Medical information processing apparatus, system, and method

Abstract

To propose an appropriate action taken according to an individual situation.SOLUTION: A medical information processing apparatus according to an embodiment comprises an acquisition unit, an extraction unit, an estimation unit, and a presentation unit. The acquisition unit acquires clinical information and vital data of a subject. The extraction unit extracts disease candidates on the basis of the vital data. The estimation unit estimates the degree of a disease state corresponding to each of the disease candidates on the basis of the clinical information of the subject and medical knowledge related to each of the disease candidates. The presentation unit presents a recommended behavior corresponding to the disease candidate on the basis of the degree of the disease state.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing device, a system, and a method. [Background technology]

[0002] Nowadays, wearable devices make it possible to obtain various vital data in daily life. Such a large amount of vital data is collected and managed for each individual and used for personal health management. For example, systems that issue alerts when the vital data collected on a daily basis meet certain conditions are known. In addition, services that allow individuals to inquire when they notice that they are not feeling well and online medical care services are becoming more common. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-009589 A [Patent Document 2] JP 2013-148996 A Summary of the Invention [Problem to be solved by the invention]

[0004] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to propose an appropriate response according to the individual's condition. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0005] A medical information processing device according to an embodiment includes an acquisition unit, an extraction unit, an estimation unit, and a presentation unit. The acquisition unit acquires clinical information and vital data of a subject. The extraction unit extracts disease candidates based on the vital data. The estimation unit estimates a pathological condition level corresponding to each of the disease candidates based on the clinical information of the subject and medical knowledge related to each of the disease candidates. The presentation unit presents a recommended behavior corresponding to the disease candidate based on the pathological condition level. [Brief description of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram showing a medical information processing system according to the first embodiment. [Diagram 2] FIG. 2 is a flowchart illustrating an example of a processing procedure of the medical image processing apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart illustrating an example of a procedure of a recommended action determination process according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining an example of a candidate disease estimation process according to the first embodiment. [Figure 5A] FIG. 5A is a diagram illustrating an example of an attribute distribution according to the first embodiment. [Figure 5B] FIG. 5B is a diagram for explaining an example of grading of attributes according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of an attribute distribution of a patient group according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of an attribute distribution of a patient group according to the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, embodiments of a medical information processing device, a system, and a method will be described in detail with reference to the drawings. Note that the medical information processing device, a system, and a method according to the present application are not limited to the embodiments described below.

[0008] (First embodiment) FIG. 1 is a block diagram showing a medical information processing system 1 according to the first embodiment. For example, as shown in FIG. 1, the medical information processing system 1 according to this embodiment includes a medical information processing device 100 and a user side device 200, and each device is communicably connected via a network 300. In the medical information processing system 1 shown in FIG. 1, only a single user side device 200 is shown, but in reality, multiple user side devices 200 are connected to the network 300. In addition, in the medical information processing system 1 shown in FIG. 1, only the medical information processing device 100 and the user side device 200 are shown, but in reality, various other devices and systems are connected to the network 300. For example, in the medical information processing system 1, a data storage device that stores information such as clinical information of subjects and various guidelines is connected to the network 300.

[0009] Here, a data storage device (not shown) receives clinical information of the subject (such as DNA information, medical history, and family disease information) from various devices and systems connected to the network 300, and stores the received clinical information of the subject in a memory circuit within the device. The data storage device also stores data of the information, such as guidelines and literature, in a memory circuit within the device in response to an operation for storing the information. For example, the data storage device is realized by a computer device such as a personal computer (PC), a workstation, or a server.

[0010] The user side device 200 has a vital data acquisition device 21 and a terminal device 22, and the vital data acquisition device 21 and the terminal device 22 are connected to each other so as to be able to communicate with each other via short-range wireless communication or the like.

[0011] The vital data acquisition device 21 has various sensors, acquires vital data of the subject, and transmits it to the terminal device 22. For example, the vital data acquisition device 21 acquires vital data such as sleep stage, snoring, heart rate, pulse, blood pressure, electrocardiogram, respiratory state, exercise progress (number of steps, time, etc.), body fat percentage, skeletal muscle, blood vessel information, degree of arteriosclerosis, etc., and transmits it to the terminal device 22. The vital data acquisition device 21 is realized by, for example, a wearable device. Note that wearable devices include, for example, wristwatch type, eyeglass type, ring type, shoe type, pocket type, pendant type, etc.

[0012] The terminal device 22 is a device operated by the subject. The terminal device 22 transmits the vital data of the subject received from the vital data acquiring device 21 to the medical information processing device 100. The terminal device 22 also displays various information received from the medical information processing device 100 on the display of the own device, and accepts various operations via the input interface of the own device. For example, the terminal device 22 accepts input operations such as clinical information of the subject, and transmits it to a data storage device (not shown) or the medical information processing device 100. The terminal device 22 is realized by, for example, a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a mobile phone, or the like.

[0013] In this embodiment, a case will be described in which the terminal device 22 transmits the vital data acquired by the vital data acquisition device 21 to the medical information processing device 100, but the embodiment is not limited to this. For example, the vital data acquisition device 21 may have the same function as the terminal device 22 and communicate with the medical information processing device 100.

[0014] The medical information processing device 100 is a device operated by an administrator of the medical information processing system 1, and executes various processes for proposing appropriate measures according to the individual's condition. Specifically, the medical information processing device 100 extracts disease candidates from vital data in daily life before the subject visits a medical institution and proposes measures according to the subject. As a result, the medical information processing device 100 allows subjects who are unaware of their symptoms to become aware of the symptoms early, and enables them to seek medical treatment and see changes in their behavior.

[0015] As mentioned above, wearable devices currently allow the acquisition of various vital signs in daily life, and a digital twin environment is being created in which such data can be accumulated and managed to restore one's own condition from digital information. However, in such an environment, although individual pieces of information are managed, there is no checking of the interrelationships between multiple pieces of information or of the individual as a whole, making it difficult to identify diseases that should be prioritized from the accumulated and managed information.

