Medical support devices and programs

The medical support device addresses the challenge of understanding in online consultations by quantifying patient comprehension, enabling accurate medical care through scene-specific adjustments and informed consent.

JP7879398B2Active Publication Date: 2026-06-24CANON KK

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
CANON KK
Filing Date
2022-06-16
Publication Date
2026-06-24

AI Technical Summary

Technical Problem

The challenge of providing accurate and precise medical care is exacerbated by online medical examinations, where patients may feel they do not understand the explanations given during consultations due to difficulties in conveying medical terminology and the online format, leading to potential treatments proceeding without informed consent.

Method used

A medical support device equipped with a specification unit to identify scenes, a calculation unit to quantify patient understanding through video and audio analysis, and an output control unit to display or audio the comprehension level, allowing doctors to adjust their explanations accordingly.

Benefits of technology

Enables accurate and precise medical care by quantifying patient understanding during each examination scene, facilitating clearer communication and ensuring informed consent through repeated explanations based on comprehension levels.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007879398000001
    Figure 0007879398000001
  • Figure 0007879398000002
    Figure 0007879398000002
  • Figure 0007879398000003
    Figure 0007879398000003
Patent Text Reader

Abstract

To provide a precise and accurate medical care to a patient by converting the patient's degree of understanding for every scene of a medical examination into numbers and presenting them to a doctor.SOLUTION: A medical care support device according to an embodiment comprises a specification unit, a calculation unit, and an output control unit. The specification unit specifies each of a plurality of scenes constituting a medical examination. The calculation unit calculates, for every scene specified by the specification unit, a numerical value indicating a medical examinee's degree of understanding for the details of explanation made by a medical examiner who conducts the medical examination based on video data and voice data of the medical examinee who has the medical examination. The output control unit controls to output the numerical value indicating the degree of understanding calculated by the calculation unit.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a medical support device and a medical support method.

Background Art

[0002] There is a concept called informed consent, where a doctor such as a attending physician explains the patient's condition and future treatment plan during a medical examination to obtain understanding and consent. This concept originated in the United States as a "patient's right," and originally meant that patients have the right to hear information about their condition if they wish. However, in Japan, informed consent is translated as "explanation and consent," so people tend to think that providing an explanation is informed consent.

[0003] Although there was an opportunity for a medical examination where a doctor explains the patient's condition and treatment method, when treatment actually begins after the examination, the patient may feel that they do not understand the explanation given during the examination. As a result, it is possible that treatment may proceed without the patient's consent. One reason why patients may feel that they do not understand the explanation given during the examination is that in recent years, there have been many opportunities for online medical examinations, and due to the online nature, doctors may be anxious about whether the explanation given during the examination is being correctly conveyed to the patient. Furthermore, the words (medical terms) used in the explanation during the examination are difficult, and it is difficult to confirm whether the patient understands the explanation given during the examination. Also, the examination time is long, and it is difficult to understand what was said and when the patient did not understand (what was difficult), so it is difficult for doctors to explain to patients during the examination.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] One of the problems that the embodiments disclosed in this specification and drawings aim to solve is to provide accurate and precise medical care to patients by quantifying and presenting to physicians the patient's level of understanding for each scene during examination. However, the problems that the embodiments disclosed in this specification and drawings aim to solve are not limited to the above problem. Problems corresponding to each effect of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0006] The medical support device according to this embodiment comprises a specification unit, a calculation unit, and an output control unit. The specification unit identifies each of a plurality of scenes that constitute a medical examination. For each scene identified by the specification unit, the calculation unit calculates a numerical value indicating the patient's level of understanding of the explanation given by the examiner, based on the patient's video data and audio data. The output control unit outputs the numerical value indicating the level of understanding calculated by the calculation unit. [Brief explanation of the drawing]

