodiment of the disclosed technology. The information processing device 10A according to this embodiment differs from the information processing device 10 according to the first embodiment (see Figure 4) in that it further includes an inspection order receiving unit 17 and a comparison unit 18.
[0052] The examination order reception unit 17 accepts the specification of examination methods to be included in the examination order for the user (patient). The examination order reception unit 17 displays the examination order reception screen illustrated in Figure 15 on the display screen 200 of the display 105. The physician creating the examination order enters the examination methods to be included in the examination order into the input field 220, taking into account subjective information, etc., recorded in the electronic medical record 51. The method of inputting the examination methods may be by directly entering text, or by selecting one or more examination methods from multiple examination methods included in a pull-down menu. When the examination methods are entered into the input field 220 and the OK button 221 is clicked, the examination methods entered into the input field 220 are designated as examination methods to be included in the examination order (hereinafter referred to as designated examination methods) and accepted by the examination order reception unit 17.
[0053] The comparison unit 18 compares the specified inspection method received by the inspection order reception unit 17 with the recommended inspection method derived by the recommended inspection method derivation unit 15, and derives a comparison result. Specifically, the comparison unit 18 determines which of the recommended inspection methods do not match the specified inspection method and which do.
[0054] The display processing unit 16 displays the recommended inspection method derived by the recommended inspection method derivation unit 15, along with the comparison results derived by the comparison unit 18, on the display screen 200 of the display 105. More specifically, it displays on the display screen 200 which of the recommended inspection methods match the specified inspection method and which do not.
[0055] Figure 16 shows an example of how the comparison results are displayed by the comparison unit 18. When an examination method is entered in the examination method input field 220 and the confirmation button 221 is clicked, the display processing unit 16 displays the recommended examination methods 300 derived by the recommended examination method derivation unit 15 on the display screen. The display processing unit 16 displays "Specified" for recommended examination methods that match the designated examination method, and "Not Specified" for those that do not match. In the example shown in Figure 16, "X-ray examination: standing chest" and "Electrocardiogram: resting 12-lead," which were derived as recommended examination methods, match the designated examination methods, and are displayed as "Specified." On the other hand, "Electrocardiogram: exercise stress," which was derived as a recommended examination method, does not match the designated examination method, and is displayed as "Not Specified."
[0056] As illustrated in Figure 17, when the recommendation reason button 222 is clicked, the display processing unit 16 displays the auxiliary medical information 400 generated by the auxiliary medical information generation unit 14 on the display screen 200. The physician can judge the appropriateness of the recommended examination method 300 by referring to the auxiliary medical information 400. Also, as illustrated in Figure 18, by clicking the specify button 223 for recommended examination methods that are not specified as examination methods to be included in the examination order ("unspecified"), the physician can specify that examination method to be included in the examination order.
[0057] Figure 19 is a flowchart showing an example of the processing flow performed by the CPU 101 in this embodiment when it executes the information processing program 110. This flowchart is the same as the flowchart shown in Figure 13, but with steps S5A and S5B added, and step S6 changed to S6A. Below, only the steps that differ from the flowchart shown in Figure 13 will be described, and the description of the other steps will be omitted.
[0058] In step S5A, the CPU 101 functions as an examination order receiving unit 17 and receives the specification of the examination methods to be included in the examination order for the user (patient). In step S5B, the CPU 101 functions as a comparison unit 18 and compares the specified examination method received in step S5A with the recommended examination method derived in step S5 and derives the comparison result. Specifically, the CPU 101 determines which of the recommended examination methods do not match the specified examination method and which do. Note that the processing in step S5A may be performed in parallel with any of the processes in steps S1 to S5, or it may be performed before the processes in steps S1 to S5.
[0059] In step S6A, the CPU 101 functions as a display processing unit 16 and displays the recommended inspection method derived in step S5, along with the comparison results derived in step S5A, on the display screen 200 of the display 105. More specifically, it displays on the display screen 200 which of the recommended inspection methods match the specified inspection method and which do not.