[0016] In addition, if the subject himself / herself is not aware of or does not notice any changes in his / her physical condition, he / she may not use services to inquire about his / her physical condition or online medical services, which may result in the disease progressing. Even if he / she notices a change in his / her physical condition, he / she may be reluctant to respond late due to the time required to search for and consider medical institutions to visit and make reservations, which may result in the disease progressing. On the other hand, medical institutions may not be able to handle frequent inquiries about asymptomatic or mild symptoms.

[0017] Therefore, the medical information processing device 100 according to this embodiment monitors vital data of a subject acquired in daily life, and if any abnormality is detected during the monitoring that may indicate the onset of a disease or require treatment, the medical information processing device 100 performs control so as to recommend an appropriate prescription for the subject.

[0018] 1, the medical information processing device 100 according to this embodiment includes a communication interface 11, an input interface 12, a display 13, a memory circuitry 14, and a processing circuitry 15. For example, the medical information processing device 100 is realized by a computer device such as a personal computer (PC), a workstation, or a server.

[0019] The communication interface 11 controls the transmission and communication of various data transmitted and received between the medical information processing device 100 and each device connected via the network 300. Specifically, the communication interface 11 is connected to the processing circuitry 15, and transmits data received from each device on the network 300 to the processing circuitry 15, or transmits data received from the processing circuitry 15 to each device on the network 300. For example, the communication interface 11 is realized by a network card, a network adapter, a NIC (Network Interface Controller), or the like.

[0020] The input interface 12 accepts input operations of various instructions and various information from an operator. Specifically, the input interface 12 is connected to the processing circuit 15, converts the input operation received from the operator into an electric signal, and transmits it to the processing circuit 15. For example, the input interface 12 is realized by a trackball, a switch button, a mouse, a keyboard, a touch pad that performs an input operation by touching the operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input interface using an optical sensor, a voice input interface, and the like. Note that in this specification, the input interface 12 is not limited to only those that have physical operation parts such as a mouse and a keyboard. For example, an electric signal processing circuit that receives an electric signal corresponding to an input operation from an external input device provided separately from the device and transmits the electric signal to a control circuit is also included as an example of the input interface 12.

[0021] The display 13 displays various information and data. Specifically, the display 13 is connected to the processing circuit 15 and displays various information and data received from the processing circuit 15. For example, the display 13 is realized by a liquid crystal display, a CRT (Cathode Ray Tube) display, a touch panel, or the like.

[0022] The memory circuitry 14 stores various data and various programs. Specifically, the memory circuitry 14 is connected to the processing circuitry 15, and stores data received from the processing circuitry 15, or reads out stored data and transmits it to the processing circuitry 15. For example, the memory circuitry 14 is realized by a semiconductor memory element such as a Read Only Memory (ROM), a Random Access Memory (RAM), or a flash memory, a hard disk, an optical disk, or the like. The memory circuitry 14 may be realized by a cloud computer connected to the medical information processing device 100 via a network 300.

[0023] The processing circuitry 15 controls the entire medical information processing device 100. Specifically, the processing circuitry 15 executes various processes for proposing appropriate measures according to the individual's condition. For example, the processing circuitry 15 controls data exchange with devices on the network 300, storage of data in the memory circuitry 14, and various processes using data.

[0024] For example, as shown in FIG. 1, in this embodiment, the processing circuitry 15 of the medical image processing device 100 executes an acquisition function 151, an extraction function 152, an estimation function 153, and a presentation function 154. Here, the acquisition function 151 is an example of an acquisition unit. The extraction function 152 is an example of an extraction unit. The estimation function 153 is an example of an estimation unit. The presentation function 154 is an example of a presentation unit.

[0025] The acquisition function 151 acquires clinical information and vital data of the subject. Specifically, the acquisition function 151 acquires vital data acquired on a daily basis by the vital data acquisition device 21 from the terminal device 22. The acquisition function 151 also acquires clinical information of the subject from the user side device 200 or a data storage device (not shown). The processing by the acquisition function 151 will be described in detail later.

[0026] The extraction function 152 extracts disease candidates based on vital data. Specifically, the extraction function 152 extracts disease candidates based on the relationship between the subject's activity state and biological information included in the vital data. For example, the extraction function 152 estimates the subject's condition based on a comparison between the exercise intensity of the subject during exercise and the respiratory change or heart rate change during the exercise, and extracts disease candidates based on the estimation result. Here, the extraction function 152 performs a comparison over time between the exercise intensity of the subject during exercise and the respiratory change or heart rate change during the exercise, and estimates the subject's condition based on the comparison over time. The processing by the extraction function 152 will be described in detail later.

[0027] The estimation function 153 estimates the degree of pathology corresponding to each of the disease candidates based on the subject's clinical information and medical knowledge regarding each of the disease candidates. Specifically, the estimation function 153 estimates the degree of pathology of the disease corresponding to each of the disease candidates based on the subject's clinical information, medical knowledge, and further the subject's vital data. The processing by the estimation function 153 will be described in detail later.

[0028] The presentation function 154 presents a recommended behavior corresponding to a disease candidate based on the degree of the pathological condition. Specifically, the presentation function 154 presents behaviors that are highly effective for the subject (e.g., no special behavior, lifestyle improvement, examination, treatment policy, etc.) as recommended behaviors corresponding to the disease candidate. For example, the presentation function 154 transmits the recommended behavior to the terminal device 22, thereby causing the display of the terminal device 22 to present the recommended behavior. Note that the processing by the presentation function 154 will be described in detail later.

[0029] The above-mentioned processing circuitry 15 is realized by, for example, a processor. In this case, each of the above-mentioned processing functions is stored in the storage circuitry 14 in the form of a program executable by a computer. Then, the processing circuitry 15 realizes a function corresponding to each program by reading and executing each program stored in the storage circuitry 14. In other words, the processing circuitry 15 has each of the processing functions shown in FIG. 1 in a state in which each program is read.