[0007] [Figure 1] A block diagram showing an example configuration of a medical support system equipped with a medical support device according to the first embodiment. [Figure 2] A schematic diagram showing a medical support system equipped with a medical support device according to the first embodiment. [Figure 3] A block diagram showing an example configuration of a medical support device according to the first embodiment. [Figure 4] A flowchart illustrating an example of the operation of the medical support device according to the first embodiment. [Figure 5] A diagram showing an example of displaying the patient's level of understanding in a medical support device according to the first embodiment. [Figure 6] A diagram showing an example of displaying information related to the explanatory content of a scene with low comprehension in a medical support device according to the first embodiment. [Figure 7] A diagram showing an example of displaying the patient's level of understanding in a medical support device according to the first embodiment. [Figure 8] A diagram showing an example of displaying information related to the explanatory content of a scene with low comprehension in a medical support device according to the first embodiment. [Figure 9] A block diagram showing an example configuration of a medical support system equipped with a medical support device according to the second embodiment. [Figure 10] A block diagram showing an example configuration of a medical support device according to the second embodiment. [Figure 11] A schematic diagram showing a medical support system equipped with a medical support device according to the third embodiment. [Figure 12] A block diagram showing an example configuration of a medical support device according to the third embodiment. [Modes for carrying out the invention]

[0008] The embodiments of the medical support device and medical support method will be described in detail below with reference to the drawings.

[0009] (First Embodiment) Figure 1 shows a medical support system M1 equipped with a medical support device 1 according to the first embodiment. The medical support system M1 comprises a physician-side device 10 (an example of the medical support device 1) operated by the examiner (e.g., a doctor) conducting the online consultation, a patient-side device 20 operated by the patient receiving the online consultation (e.g., a patient), and a medical management device 30, and constitutes a video conferencing system or a web conferencing system. The physician-side device 10, the patient-side device 20, and the medical management device 30 can communicate with each other via a network N. When the medical support system M1 constitutes a video conferencing system, the medical management device 30 is a server, while when the medical support system M1 constitutes a web conferencing system, the medical management device 30 is a multi-unit control unit (MCU).

[0010] As shown in Figure 2, the physician-side device 10 is assumed to be able to communicate with the patient-side device 20 (shown in Figure 1) when conducting an online consultation. Physician D can conduct an online consultation with patient P while referring to the display 17 of the physician-side device 10.

[0011] Returning to the explanation of Figure 1, the physician's device 10 includes a processing circuit 11, memory 12, input interface 13, network interface 14, camera 15, microphone 16, display 17, and speaker 18. Note that some or all of the camera 15, microphone 16, and speaker 18 may be externally connected to a computer that includes the processing circuit 11 and memory 12.

[0012] The processing circuit 11 controls the overall operation of the physician-side device 10. The processing circuit 11 includes processors such as dedicated or general-purpose CPUs (Central Processing Units), MPUs (Micro Processor Units), or GPUs (Graphics Processing Units), as well as ASICs and programmable logic devices. Examples of programmable logic devices include simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs).

[0013] Furthermore, the processing circuit 11 may be composed of a single circuit or a combination of multiple independent processing circuit elements. In the latter case, memory may be provided individually for each processing circuit element, or a single memory may store programs corresponding to the functions of multiple processing circuit elements.

[0014] The memory 12 is composed of, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, hard disks, optical disks, etc. The memory 12 may also be composed of portable media such as USB (Universal Serial Bus) memories and DVDs (Digital Video Disk). The memory 12 stores various processing programs (including operating systems (OS) in addition to application programs) used in the processing circuit 11 and data necessary for program execution. Also, the OS can include a GUI (Graphic User Interface) that makes extensive use of graphics for displaying information on the display 17 to operators such as doctor D and allows basic operations to be performed by the input interface 13. The memory 12 is an example of a storage unit.

[0015] The input interface 13 includes an input device operable by an operator such as doctor D and an input circuit that inputs a signal from the input device. The input device is realized by a mouse, keyboard, trackball, switch, button, joystick, touch pad that performs an input operation by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, a voice input circuit, etc. When the input device receives an input operation from the operator, the input circuit generates an electrical signal corresponding to the input operation and outputs it to the processing circuit 44. The input interface 13 may be composed of a tablet terminal or the like capable of wireless communication with an external device. Note that the input interface 13 is an example of an input unit.

[0016] The network interface 14 is composed of connectors conforming to parallel connection specifications and serial connection specifications. The network interface 14 transmits and receives information to and from external devices on the network N.