[0060] As described above, the information processing device 10A according to this embodiment presents recommended inspection methods that match the specified inspection method and those that do not, in a distinguishable manner. In other words, it is possible to clearly indicate recommended inspection methods that are not included in the inspection order, thereby enhancing the effect of supporting the formulation of inspection methods.
[0061] [Third Embodiment] Figure 20 is a functional block diagram showing an example of the functional configuration of the information processing device 10B according to the third embodiment of the disclosed technology. The information processing device 10B according to this embodiment differs from the information processing device 10 according to the first embodiment (see Figure 4) in that it further includes an electronic medical record acquisition unit 19 and an integrated processing unit 20.
[0062] The electronic medical record acquisition unit 19 acquires the electronic medical record 51 in which medical information is recorded. For example, the electronic medical record acquisition unit 19 may acquire the electronic medical record 51 when its creation using the information processing device 10 is completed. Alternatively, the electronic medical record acquisition unit 19 may acquire the completed electronic medical record 51 stored in the medical data server 50.
[0063] In this embodiment, the recommended examination method derivation unit 15 derives a first recommended examination method based on auxiliary medical information generated by the auxiliary medical information generation unit 14. The recommended examination method derivation unit 15 also derives a second recommended examination method based on medical information recorded in the electronic medical record 51 acquired by the electronic medical record acquisition unit 19.
[0064] As shown in Figure 21, the recommended examination method derivation unit 15 derives first and second recommended examination methods using the recommended examination method derivation model 130 stored in the non-volatile memory 103. In this embodiment, the recommended examination method derivation model 130 derives a first recommended examination method based on auxiliary medical information including biological information and input information, and derives a second recommended examination method based on medical information recorded in the electronic medical record 51. The medical information recorded in the electronic medical record 51 includes subjective information obtained through interviews with medical information patients. That is, the recommended examination method derivation model 130 derives a second recommended examination method by taking into account information on subjective symptoms reported by the patient, onset time, present illness, past medical history, family history, and lifestyle history.
[0065] The integrated processing unit 20 performs an integration process to integrate the inspection method derived as the first recommended inspection method and the inspection method derived as the second recommended inspection method. For each of the inspection methods derived as the first and second recommended inspection methods, the integrated processing unit 20 assigns information indicating the degree of recommendation, depending on whether the inspection method is included in the first or second recommended inspection method. Specifically, the integrated processing unit 20 assigns information indicating a high degree of recommendation to inspection methods that are included in both the first and second recommended inspection methods. The integrated processing unit 20 also assigns information indicating a moderate degree of recommendation to inspection methods that are not included in the first recommended inspection method but are included in the second recommended inspection method. Furthermore, the integrated processing unit 20 assigns information indicating a low degree of recommendation to inspection methods that are included in the first recommended inspection method but not in the second recommended inspection method. The integrated processing unit 20 derives the recommended inspection method to which the information indicating the degree of recommendation has been assigned as the integration result.
[0066] Figure 22 shows an example of integration processing in the integration processing unit 20. In Figure 22, a recommendation level of 3 is assigned to "X-ray examination: standing chest" and "electrocardiogram: resting 12-lead," which are included in both the first and second recommended examination methods, a recommendation level of 1 is assigned to "echocardiography," which is included only in the first recommended examination method, and a recommendation level of 2 is assigned to "electrocardiogram: exercise stress," which is included only in the second recommended examination method. In this example, a numerical value (recommendation level) is used to indicate the degree of recommendation, with a recommendation level of 3 indicating a high degree of recommendation, a recommendation level of 2 indicating a moderate degree of recommendation, and a recommendation level of 1 indicating a low degree of recommendation.
[0067] The display processing unit 16 displays the recommended inspection method, which has been integrated by the integration processing unit 20, on the display 105. Figure 23 is a diagram showing an example of the display format of the integrated recommended inspection method. Figure 23 illustrates a recommended inspection method 300 which is an integrated version of the first or second recommended inspection method. Each inspection method derived as the first or second recommended inspection method is assigned a recommendation level as information indicating the degree of recommendation.