[0030] The processing circuitry 15 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize each processing function. Each processing function of the processing circuitry 15 may be appropriately distributed or integrated and realized in a single or multiple processing circuits. Each processing function of the processing circuitry 15 may be realized by a mixture of hardware such as a circuit and software. Here, an example in which a program corresponding to each processing function is stored in a single storage circuitry 14 has been described, but the embodiment is not limited to this. For example, a configuration in which a program corresponding to each processing function is distributed and stored in a plurality of storage circuits, and the processing circuitry 15 reads out and executes each program from each storage circuit. A part of each processing function of the processing circuitry 15 may be realized by a cloud computer connected to the medical information processing device 100 via a network 300.

[0031] Next, the procedure of processing by the medical information processing device 100 will be described with reference to Fig. 2, and then each process will be described in detail. Fig. 2 is a flowchart showing an example of the processing procedure of the medical information processing device 100 according to the first embodiment.

[0032] 2, in this embodiment, the acquisition function 151 acquires vital data of a subject (step S101). Specifically, the acquisition function 151 acquires vital data of a user, which is acquired on a daily basis, from a user-side device 200 owned by the user of the information presentation service by the medical information processing device 100. This process is realized, for example, by the processing circuitry 15 calling up a program corresponding to the acquisition function 151 from the storage circuitry 14 and executing it.

[0033] Next, the extraction function 152 converts the vital data into disease-related factors (step S102) and accumulates changes in the disease-related factors over time (step S103). That is, the extraction function 152 converts vital data at multiple points in time acquired from the subject over time into disease-related factors, respectively, and stores them in the memory circuitry 14. The disease-related factors include symptoms and indices (vital data itself, indices derived from vital data, etc.) associated with diseases based on various guidelines and papers.

[0034] Furthermore, the extraction function 152 estimates the state of the subject based on the accumulated disease-related factors (changes in disease-related factors over time) (step S104), and extracts disease candidates based on the estimation result (step S105). These processes are realized, for example, by the processing circuitry 15 calling up a program corresponding to the extraction function 152 from the storage circuitry 14 and executing it.

[0035] Next, the estimation function 153 estimates the degree of the extracted disease candidate (step S106). Specifically, the estimation function 153 estimates the state of the subject with respect to the disease candidate by comparing information on a patient group diagnosed with the disease candidate with information on the subject. For example, the estimation function 153 estimates the state of the subject with respect to the disease extracted as the disease candidate. This process is realized, for example, by the processing circuitry 15 calling up a program corresponding to the estimation function 153 from the storage circuitry 14 and executing it.

[0036] Next, the estimation function 153 determines a recommended action according to the degree of the disease candidate, and the presentation function 154 controls the terminal device 22 to present the determined recommended action (step S107). This process is realized, for example, by the processing circuitry 15 calling up and executing a program corresponding to the estimation function 153 and the presentation function 154 from the storage circuitry 14.

[0037] Here, the estimation function 153 determines various recommended actions according to the degree of the disease candidate, and when it is determined that treatment is necessary for the subject based on the degree of the disease candidate, it can estimate the treatment effect. For example, the estimation function 153 can estimate the effect of a drug predicted to be prescribed for the subject. Hereinafter, the determination of the recommended action by the estimation function 153 will be described with reference to FIG. 3. FIG. 3 is a flowchart showing an example of a process of determining a recommended action according to the first embodiment. Note that FIG. 3 shows a process in the case where a state of shortness of breath is used as a disease-related factor.

[0038] For example, in the medical information processing device 100, the acquisition function 151 monitors vital data (step S201) as shown in Fig. 3. This process corresponds to step S101 in Fig. 2.

[0039] Next, the extraction function 152 calculates the state of shortness of breath from the state of exercise and changes in heart rate and respiratory rate contained in the monitored vital data (step S202), and extracts candidate diseases based on the state of shortness of breath (step S203).

[0040] Next, the estimation function 153 estimates the degree of the disease candidate (step S204). Note that this process corresponds to step S106 in FIG.

[0041] Then, the estimation function 153 determines a recommended action according to the degree of estimation, and the presentation function 154 causes the terminal device 22 to present the recommended action. This process corresponds to step S107 in FIG.

[0042] For example, when the estimated degree is mild ("mild" in the figure), the estimation function 153 determines only notification of the degree as the recommended action for the subject. The presentation function 154 causes the terminal device 22 to present the degree of the disease candidate estimated by the estimation function 153 (step S205).

[0043] Furthermore, for example, when the degree of estimation is medium ("Medium" in the figure), the estimation function 153 determines an examination as a recommended action for the subject. In this case, the estimation function 153 extracts an examination according to the disease candidate. The presentation function 154 causes the terminal device 22 to present an examination plan proposing to perform the examination extracted by the estimation function 153 (step S206).

[0044] Also, for example, if the estimated degree is severe ("Severe" in the figure), the estimation function 153 determines administration of a drug as a recommended action for the subject (step S207). In this case, the estimation function 153 next acquires statistical information regarding the effect of the drug to be prescribed for the disease candidate (step S208), and evaluates the effect of the drug on the subject (step S209). The presentation function 154 causes the terminal device 22 to present candidate drugs suitable for the subject based on the evaluation by the estimation function 153 (step S210).

[0045] Through such processing by the medical information processing device 100, vital data is monitored in a state where the subject is not aware that he or she does not actively transmit information himself or herself, and some kind of presentation can awaken the subject and allow the subject to take the next action. Here, since the medical information processing device 100 according to this embodiment can present various information according to the degree, the subject can take appropriate action at the present time (changing lifestyle habits, undergoing simple examinations, visiting a hospital, etc.) based on the information.

[0046] Below, a detailed description will be given of each process executed by the medical information processing device 100. Note that, below, a process in which a state of shortness of breath is used as a disease-related factor will be described as an example, but the embodiment is not limited thereto, and any disease-related factor that can be obtained from vital data may be used.