[0017] The camera 15 uses a semiconductor sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), which converts light into an electrical signal, as an imaging device. The camera 15 has its field of view directed towards the doctor D, captures the video of the doctor D during online diagnosis under the control of the processing circuit 11, generates video data of the doctor D, and sends it to the processing circuit 11. The video data of the doctor D is sent to the patient-side device 20 via the network N and is output as a video from the display 27 of the patient-side device 20.

[0018] The microphone 16 is an acoustic device that converts sound into an electrical signal. The microphone 16 records the voice of the doctor D during online diagnosis under the control of the processing circuit 11, generates voice data of the doctor D, and sends it to the processing circuit 11. The voice data of the doctor D is sent to the patient-side device 20 via the network N and is output as the voice of the doctor D from the speaker 28 of the patient-side device 20. Also, the voice data of the doctor D is used for calculating the comprehension level of the patient P and calculating low-comprehension information, which will be described later.

[0019] The display 17 is a device that displays video data output from devices such as a computer. For example, the display 17 is a liquid crystal display, a CRT (Cathode Ray Tube) display, or an OLED (Organic Light Emitting Diode) display, etc. Also, the display 17 may be a desktop type or may be configured as a tablet terminal, etc. The display 17 displays various types of information under the control of the processing circuit 11. For example, the display 17 outputs a medical record generated by the processing circuit 11, a GUI for receiving various operations from the operator, etc. Also, the display 17 receives the video data of the patient P during online diagnosis via the network N under the control of the processing circuit 11 and outputs it as the video of the patient P. Note that the display 17 is an example of a display unit.

[0020] Speaker 18 is a device that converts electrical signals (electrical vibrations) into sound (physical vibrations). Alternatively, a device integrating the functions of speaker 18 and microphone 16 (for example, a headset or earphone microphone) may be used. Under the control of processing circuit 11, speaker 18 receives voice data from patient P during online consultations via network N and outputs it as patient P's voice.

[0021] On the other hand, the patient-side device 20 includes a processing circuit 21, memory 22, input interface 23, network interface 24, camera 25, microphone 26, display 27, and speaker 28. Some or all of the camera 25, microphone 26, and speaker 28 may be externally connected to a computer that includes the processing circuit 21 and memory 22. The configurations of elements 21-28 of the patient-side device 20 are equivalent to the configurations of elements 11-18 of the physician-side device 10, so their explanation is omitted.

[0022] Camera 25 is positioned so that its field of view is directed towards patient P. Under the control of the processing circuit 21, it captures video of patient P during the online consultation, generates video data of patient P, and sends it to the processing circuit 21. The video data of patient P is sent to the physician's device 10 via the network N and output as video of patient P on the display 17 of the physician's device 10. The video data of patient P is also used to calculate patient P's level of understanding and to calculate information about low levels of understanding, as described later.

[0023] Microphone 26, under the control of processing circuit 21, records the voice of patient P during online consultations, generates patient P's voice data, and sends it to processing circuit 21. Patient P's voice data is sent to physician-side device 10 via network N and output as patient P's voice from speaker 18 of physician-side device 10. Patient P's voice data is also used to calculate patient P's level of understanding and to calculate low-understanding information, as described later.

[0024] The display 27 receives video data of doctor D during online consultations via the network N under the control of the processing circuit 21, and outputs it as the video of doctor D.

[0025] The speaker 28 receives voice data from doctor D during online consultations via the network N under the control of the processing circuit 21, and outputs it as doctor D's voice.

[0026] Next, we will explain the functions of the physician's device 10 using Figure 3.

[0027] The processing circuit 11 executes a computer program stored in memory 12 or a non-transient recording medium such as memory within the processing circuit 11, thereby realizing the specific function F1, the calculation function F2, and the output control function F3, as shown in Figure 3. Note that all or part of functions F1 to F3 are not limited to being realized by the execution of a computer program; they may also be provided as circuits such as ASICs in the physician-side device 10.