[0068] Figure 24 is a flowchart showing an example of the processing flow performed by the CPU 101 in this embodiment when it executes the information processing program 110. This flowchart is the same as the flowchart shown in Figure 13, but with the addition of steps S4A and S5D, the change of step S5 to step 5C, and the change of step S6 to step S6B. Below, only the steps that differ from the flowchart shown in Figure 13 will be described, and the description of the other steps will be omitted.
[0069] In step S4A, the CPU 101 functions as an electronic medical record acquisition unit 19 and acquires an electronic medical record 51 in which medical information is recorded.
[0070] In step S5C, the CPU 101 functions as a recommended examination method derivation unit 15, deriving a first recommended examination method based on the auxiliary medical information generated in step S4, and a second recommended examination method based on the medical information recorded in the electronic medical record 51 acquired in step S4A. The processing in step S4A may be performed in parallel with any of the processing in steps S1 to S4, or it may be performed before the processing in steps S1 to S4. Furthermore, the derivation of the second examination method in step S5C may be performed after the processing in step S4A and in parallel with the processing in steps S1 to S4.
[0071] In step S5D, the CPU 101 functions as the integration processing unit 20 and performs integration processing to combine the inspection method derived as the first recommended inspection method and the inspection method derived as the second recommended inspection method, and assigns information indicating the degree of recommendation to each integrated inspection method. Specifically, the CPU 101 assigns information indicating a high degree of recommendation to inspection methods that are included in both the first and second recommended inspection methods. The CPU 101 also assigns information indicating a moderate degree of recommendation to inspection methods that are not included in the first recommended inspection method but are included in the second recommended inspection method. Furthermore, the CPU 101 assigns information indicating a low degree of recommendation to inspection methods that are included in the first recommended inspection method but not in the second recommended inspection method. The integration processing unit 20 derives the recommended inspection methods to which the degree of recommendation information has been assigned as the integration result.
[0072] In step S6B, the CPU 101 functions as a display processing unit 16 and displays the integrated results derived in step S5D on the display screen 200 of the display 105. For example, when recording an examination order in the electronic medical record 51 using the information processing device 10, the CPU 101 may display the first recommended examination method and the second recommended examination method for the patient after the integrated processing has been performed.
[0073] As described above, the information processing device 10B according to this embodiment derives recommended testing methods based not only on biological information and input information, but also on medical information recorded in the electronic medical record 51. The medical information recorded in the electronic medical record 51 includes subjective information such as the patient's reported symptoms, onset date, current illness history, past medical history, family history, and lifestyle history. By including this medical information recorded in the electronic medical record 51 in the information used to derive recommended testing methods, it becomes possible to derive more appropriate recommended testing methods.
[0074] Furthermore, each of the recommended testing methods is accompanied by information indicating its degree of recommendation, which can be used as a reference when specifying which recommended testing methods to include in a test order.
[0075] In this embodiment, an example is shown in which the results of integrating the first recommended examination method and the second recommended examination method are displayed on the display screen 200, but the embodiment is not limited to this. As illustrated in Figure 25, the first recommended examination method 300A based on biological information and input information and the second recommended examination method 300B based on medical information recorded in the electronic medical record 51 may be displayed side by side on the display screen 200. In this case, the integration processing unit 20 of the information processing device 10B does not need any additional functionality.
[0076] The information processing devices 10, 10A, and 10B according to the first to third embodiments described above are examples of "information processing devices" relating to the technology of this disclosure. Furthermore, the "information processing device" relating to the technology of this disclosure may be a system including the configuration of the information processing device 10, 10A, or 10B and the medical data server 20. More specifically, the information processing device may be a system including a medical data server 20 that includes at least an electronic medical record 22 and the information processing device 10, 10A, or 10B. Also, in this embodiment, the acquisition of user information is performed periodically, once or twice a day or more, but is not limited to this. The user information acquisition unit 11 may, for example, start acquiring user information when the user visits the hospital, triggering access to user information in the electronic medical record or the user starts inputting into the electronic medical record.