[0047] (Information Acquisition Processing) 2, the acquisition function 151 acquires vital data of the subject over time. Specifically, the acquisition function 151 inquires of the information presentation service by the medical information processing device 100, and acquires the vital data over time from the user side device 200 of the subject (user) who has approved the provision of his / her information. For example, the acquisition function 151 receives the vital data from the terminal device 22 every time the vital data is acquired by the vital data acquisition device 21 (wearable device) worn by the subject. The acquisition function 151 stores the acquired vital data in the memory circuitry 14.

[0048] When a state of shortness of breath is used as a disease-related factor, for example, the acquisition function 151 acquires vital data including the state of exercise, heart rate, respiratory rate, and electrocardiogram. For example, by recording the heart rate and respiratory rate in a certain activity state for a certain period of time or more, it is possible to measure trends during that period. Therefore, it is possible to observe that the heart rate suddenly increases even when the activity level is not high during daily movements, or that the heart rate fluctuation increases and the respiratory rate increases and the person stops walking during gentle exercise such as a walk.

[0049] Moreover, the acquisition function 151 acquires clinical information of a subject (user) who has applied for an information presentation service by the medical information processing device 100 and approved the provision of his / her information. Specifically, the acquisition function 151 acquires clinical information including DNA information of the subject, medical history, and disease information of family members. For example, the acquisition function 151 acquires clinical information from information input when applying for an information presentation service by the medical information processing device 100. In this case, the medical information processing device 100 requests input of clinical information required when applying for the information presentation service, and the acquisition function 151 acquires the clinical information from the input information and stores it in the memory circuitry 14.

[0050] Also, for example, the acquisition function 151 acquires clinical information from a data storage device connected to the network 300. As an example, the acquisition function 151 acquires DNA information, detailed information on medical history, and the like from the data storage device and stores them in the memory circuitry 14.

[0051] (Conversion to disease-related factors) 2, the extraction function 152 converts the vital data acquired by the acquisition function 151 into disease-related factors. For example, the extraction function 152 calculates a state of shortness of breath as a disease-related factor from vital data including an exercise state, a heart rate, and a respiratory rate.

[0052] In this case, first, a reference condition is set. Specifically, the heart rate, respiratory rate, oxygen saturation, etc. at rest are set as reference conditions, and the amount of change during exercise and the time required to return from the changed state to the reference state are set as conditions. In other words, a reference condition for comparison with vital data acquired from the subject is set.

[0053] Here, the value of the reference state (resting state) may be set statistically from, for example, the age, height, and weight of the subject, or may be set from the average value of the state of the subject at rest. The value of the state during exercise may be set statistically from, for example, the age, height, and weight of the subject, or may be set from the value when the subject performs light exercise (for example, the subject continuously goes up and down stairs).

[0054] The heart rate and respiratory rate during exercise can also be calculated using the resting state. For example, it is known that the heart rate during exercise according to the exercise intensity is calculated by the following formula using the resting heart rate:

[0055] Heart rate during exercise = (A-age-resting heart rate) x exercise intensity + resting heart rate A=220

[0056] The exercise respiration rate according to the exercise intensity can be calculated by the following formula using the resting respiration rate: Note that "B" in the formula is set to a value set at the time of statistics, for example, B=10.

[0057] Exercise breathing rate = (B - resting breathing rate) x exercise intensity + resting breathing rate

[0058] For example, since it is said that an exercise intensity that allows relaxation is "50%," the exercise intensity may be set to "50%," and the exercise heart rate and exercise respiration rate may be calculated from the resting heart rate and resting respiration rate using the above formula.

[0059] In addition, by using the above formula, the heart rate and respiratory rate during exercise can be set according to the exercise intensity. For example, the exercise intensity is divided into 10 levels in increments of 10%, namely, "1: 1-10% (sleep, etc.), 2: 10-20% (meal, etc.), 3: 20-30 (bathing, etc.), 4: 30-40% (cleaning, etc.), 5: 40-50% (brisk walking, etc.), 6: 50-60% (relaxing exercise intensity), 7: 60-70% (comfortable exercise intensity), 8: 70-80% (slightly strenuous exercise intensity), 9: 80-90% (very strenuous exercise intensity), 10: 90-100% (full strength)". In this case, the amount of change during exercise and the time it takes for the heart rate and respiratory rate to return to their resting levels (time to return to normal: TTR) are set for each exercise intensity, depending on age and exercise habit. That is, the TTR is set to 10 stages of time (T1 to T10).

[0060] The extraction function 152 calculates disease-related factors using the vital data acquired by the acquisition function 151 and the above-mentioned conditions. For example, the extraction function 152 calculates disease-related factors when the heart rate or respiratory rate in the monitored vital data exceeds the exercise state (exceeds the amount of change during exercise set in the above-mentioned conditions). If the conditions are set according to exercise intensity, the condition that exceeds the amount of change and is the highest exercise intensity is used.

[0061] In such a case, the extraction function 152 calculates the difference between the exercise intensity estimated from the heart rate and respiratory rate included in the vital data and the actual exercise intensity (exercise intensity based on the exercise state included in the vital data) "ΔML = estimated exercise intensity - actual exercise intensity".

[0062] In addition, the extraction function 152 calculates the difference between the actual time it takes for the heart rate and respiratory rate to return to the resting state in the currently acquired vital data (time to return to normal: TTRm) and the time to return to normal (TTRi) set as a condition, i.e., "ΔTTR = actually measured time to return to normal TTRm - time to return to normal TTRi."

[0063] In addition, the extraction function 152 calculates the number of heartbeats occurring when there is no R wave and the heartbeat is long, or conversely, when the heartbeat intervals are very short, from the electrocardiogram state at rest as the number of irregular heartbeats (NR = the average number of irregular heartbeats per unit time).

[0064] The extraction function 152 then calculates the breathlessness state "BW (Breathlessness to watch)" that requires attention using the following formula. Here, breathlessness is defined as a high heart rate and a high respiratory rate within a unit time. In addition, a state in which the heartbeat is irregular in this state is defined as palpitations. The standard for a high heart rate and a high respiratory rate is the average + 1SD of healthy people in the age group to which the subject belongs. This value can be changed and set.