[0028] Although opportunities for consultations where doctors, such as the attending physician, explain the patient's condition and treatment methods were provided, patients sometimes feel that they did not understand the explanation given during the consultation once treatment began. As a result, treatment may proceed without the patient's consent. One reason why patients feel they did not understand the explanation given during the consultation is that online consultations have become more common in recent years, and doctors may feel unsure whether the explanation given during the consultation is being correctly conveyed to the patient due to the online format. Furthermore, the language (medical terminology) used in the explanation during the consultation may be difficult, making it difficult to confirm whether the patient understood the explanation. In addition, consultation times are long, and it is difficult to determine what was not understood (or was difficult to understand), making it difficult for doctors to explain things to patients during consultations. To address these problems, the doctor-side device 10 is equipped with functions F1 to F3.

[0029] Specific function F1 includes the function of identifying each of the multiple scenes that make up a medical examination. A scene is an element after the examination time has been divided according to the flow of the examination, and includes, for example, "making a future outlook," "knowing the treatment record," "predicting the effectiveness of the treatment," "helping in the selection of treatment methods," and "comparing the medical condition." Specific function F1 identifies whether the scene is one of the following: "making a future outlook," "knowing the treatment record," "predicting the effectiveness of the treatment," "helping in the selection of treatment methods," or "comparing the medical condition."

[0030] The calculation function F2 includes a function that calculates a numerical value indicating the degree of patient P's understanding of the doctor D's explanation, based on the patient P's video data and audio data, for each scene identified by the identification function F1.

[0031] Here, the calculation function F2 calculates patient P's level of understanding as a numerical value based on patient P's video data. For example, the calculation function F2 inputs patient P's video data into a trained model that has been trained on video data (or image data) containing nodding movements of many patients and the corresponding "nodding movements" for each video data, thereby obtaining the number of "nodding movements" corresponding to patient P's video data. The calculation function F2 calculates a numerical value indicating individual understanding as the number of "nodding movements" × coefficient G1. Similarly, the calculation function F2 calculates a numerical value indicating individual understanding as the number of "head tilt movements" × coefficient G2, and calculates a numerical value indicating individual understanding as the number of "smiles (surprise, anger, sadness, or neutral face)" (or the duration of the smile movement [sec.]) × coefficient G3.

[0032] Furthermore, for example, calculation function F2 identifies "silent periods" where silence lasts longer than a threshold time, based on patient P's audio data and doctor D's audio data, and calculates a numerical value indicating individual comprehension as "silent period [sec.]" × coefficient H1. Similarly, calculation function F2 extracts "difficult words (e.g., medical terms)" from patient P's audio data using speech recognition technology, and calculates a numerical value indicating individual comprehension as the number of "difficult words" × coefficient H2. Then, calculation function F2 adds the numerical values ​​indicating individual comprehension calculated based on the video data and audio data, normalizes them as necessary, and calculates a numerical value indicating overall comprehension. Note that if patient P's audio data includes positive statements such as "I understand," the numerical value of patient P's comprehension for that scene may be set to 100% regardless of other video or audio.

[0033] Furthermore, calculation function F2 includes a function to calculate information regarding the explanatory content (referred to as "low comprehension scene information" in this specification and the drawings) for low comprehension scenes among multiple scenes, where the numerical value corresponds to a predetermined threshold or lower.

[0034] The output control function F3 includes a function to output a numerical value indicating the level of understanding calculated by the calculation function F2. Furthermore, for example, the output control function F3 may also include a function to output low-understanding scene information calculated by the calculation function F2. The output control function F3 can display the numerical value indicating the level of understanding and the low-understanding scene information as images on the display 17, or it can pronounce them as audio from the speaker 18. The low-understanding scene information includes items that may have caused the scene to be poorly understood, and includes at least one of the following: difficult words used in Doctor D's explanation in the low-understanding scene, explanation difficulty, explanation speed, and network speed (as shown in the lower part of Figure 6). The output control function F3 can also display medical records, etc., as images on the display 17.

[0035] Details of functions F1 to F3 will be described later using Figures 4 to 8.

[0036] Next, we will explain the clinical support method using Figure 4. In Figure 4, the symbols with numbers attached to "S" indicate each step in the flowchart.