[0077] Furthermore, in the first to third embodiments described above, electronic medical records were used as an example of medical document data in which medical information is recorded. However, recommended examination methods may also be derived based on medical information recorded in medical document data other than electronic medical records.
[0078] Furthermore, while the first to third embodiments described above illustrate a case in which the recommended examination method derivation unit 15 derives a recommended examination method based on auxiliary medical information derived by the auxiliary medical information derivation unit 14, the disclosed technology is not limited to this embodiment. The recommended examination method derivation unit 15 may also derive a recommended examination method based on analysis results derived by the analysis unit 13. Figure 26 is a functional block diagram showing an example of the functional configuration of the information processing device 10 in this case. The recommended examination method derivation unit 15 may, for example, derive a recommended examination method using a mathematical model such as a neural network that takes the analysis results from the analysis unit 13 (i.e., information extracted from biological information and input information) as input and outputs a recommended examination method.
[0079] In the above embodiment, for example, the hardware structure of the processing unit that performs various processes such as the user information acquisition unit 11, the recording processing unit 12, the analysis unit 13, the auxiliary medical information generation unit 14, the recommended examination method derivation unit 15, the display processing unit 16, the examination order reception unit 17, the comparison unit 18, the electronic medical record acquisition unit 19, and the integrated processing unit 20 can be any of the following types of processors. As mentioned above, these types of processors include CPUs and GPUs, which are general-purpose processors that execute software (programs) and function as various processing units, as well as Programmable Logic Devices (PLDs), which are processors whose circuit configuration can be changed after manufacturing, such as FPGAs, and dedicated electrical circuits, which are processors with circuit configurations specifically designed to perform specific processes, such as ASICs (Application Specific Integrated Circuits).
[0080] A single processing unit may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, multiple processing units may be composed of a single processor.
[0081] Examples of configuring multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software combine to form a single processor, which then functions as multiple processing units, as exemplified by client and server computers. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as exemplified by System on Chip (SoC). Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned processors.
[0082] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits, which are combinations of circuit elements such as semiconductor devices.
[0083] Furthermore, although the above embodiment describes an embodiment in which the information processing program 110 is pre-stored (installed) in the non-volatile memory 103, the embodiment is not limited to this. The information processing program 110 may be provided in the form of being recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus) memory. Alternatively, the information processing program 110 may be provided in the form of being downloaded from an external device via a network. In other words, the program (i.e., program product) described in this embodiment may be provided on a recording medium or distributed from an external computer. [Explanation of Symbols]
[0084] 1. Information Processing System 10, 10A, 10B Information Processing Devices 11. User Information Acquisition Unit 12 Recording Processing Unit 13 Analysis Department 14. Auxiliary Medical Information Generation Unit 15 Recommended Test Method Derivation Section 16 Display Processing Unit 17. Inspection Order Reception Department 18. Comparison Section 19 Electronic Medical Record Acquisition Department 20 Integrated Processing Unit 30 User terminal device 31. Biological Information Measurement Device 41, 42 Network 50 Medical Data Servers 51 Electronic medical records 101 CPU 102 RAM 103 Non-volatile memory 104 Input device 105 displays 106 Network Interfaces 107 Bus 110 Information Processing Programs 120 Supplementary Medical Information Generation Model 130 Recommended Test Method Derivation Model 140 Classifiers 200 display screen 220 input fields 221 Confirm button 222 Recommended Reason Button 223 Select button Recommended testing methods for 300, 300A, and 300B. 400 Supplementary Medical Information
Claims
1. An information processing device comprising at least one processor, The aforementioned processor, The system acquires at least one of the input information entered into a user terminal device used by the user and biometric information measured for the user. Based on at least one of the acquired input information and the biometric information, a recommended examination method for diagnosing the user's body is derived. We accept the specification of the inspection method to be included in the inspection order for the aforementioned user. Of the inspection methods derived as recommended inspection methods, those that match the inspection methods designated to be included in the inspection order and those that do not are presented in a way that allows for identification. The medical document data containing medical information obtained from the aforementioned user's examination is acquired. A first recommended testing method is derived based on at least one of the input information and the biological information. Based on the aforementioned medical information, a second recommended testing method was derived. For each of the testing methods derived as the first recommended testing method and the testing methods derived as the second recommended testing method, information indicating the degree of recommendation is provided, depending on which of the first and second recommended testing methods the testing method is derived from. Information processing device.