[0065] BW = α × ΔML + β × ΔTTR + γ × NR where ΔML>0, ΔTTR>0, NR>m (initial value m=2, m or less is 0), α, β, γ=count (initial value=1)

[0066] Here, when a healthy person exercises at a moderate level or higher, or when the heart rate and respiratory rate return to normal within the set normal return time, the difference between the estimated exercise intensity and the actual exercise intensity is "ΔML≦0", the difference between the actual normal return time and the set normal return time is "ΔTTR≦0", and the number of irregular heartbeats is "NR=0". Therefore, in the case of a healthy state, the index expressed by the above formula is "BW≦0". On the other hand, in the case of an abnormality such as a sudden increase in heart rate during daily activities that are not considered to be mild exercise (housework, going up and down stairs, walking, going to the toilet, etc.), the results are "ΔML>0", "ΔTTR>0", and "NR>m", and the above index is "BW>0". Therefore, when using it as an index indicating a state of shortness of breath that requires attention, the above conditions are attached to the above formula.

[0067] (Data accumulation and state estimation processing) 2, the extraction function 152 accumulates the changes in disease-related factors over time and estimates the condition of the subject. For example, the extraction function 152 stores the occurrence date and time, duration, etc. of the above-mentioned noteworthy shortness of breath condition in the memory circuitry 14 during monitoring of vital data. For example, the extraction function 152 records the number of occurrences and total duration per unit time (e.g., every three months).

[0068] For example, if you notice an increase in the number of sudden increases in your heart rate and breathing rate or a longer time it takes for your heart rate and breathing rate to return to their resting states during everyday activities that do not constitute mild exercise (housework, climbing stairs, walking, going to the toilet, etc.), this will indicate a frequency of shortness of breath (BW) that you should be concerned about.

[0069] Therefore, the extraction function 152 counts the number of occurrences of "BW" per unit period (e.g., every three months) and compares it with a threshold value to estimate the condition of the subject. For example, the extraction function 152 estimates the possibility of disease based on whether the number of occurrences of "BW" per unit period is higher than the average value for the same age group. As one example, the extraction function 152 determines that there is a suspicion of disease when the number of occurrences of "BW" per unit period exceeds the average value for a certain period of time (e.g., one year). Also, for example, the extraction function 152 determines that there is a suspicion of disease when the value of "BW" is higher than a predetermined threshold value.

[0070] (Disease candidate extraction process) As described in step S105 of Fig. 2, the extraction function 152 extracts disease candidates based on the condition of the subject. Specifically, when the extraction function 152 determines that a disease is suspected using a disease-related factor, it extracts a disease related to the disease-related factor as a disease candidate. Fig. 4 is a diagram for explaining an example of a disease candidate estimation process according to the first embodiment. Here, Fig. 4 shows a disease ontology that represents a link between a symptom and a disease.

[0071] For example, when it is determined that there is a suspicion of disease due to the above-mentioned shortness of breath condition "BW" that requires attention, the extraction function 152 extracts disease candidates of the subject using a disease ontology that includes shortness of breath and palpitations as symptoms, as shown in Fig. 4. For example, the extraction function 152 extracts "heart failure", which is closely related in the disease ontology, as a disease candidate.

[0072] The extraction function 152 can extract multiple disease candidates from a single disease-related factor, and can also extract multiple disease candidates from multiple disease-related factors.

[0073] (Degree estimation process) As described in step S106 of Fig. 2, the estimation function 153 estimates the degree of the extracted disease candidate. Specifically, the estimation function 153 estimates the state of the subject with respect to the disease candidate by comparing information on a patient group suffering from the disease candidate with information on the subject. For example, when "heart failure" is extracted as a disease candidate, the estimation function 153 estimates the state of the subject with respect to "heart failure."

[0074] Here, in order to compare information on a patient group suffering from a disease candidate with information on the subject, the estimation function 153 sets attributes for the patient group and the subject. The attributes include epidemiological information, patient functional index, main disease state, overall state, heredity, family history, lifestyle, etc., and are composed of, for example, current state (age, sex, weight, blood type, vital data), index value, risk information, medical history, hereditary information, etc. Note that the above is merely an example, and other information may be used as attributes. Also, all of the above information may be used, or only a part of it may be used.

[0075] The estimation function 153 quantifies the above-mentioned attributes for the patient group and the subject, and compares them to perform estimation processing of the degree of the disease candidate. For example, the estimation function 153 generates an attribute distribution that quantitatively represents the attributes, and compares the patient group and the subject using the generated attribute distribution. Fig. 5A is a diagram showing an example of the attribute distribution according to the first embodiment. Note that Fig. 5A shows the attribute distribution of the subject.

[0076] For example, as shown in FIG. 5A, the attribute distribution is generated in a radar chart in which the degree of each attribute, "age / gender," "general condition," "lifestyle," "medical history / hereditary," "vital data," "index value," and "risk information," is indicated in a scale of 0 to 5. That is, the value of each attribute is normalized to be scaled from 0 to 5, and is indicated as a radar chart distribution. Each attribute shown in FIG. 5A includes a plurality of items classified into the attribute, and each item is quantified and a value is plotted. For example, the attribute "vital data" includes items such as heart rate, pulse, blood pressure, electrocardiogram, respiratory rate, body fat percentage, skeletal muscle, vascular information, and degree of arteriosclerosis. Also, for example, the attribute "index value" includes items such as index values ​​derived from vital data (e.g., BW, etc.) and index values ​​obtained by medical examinations.

[0077] Here, the index values ​​obtained by the examination of the health checkup can be divided into symptom levels according to guidelines or the like, and these may be used for the above-mentioned grading. FIG. 5B is a diagram for explaining an example of grading of attributes according to the first embodiment. For example, as shown in FIG. 5B, each index value (vital sign in the figure) obtained by the examination is classified into symptom levels according to its numerical value. Therefore, for such index values, the attribute distribution may be graded according to the symptom level.