[0037] First, the specific function F1 of the physician's device 10 establishes a connection with the patient's device 20 via the network N (step S1). Then, the online consultation with patient P is initiated.

[0038] The specific function F1 detects the start of a scene when patient P's online consultation begins (step S2). For example, the specific function F1 detects the start of a scene based on the doctor D's "start scene" operation via the input interface 13. Doctor D inputs the following operations as the start of a scene: "Start 'Prepare for future prospects'", "Start 'Learn about treatment results'", "Start 'Predict the effectiveness of treatment'", "Start 'Use this to help select a treatment method'", and "Start 'Compare the patient's condition'". Note that the specific function F1 is not limited to the doctor D's operation via the input interface 13; it may also detect the start of a scene based on the voice command "Let's begin discussing future prospects".

[0039] In the consultation scene "Preparing for the future outlook," Doctor D explains to Patient P how the abnormal area (e.g., a tumor) will progress (what the prognosis will be) if no treatment is given. In the consultation scene "Learning about treatment results," Doctor D explains to Patient P what treatments have been given to other patients with the same type of abnormal area and degree of progression (what the effects and prognosis were). In the consultation scene "Predicting the effectiveness of treatment," Doctor D explains to Patient P the effectiveness of a planned treatment and what side effects it may have in other patients with the same condition. In the consultation scene "Helping in the selection of a treatment method," Doctor D explains to Patient P which of the several treatment methods being considered would be effective for Patient P's current condition. In the consultation scene "Comparing the disease state," Doctor D explains to Patient P whether the treatment methods and subsequent progress of other people's abnormal areas are applicable to Patient P, based on the opportunity to hear about them.

[0040] The identification function F1 identifies the scene initiated in step S2 (or step S9) based on the video and audio data of patient P during the online consultation (step S3). Then, the calculation function F2 calculates a numerical value indicating patient P's level of understanding in order to quantify patient P's level of understanding in the scene identified in step S3 (step S4). The calculation function F2 continues to calculate the numerical value indicating patient P's level of understanding until the end of the scene, as long as the acquisition of video and audio data of patient P during the online consultation continues.

[0041] The specific function F1 determines whether or not it has detected the end of the scene started in step S2 (or step S9) (step S5). For example, the specific function F1 detects the end of a scene based on the doctor D's "end scene" operation via the input interface 13. Note that the specific function F1 is not limited to the doctor D's operation via the input interface 13, but may also detect the end of a scene based on the voice statement "I'm ending the discussion on future prospects." If the determination in step S5 is NO, that is, if it is determined that the end of a scene has not been detected, the specific function F1 identifies the scene started in step S2 (or step S9) (step S3).

[0042] If the determination in step S5 is YES, that is, if it is determined that the end of the scene has been detected, the output control function F3 outputs a numerical value indicating the patient P's level of understanding, which was calculated in step S4 (step S6). In step S6, the output control function F3 can display the numerical value indicating the patient P's level of understanding regarding the explanation of the scene as an image on the display 17 (see Figure 5), or it can be spoken aloud from the speaker 18.

[0043] Figure 5(A) is an example of a graph showing patient P's level of understanding after the completion of the first scene, "Future Outlook." Patient P's level of understanding for the "Future Outlook" scene is displayed as 100% because it exceeds the threshold (e.g., 50%). On the other hand, Figure 5(B) is an example of a graph showing patient P's level of understanding after the completion of the third scene, "Treatment Effects." Patient P's level of understanding for each of the three scenes, from the first to the third, "Treatment Effects," is displayed. Furthermore, the third scene, "Treatment Effects," where the level of understanding is below the threshold (e.g., 50%), may be highlighted. Note that the numerical value indicating patient P's level of understanding is not limited to being displayed as a graph; it may also be simply displayed as a list of numbers.

[0044] Returning to the explanation of Figure 4, the output control function F3 determines whether the numerical value indicating patient P's level of understanding, calculated in step S4, is below a predetermined threshold (or less than the threshold) (step S7). If the determination in step S7 is NO, that is, if the numerical value indicating patient P's level of understanding exceeds the predetermined threshold (or is above the threshold), the process proceeds to step S9.