2. The aforementioned processor, When creating an inspection order for the aforementioned user, the recommended inspection method is presented. The information processing apparatus according to claim 1.
3. The processor generates supplementary medical information indicating the user's physical condition based on at least one of the input information and biometric information. Based on the aforementioned supplementary medical information, the recommended testing method is derived. The recommended testing methods are presented along with the aforementioned supplementary medical information. The information processing apparatus according to claim 1 or claim 2.
4. The processor includes the specified test method from among the recommended test methods derived as such in the test order. The information processing apparatus according to any one of claims 1 to 3.
5. The aforementioned input information includes search keywords entered into the search engine. The information processing apparatus according to any one of claims 1 to 4.
6. The aforementioned input information includes content that has been sent or transmitted to a specific or unspecified recipient. The information processing apparatus according to any one of claims 1 to 5.
7. The processor selects input information from the acquired input information that includes specific words related to the user's physical condition and records it on a recording medium, and derives the recommended examination method based on the input information recorded on the recording medium. The information processing apparatus according to any one of claims 1 to 6.
8. The processor acquires the biometric information measured by the wearable device worn by the user. The information processing apparatus according to any one of claims 1 to 7.
9. The processor displays a button to specify, among the recommended test methods derived, that do not match the test methods designated as to be included in the test order, as test methods to be included in the test order. An information processing apparatus according to any one of claims 1 to 8.
10. The processor performs control to display the reason for the recommendation for any test method that does not match the test method specified as to be included in the test order, among the test methods derived as recommended test methods. An information processing apparatus according to any one of claims 1 to 9.
11. The system acquires at least one of the input information entered into a user terminal device used by the user and biometric information measured for the user. Based on at least one of the acquired input information and the biometric information, a recommended examination method for diagnosing the user's body is derived. We accept the specification of the inspection method to be included in the inspection order for the aforementioned user. Of the inspection methods derived as recommended inspection methods, those that match the inspection methods designated to be included in the inspection order and those that do not are presented in a way that allows for identification. The medical document data containing medical information obtained from the aforementioned user's examination is acquired. A first recommended testing method is derived based on at least one of the input information and the biological information. Based on the aforementioned medical information, a second recommended testing method was derived. For each of the testing methods derived as the first recommended testing method and the testing methods derived as the second recommended testing method, information indicating the degree of recommendation is provided, depending on which of the first and second recommended testing methods the testing method is derived from. An information processing method in which processing is performed by at least one processor provided in an information processing device.
12. The system acquires at least one of the input information entered into a user terminal device used by the user and biometric information measured for the user. Based on at least one of the acquired input information and the biometric information, a recommended examination method for diagnosing the user's body is derived. We accept the specification of the inspection method to be included in the inspection order for the aforementioned user. Of the inspection methods derived as recommended inspection methods, those that match the inspection methods designated to be included in the inspection order and those that do not are presented in a way that allows for identification. The medical document data containing medical information obtained from the aforementioned user's examination is acquired. A first recommended testing method is derived based on at least one of the input information and the biological information. Based on the aforementioned medical information, a second recommended testing method was derived. For each of the testing methods derived as the first recommended testing method and the testing methods derived as the second recommended testing method, information indicating the degree of recommendation is provided, depending on which of the first and second recommended testing methods the testing method is derived from. An information processing program that causes at least one processor in an information processing device to perform a process.
Citation Information
Patent Citations
Examination item selection device, examination item selection method and examination item selection program
JP2008077603A
Medical support method and medical support system
JP2018005553A
Machine learning for medical screening recommendations based on patient activity information in social media
US20190026438A1
Medical information processing system, medical information processing device, and medical information processing method
WO2020036207A1
Animal patient inspection suggestion system, animal patient inspection suggestion terminal, and animal patient inspection suggestion program
WO2021191985A1