[0078] The grading of attributes is not limited to the above-mentioned method, and other methods can be used. For example, grading may be performed using diagnostic criteria or diagnostic trees at each medical institution. Furthermore, grading may be performed using machine learning or deep learning.

[0079] The estimation function 153 quantifies each item included in the attribute and plots it on a radar chart as shown in Fig. 5A to generate an attribute distribution of the subject. Note that the attribute distribution is not limited to a radar chart and may be expressed by a histogram, a stacked graph, a heat map, or the like. Also, the number of stages of the attribute can be set arbitrarily.

[0080] Furthermore, the estimation function 153 generates an attribute distribution in a patient group of a disease candidate, which is to be compared with the attribute distribution of the subject. Specifically, the estimation function 153 extracts a patient group suffering from a disease candidate (e.g., heart failure), and generates an attribute distribution in the extracted patient group. Here, the patient group to be extracted may be a patient group in a single medical institution, a patient group in all related medical institutions, or a patient group in medical statistics.

[0081] For example, the estimation function 153 acquires information about the above-mentioned patient groups (patient groups at a single medical institution, patient groups at all related medical institutions, or patient groups based on medical statistics) from a data storage device, and uses the acquired information to generate an attribute distribution for the patient group.

[0082] Here, the estimation function 153 stratifies (classifies, groups, clusters) the acquired patient group according to the degree of the disease, and then generates an attribute distribution for each stratified group. For example, a standard is set for the pathology of the disease, and stratification is performed based on the set standard. As one example, the pathology of the disease is classified into two (above standard value / below standard value) or three (within standard range / above standard range / below standard range) based on a predetermined standard value, and the patient group is stratified into each group. Note that the number of groups may be four or more.

[0083] The standard value used for stratification may be a fixed value determined based on medical statistical results or guidelines, or may be a value to which a margin set for a reference value (such as the national average or the average value within each medical institution) is added or subtracted. Alternatively, the standard value may be a standard deviation such as ±1σ, ±2σ, or ±3σ, or may be a coefficient of variation (CV value).

[0084] Fig. 6 is a diagram showing an example of attribute distribution of a patient group according to the first embodiment. Fig. 6 shows a case where the patient group is stratified into three groups according to the probability of developing into a pathology. For example, as shown in Fig. 6, the estimation function 153 stratifies a patient group with heart failure into three groups, namely, group A (probability of developing into a pathology: low), group B (probability of developing into a pathology: medium), and group C (probability of developing into a pathology: high), based on a preset criterion. Then, the estimation function 153 generates an attribute distribution for each group.

[0085] For example, the estimation function 153 acquires information (clinical information and vital data) of multiple patients included in colony A, generates an attribute distribution for each of the multiple patients from the acquired information, and averages the generated attribute distributions to generate the attribute distribution for colony A shown in Fig. 6. Similarly, the estimation function 153 generates an attribute distribution for each patient for colonies B and C, and averages the generated attribute distributions to generate the attribute distributions for colonies B and C, respectively.

[0086] Then, the estimation function 153 estimates the degree of the subject's disease (heart failure) by comparing the attribute distribution of the subject (see FIG. 5A) with the attribute distribution of the patient group (see FIG. 6). For example, the estimation function 153 compares the attribute distribution of the subject with the attribute distributions of the colonies A, B, and C to calculate the similarity of the attribute distributions, and estimates the degree based on the calculated similarity. As an example, the estimation function 153 calculates the similarity between the geometric shape of the attribute distribution of the subject and the geometric shape of the attribute distribution of the colony A as the similarity. Similarly, the estimation function 153 calculates the similarity between the attribute distribution of the subject and the attribute distribution of the colony B, and the similarity between the attribute distribution of the subject and the attribute distribution of the colony C. The calculation of the similarity may be obtained from the overlap of statistical distributions, or may be performed by calculating the likelihood using machine learning.

[0087] Then, the estimation function 153 estimates the pathology probability of the group with the highest similarity as the degree of the subject's disease (heart failure). For example, when the result of comparing the attribute distribution shows that the similarity with group C is highest, the estimation function 153 estimates that the probability of the subject's disease (heart failure) developing into a pathology is high. Also, for example, when the result of comparing the attribute distribution shows that the similarity with group B is highest, the estimation function 153 estimates that the probability of the subject's disease (heart failure) developing into a pathology is medium. Also, for example, when the result of comparing the attribute distribution shows that the similarity with group A is highest, the estimation function 153 estimates that the probability of the subject's disease (heart failure) developing into a pathology is low.

[0088] (Recommended action presentation process) As described in step S107 of Fig. 2, the presentation function 154 controls to present a recommended action according to the estimated degree to the subject (terminal device 22). Here, the presentation function 154 presents different information according to the estimated degree, as described in steps S205 to S210 of Fig. 3.

[0089] For example, when it is estimated that the probability of the subject's disease (heart failure) developing into a pathology is low, the presentation function 154 causes the display of the terminal device 22 to present information indicating that the rate of the subject's disease developing into a pathology of heart failure at the present time is low.

[0090] Furthermore, when the probability of the subject's disease (heart failure) becoming a pathological condition is estimated to be medium, the presentation function 154 presents a proposed test, for example, recommending a blood test for heart failure (for example, BNP or NT-proBNP). That is, the presentation function 154 presents a test method for diagnosing a candidate disease. The proposed test may include information on ordering a test kit and introducing hospitals where the test can be taken.

[0091] Furthermore, when it is estimated that the probability of the disease (heart failure) in the subject becoming pathological is high, the presentation function 154 presents a prescription suggestion showing candidate drugs suitable for the subject. Here, when presenting a prescription suggestion, prior to the presentation of information by the presentation function 154, the effect of the drug is evaluated by the prediction function 153, and a drug suitable for the subject is predicted.