[0045] On the other hand, if the judgment in step S7 is YES, that is, if the numerical value indicating patient P's level of understanding is below a predetermined threshold, the calculation function F2 calculates low-understanding scene information for that scene, and the output control function F3 outputs the low-understanding scene information for that scene (step S8). In step S8, the output control function F3 can display the low-understanding scene information as an image on the display 17, or it can be played as audio from the speaker 18.

[0046] Figure 6 is an example of a display where the upper section shows a graph of patient P's understanding level after the completion of the third scene, "Effects of Treatment," and the lower section shows a table of information about scenes with low comprehension. The information about scenes with low comprehension refers to information about the explanation content of scenes with low comprehension, and includes at least one of the following: difficult vocabulary, difficulty level of explanation, explanation speed, and internet connection speed. It is assumed that patient P's understanding level will be low if difficult vocabulary is used in the explanation during the examination scene. Note that it is sufficient for the difficult vocabulary itself to be displayed.

[0047] Explanation difficulty refers to the number (percentage) of times difficult words were used, and it is thought that the more difficult words used, the lower the patient P's comprehension. Explanation speed can be determined as the average value in the scene from the voice data of doctor D acquired by the microphone 16 of the doctor's device 10, and it is thought that the faster the explanation speed during the examination in the scene, the lower the patient P's comprehension. Connection speed includes both upload and download connection speeds, and it is thought that the slower the connection speed during the examination in the scene, the lower the patient P's comprehension.

[0048] In this way, the system can determine the patient P's level of understanding of the scenes during the examination and display information about scenes with low comprehension. The doctor then focuses on explaining the scenes with low comprehension to the patient P again. When doing so, the doctor D selects simpler words based on the cause and slows down the explanation speed when explaining again. The calculation function F2 then obtains a numerical value indicating the level of comprehension again. If the comprehension value has improved, the output control function F3 reflects this on the graph shown in Figure 5(B). This allows the doctor to reconfirm the patient P's level of understanding of the repeated explanations in the scenes with low comprehension and to confirm the improvement in the patient P's comprehension.

[0049] Returning to the explanation in Figure 4, Doctor D refers to the outputted low comprehension scene information and decides whether to repeat the explanation of the completed low comprehension scene or proceed to the explanation of the next scene. The specific function F1 determines whether it has detected the start of the completed low comprehension scene (repetition of the low comprehension scene) or the start of the next scene (proceeding to the next scene) (step S9). For example, the specific function F1 detects the start of a scene based on Doctor D's "start scene" operation via the input interface 13. If the determination in step S9 is YES, that is, if it is determined that the start of the completed low comprehension scene or the start of the next scene has been detected, the specific function F1 identifies the scene that was started in step S9 (step S3).

[0050] If the determination in step S9 is NO, meaning that the start of a completed low-understanding scene and the start of the next scene have not been detected, the specific function F1 disconnects the network N with the patient-side device 20 connected by step S1 (step S10). The physician then terminates the online consultation initiated by step S1.

[0051] In the flowchart shown in Figure 4, the patient P's level of understanding (illustrated in Figure 5) and information on scenes with low understanding (illustrated in Figure 6) are output each time a scene ends, but this is not the only case. For example, the output control function F3 may output the patient P's level of understanding for each scene (illustrated in Figure 7) and information on scenes with low understanding (illustrated in the lower part of Figure 8) after the explanation of all scenes has been completed. This allows physician D and other related parties (such as physician D's superiors and colleagues) to review the examination itself and check the information on scenes with low understanding within that examination.

[0052] As described above, according to the physician-side device 10, which is an example of the medical support device 1 according to the first embodiment, the patient P's level of understanding for each scene of the online consultation is quantified and presented to the physician D at the end of each scene. This allows the physician D to repeatedly provide explanations according to the patient P's level of understanding and to conduct online consultations with caution for subsequent patients (or subsequent consultations). As a result, the physician-side device 10 can provide accurate and precise medical care to patient P.