[0092] For example, the estimation function 153 estimates the therapeutic effect of a drug based on the subject's clinical information, medical knowledge about a drug prescribed for a disease candidate, and vital data of the subject. As an example, the estimation function 153 acquires information about a drug prescribed for a disease, stratifies a patient group based on the acquired information, and estimates a drug suitable for the subject by comparing the attribute distribution of each stratified group with the attribute distribution of the subject. That is, the estimation function 153 estimates a drug suitable for the subject by the same method as when estimating the degree of the disease.

[0093] Fig. 7 is a diagram showing an example of attribute distribution of a patient group according to the first embodiment. Fig. 7 shows attribute distribution in the case where the degree of disease of a subject is estimated to be the highest similarity to the group C in Fig. 6. For example, the estimation function 153 acquires information on drugs prescribed to a plurality of patients based on information on the plurality of patients included in group C determined to have a high similarity in the estimation of the degree of disease, and stratifies the plurality of patients based on the acquired drug information.

[0094] As an example, as shown in Fig. 7, the estimation function 153 stratifies a plurality of patients included in the colony C into a colony C-1 to which drug A is prescribed, a colony C-2 to which drug B is prescribed, and a colony C-3 to which drug C is prescribed. Then, the estimation function 153 generates the attribute distribution of the colony C-1 shown in Fig. 7 by averaging the attribute distribution of the plurality of patients included in the colony C-1. Similarly, the estimation function 153 generates the attribute distributions of the colonies C-2 and C-3, respectively, by averaging the attribute distributions of each patient for the colonies C-2 and C-3.

[0095] Then, the estimation function 153 estimates a drug suitable for the subject by comparing the attribute distribution of the subject (see FIG. 5A) with the attribute distribution of the patient group (see FIG. 7). For example, the estimation function 153 calculates the similarity of the attribute distribution by comparing the attribute distribution of the subject with each of the attribute distributions of the colonies C-1, C-2, and C-3, and estimates a drug suitable for the subject based on the calculated similarity. As an example, the estimation function 153 calculates the similarity between the geometric shape of the attribute distribution of the subject and the geometric shape of the attribute distribution of the colony C-1 as the similarity. Similarly, the estimation function 153 calculates the similarity between the attribute distribution of the subject and the attribute distribution of the colony C-2, and the similarity between the attribute distribution of the subject and the attribute distribution of the colony C-3.

[0096] Then, the estimation function 153 estimates the drug prescribed to the group with the highest similarity as the drug suitable for the subject. For example, when the result of comparing the attribute distribution shows the highest similarity with the colony C-1, the estimation function 153 estimates that the drug A is the drug suitable for the subject. Also, for example, when the result of comparing the attribute distribution shows the highest similarity with the colony C-2, the estimation function 153 estimates that the drug B is the drug suitable for the subject. Also, for example, when the result of comparing the attribute distribution shows the highest similarity with the colony C-3, the estimation function 153 estimates that the drug C is the drug suitable for the subject.

[0097] Here, the estimation function 153 estimates side effects that will occur in the subject when the drug is administered, and estimates the therapeutic effect including the estimation result. For example, the estimation function 153 extracts information on side effects of the drug (presence or absence, degree, etc.) included in the information on the patient group for each of the colonies C-1, C-2, and C-3. Then, the estimation function 153 estimates a drug suitable for the subject based on the similarity of the attribute distribution and the information on the side effects of the drug. The correspondence between the similarity and the side effects may be obtained from information organized in a database, or may be associated by a machine learning algorithm.

[0098] For example, if the similarity of the attribute distribution is "C-1>C-3>C-2" and the degree of side effects is "C-1>C-2>C-3", the estimation function 153 estimates that the drug C prescribed to the group C-3 is suitable for the subject.

[0099] The estimation function 153 can also estimate the mutual influence with drugs currently being taken, and estimate a drug suitable for the subject, including the estimation result. In such a case, the estimation function 153 acquires information on drug interactions with drugs taken by the subject from guidelines, etc. Then, the estimation function 153 determines whether or not a drug to be prescribed is included as a drug that has poor interactions with the drug taken by the subject. Here, if the drug to be prescribed is included as a drug that has poor interactions, the estimation function 153 estimates a drug suitable for the subject from among drugs other than the drug that has poor interactions.

[0100] For example, if the similarity of the attribute distribution is "C-1>C-3>C-2" and "drug A" is a drug that has poor drug interactions, the estimation function 153 estimates that drug C prescribed to the group C-3 is a drug suitable for the subject.

[0101] The presentation function 154 causes the terminal device 22 to present a prescription plan including information on the drug estimated as described above. Note that the information presented by the presentation function 154 is not limited to the information described above. For example, the presentation function 154 can also cause the terminal device 22 to present a checklist for conducting a simple medical interview with the subject. The presentation function 154 can also cause the terminal device 22 to present information for introducing the subject to the nearest specialist. In addition, when a sudden drop in heart rate or respiratory rate occurs in the monitored vital data, the presentation function 154 can also control the terminal device 22 to output an alert sound to notify people around the device of an emergency.

[0102] As described above, according to the first embodiment, the acquisition function 151 acquires clinical information and vital data of the subject. The extraction function 152 extracts disease candidates based on the vital data. The estimation function 153 estimates the degree of pathology corresponding to each disease candidate based on the clinical information of the subject and medical knowledge regarding each disease candidate. The presentation function 154 presents recommended actions corresponding to the disease candidate based on the degree of pathology. Therefore, the medical information processing device 100 according to the first embodiment can monitor the vital data of the subject acquired in daily life, and when an abnormality is detected during monitoring, can control the device to recommend an appropriate prescription according to the subject, making it possible to propose an appropriate response according to the individual's condition.

[0103] According to the first embodiment, the estimation function 153 estimates the degree of pathology of a disease corresponding to each disease candidate based on the subject's clinical information, medical knowledge, and further the subject's vital data. Therefore, the medical information processing apparatus 100 according to the first embodiment makes it possible to propose a response suited to the current condition of an individual.