[0053] Furthermore, by focusing only on scenes with low comprehension, it is possible to determine that the scenes with high comprehension likely conveyed what Dr. D wanted to explain, thus reducing Dr. D's explanation time. Additionally, by recording the interaction between Dr. D and patient P as video and audio, this recording can be used as information for reaching an agreement with patient P during subsequent consultations.

[0054] (Second Embodiment) The explanations in Figures 1 to 8 describe the case where the medical support device 1 is the physician-side device 10 of the medical support system M1, but it is not limited to this case. For example, the medical support device 1 may be a medical management device 30 that is connected to the network N in a communicative manner. The medical management device 30 means a device that is neither the physician-side device 10 nor the patient-side device 20. This case will be explained using Figures 9 to 10.

[0055] Figure 9 shows a medical support system M2 equipped with a medical support device 1 according to the second embodiment. The medical support system M2 comprises a physician-side device 10 operated by a physician conducting an online consultation, a patient-side device 20 operated by a patient receiving an online consultation, and a medical management device 30 (an example of medical support device 1), and constitutes a video conferencing system or a web conferencing system. The physician-side device 10, the patient-side device 20, and the medical management device 30 can communicate with each other via a network N. Note that the configuration of the physician-side device 10 and the patient-side device 20 has been explained using Figure 1, so the explanation is omitted here.

[0056] When the medical support system M2 constitutes a video conferencing system, the medical management device 30 is a server, whereas when the medical support system M2 constitutes a web conferencing system, the medical management device 30 is a multi-point control unit (MCU). As shown in Figure 9, the medical management device 30 comprises a processing circuit 31, a memory 32, and a network interface 34. Note that the configurations of elements 31, 32, and 34 of the medical management device 30 are equivalent to the configurations of elements 11, 12, and 14 of the physician-side device 10 described using Figure 1, so their explanation is omitted.

[0057] The processing circuit 31 executes a computer program stored in memory 32 or a non-transient recording medium such as memory within the processing circuit 31, thereby realizing the calculation function F2, the specific function F4, and the output control function F5, as shown in Figure 10.

[0058] Specific function F4 is equivalent to specific function F1 shown in Figure 3. However, it differs from specific function F1 in that it acquires patient P's video and audio data from the patient-side device 20 via network N, and also acquires physician D's audio data from the physician-side device 10 via network N.

[0059] Output control function F5 is equivalent to output control function F3 shown in Figure 3. However, it differs from output control function F3 in that it outputs the patient P's level of understanding for each scene, calculated by calculation function F2, and low-understanding scene information from the physician's device 10 via network N.

[0060] The functions and operations of the medical management device 30, F2, F4, and F5, are equivalent to those explained using Figures 3 and 4, so their explanation will be omitted.

[0061] As described above, according to the medical management device 30, which is an example of the medical support device 1 according to the second embodiment, the patient P's level of understanding for each scene of the online consultation is quantified and presented to the doctor D at the end of each scene. This allows the doctor D to repeatedly provide explanations according to the patient P's level of understanding and to conduct online consultations with caution for subsequent patients (or subsequent consultations). As a result, the medical management device 30 can provide accurate and precise medical care to the patient P.

[0062] (Third embodiment) Figures 1 to 10 illustrate the operation during online consultations, but this is not limited to that scenario. Figures 11 to 12 illustrate the operation during in-person consultations conducted at medical institutions where the medical support device 1 is installed.

[0063] As shown in Figure 11, the physician-side device 10A (an example of the medical support device 1) according to the third embodiment is designed for situations where a face-to-face examination is conducted while facing the patient P. The physician D can conduct an online examination of patient P while referring to the display 17A of the physician-side device 10A.

[0064] Figure 12 shows a physician-side device 10A operated by the examining physician according to the third embodiment. It is not essential that the physician-side device 10A is network-connectable (has a network interface).

[0065] The physician-side device 10A comprises a processing circuit 11A, memory 12A, input interface 13A, camera 15A, microphone 16A, and display 17A. The configurations of elements 11A-13A, 15A, and 16A of the physician-side device 10A are equivalent to the configurations of elements 11-13, 15, and 16 of the physician-side device 10 described using Figure 1, so their explanation is omitted.

[0066] Camera 15A is positioned so that its field of view is directed towards patient P. Under the control of processing circuit 11A, it captures video of patient P during face-to-face examinations, generates video data of patient P, and sends it to processing circuit 11A. The video data of patient P is also used to calculate patient P's level of comprehension and to calculate information about low levels of comprehension.

[0067] Microphone 16A, under the control of processing circuit 11A, records the voices of doctor D and patient P during face-to-face consultations, generates voice data of doctor D and patient P, and sends it to processing circuit 11A. The voice data includes the voices of doctor D and patient P, but they can be separated based on differences in voice frequency. In addition, patient P's voice data is used to calculate patient P's level of comprehension and to calculate information about low level of comprehension.

[0068] The display 17A outputs medical records generated by the processing circuit 11A, as well as a GUI for receiving various operations from the operator.

[0069] The processing circuit 11A executes a computer program stored in memory 12A or a non-transient recording medium such as memory within the processing circuit 11A, thereby realizing a specific function F1, a calculation function F2, and an output control function F3, as shown in Figure 12.

[0070] The functions and operation of the physician-side device 10A (F1-F3) are equivalent to those explained using Figures 3 and 4, so their explanation will be omitted. In the case of the physician-side device 10A for face-to-face examinations, the line speed is not included in the low-comprehension information.

[0071] As described above, according to the physician-side device 10A, which is an example of the medical support device 1 according to the third embodiment, the patient P's level of understanding for each scene of face-to-face examination is quantified and presented to the physician D at the end of each scene. This allows the physician D to repeatedly provide explanations according to the patient P's level of understanding and to conduct face-to-face examinations with care for subsequent patients (or subsequent examinations). As a result, the physician-side device 10A can provide accurate and precise medical care to patient P.

[0072] Note that specific functions F1 and F4 are examples of specific units. Calculation function F2 is an example of a calculation unit. Output control functions F3 and F5 are examples of output control units.

[0073] According to at least one embodiment described above, by quantifying the patient's level of understanding for each scene during the examination and presenting this to the doctor, it is possible to provide patients with accurate and precise medical care.

[0074] While several embodiments have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be implemented in a variety of other forms, and various omissions, substitutions, modifications, and combinations of embodiments are possible without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0075] 1...Medical support equipment 10, 10A…Physician's device 11,11A…Processing circuit 17,17A…Display 20…Patient-side device 30…Clinical management device 31…Processing circuit F1, F4...Specific functions F2...Calculation function F3, F5... Output control function M1, M2... Medical support system

Claims

1. A specific unit that identifies each of the multiple scenes that make up the examination, For each of the identified scenes, a calculation unit calculates a numerical value indicating the patient's level of understanding of the explanation given by the examiner, based on the video and audio data of the patient receiving the examination. An output control unit that outputs a numerical value indicating the calculated level of understanding, A medical support device equipped with this device.

2. The output control unit, At the end of each of the aforementioned scenes, the calculated numerical value indicating the level of understanding is output. The medical support device according to claim 1.

3. The output control unit, After all of the aforementioned scenes have finished, the system outputs a numerical value indicating the calculated level of understanding. The medical support device according to claim 1.

4. The calculation unit described above, For the scenes among the aforementioned multiple scenes where the numerical value corresponds to a low level of understanding below a predetermined threshold, information regarding the explanatory content is calculated. The output control unit, Further outputting information regarding the calculated explanatory content, A medical support device according to any one of claims 1 to 3.

5. The output control unit, Information including items that may be the cause of the low level of understanding in the scene is output as information related to the explanation content. The medical support device according to claim 4.

6. The output control unit, For the aforementioned low-comprehension scene, output at least one of the following: difficult words included in the explanation, the difficulty level of the explanation, the speed of the explanation, and the connection speed. The medical support device according to claim 5.

7. A computer, A specific unit that identifies each of the multiple scenes that make up the examination, For each of the identified scenes, a calculation unit calculates a numerical value indicating the patient's level of understanding of the explanation given by the examiner, based on the video and audio data of the patient receiving the examination. It functions as an output control unit that outputs a numerical value indicating the calculated level of understanding. program.