[0104] According to the first embodiment, the extraction function 152 extracts disease candidates based on the relationship between the subject's activity state and biological information contained in the vital data. Therefore, the medical information processing apparatus 100 according to the first embodiment makes it possible to extract disease candidates based on the subject's condition.

[0105] According to the first embodiment, the extraction function 152 estimates the condition of the subject based on a comparison between the exercise intensity of the subject during exercise and the respiratory change or heart rate change during the exercise, and extracts disease candidates based on the estimation result. Therefore, the medical information processing apparatus 100 according to the first embodiment makes it possible to accurately determine the condition of the subject.

[0106] According to the first embodiment, the extraction function 152 performs a comparison over time between the exercise intensity of the subject during exercise and the respiratory change or heart rate change during the exercise, and estimates the condition of the subject based on the comparison over time. Therefore, the medical information processing device 100 according to the first embodiment makes it possible to accurately determine the condition of the subject.

[0107] According to the first embodiment, the estimation function 153 estimates the therapeutic effect of a drug based on the subject's clinical information, medical knowledge about a drug prescribed for a disease candidate, and the subject's vital data. Therefore, the medical information processing apparatus 100 according to the first embodiment makes it possible to estimate a drug suitable for the subject.

[0108] According to the first embodiment, the estimation function 153 estimates side effects that will occur in a subject when a drug is administered, and estimates the therapeutic effect including the estimation result. Therefore, the medical information processing apparatus 100 according to the first embodiment makes it possible to estimate a drug suitable for a subject, taking into account side effects.

[0109] According to the first embodiment, the presentation function 154 further presents a test method for diagnosing a disease candidate. Therefore, the medical information processing apparatus 100 according to the first embodiment makes it possible to provide useful information to the subject.

[0110] (Other embodiments) In the above-described embodiment, an example has been described in which the acquisition unit, extraction unit, estimation unit, and presentation unit in this specification are realized by the acquisition function, extraction function, estimation function, and presentation function of a processing circuit, respectively, but the embodiment is not limited to this. For example, the acquisition unit, extraction unit, estimation unit, and presentation unit in this specification may be realized by only hardware, only software, or a combination of hardware and software, in addition to being realized by the acquisition function, extraction function, estimation function, and presentation function described in the embodiment.

[0111] The term "processor" used in the description of the above-mentioned embodiment means a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). Here, instead of storing a program in a memory circuit, the program may be directly built into the circuit of the processor. In this case, the processor realizes its function by reading and executing the program built into the circuit. Furthermore, each processor in the present embodiment is not limited to being configured as a single circuit for each processor, and may be configured as a single processor by combining multiple independent circuits to realize its function.

[0112] Here, the medical information processing program executed by the processor is provided by being pre-installed in a ROM (Read Only Memory) or a storage circuit. The medical information processing program may be provided by being recorded in a computer-readable non-transient storage medium such as a CD (Compact Disk)-ROM, a FD (Flexible Disk), a CD-R (Recordable), or a DVD (Digital Versatile Disk) in a format that can be installed in these devices or in a format that can be executed. The medical information processing program may be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, the medical information processing program is composed of modules including each of the above-mentioned processing functions. As actual hardware, a CPU reads out and executes the medical image processing program from a storage medium such as a ROM, so that each module is loaded onto a main storage device and generated on the main storage device.

[0113] In addition, in the above-mentioned embodiment and modified examples, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution or integration of each device is not limited to that shown in the figure, and all or a part of it can be functionally or physically distributed or integrated in any unit according to various loads, usage conditions, etc. Furthermore, all or any part of each processing function performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0114] Furthermore, among the processes described in the above-mentioned embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0115] According to at least one of the embodiments described above, it is possible to propose an appropriate response according to the individual's condition.

[0116] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0117] 1 Medical information processing system 100 Medical information processing device 151 Acquisition Function 152 Extraction function 153 Estimation Function 154 Presentation function

Claims

1. An acquisition unit that acquires clinical information and vital data of a subject; An extraction unit that extracts disease candidates based on the vital data; an estimation unit that estimates a degree of a pathology corresponding to each of the disease candidates based on the clinical information of the subject and medical knowledge regarding each of the disease candidates; a presentation unit that presents a recommended action corresponding to the disease candidate based on the degree of the pathological condition; A medical information processing device comprising:

2. The medical information processing apparatus according to claim 1 , wherein the estimation unit estimates a degree of a pathology of a disease corresponding to each of the disease candidates based on clinical information of the subject, the medical knowledge, and vital data of the subject.

3. The medical information processing apparatus according to claim 1 , wherein the extraction unit extracts the disease candidate based on a relationship between an activity state of the subject and biological information contained in the vital data.

4. The medical information processing device according to claim 3 , wherein the extraction unit estimates a condition of the subject based on a comparison between an exercise intensity of the subject during exercise and a change in respiration or a change in heart rate during the exercise, and extracts the disease candidate based on a result of the estimation.

5. The medical information processing device according to claim 4 , wherein the extraction unit performs a comparison over time between an exercise intensity of the subject during exercise and a change in respiration or a change in heart rate during the exercise, and estimates a condition of the subject based on the comparison over time.

6. The medical information processing device according to claim 2 , wherein the estimation unit estimates a therapeutic effect of a drug based on clinical information of the subject, medical knowledge regarding a drug prescribed for the suspected disease, and vital data of the subject.

7. The medical information processing device according to claim 6 , wherein the estimation unit estimates a side effect that will occur in the subject when the drug is administered, and estimates the therapeutic effect including an estimation result.

8. The medical information processing device according to claim 1 , wherein the presentation unit further presents a test method for diagnosing the suspected disease.

9. An acquisition unit that acquires clinical information and vital data of a subject; An extraction unit that extracts disease candidates based on the vital data; an estimation unit that estimates a degree of a pathology corresponding to each of the disease candidates based on the clinical information of the subject and medical knowledge regarding each of the disease candidates; a presentation unit that presents a recommended action corresponding to the disease candidate based on the degree of the pathological condition; A medical information processing system comprising:

10. acquiring clinical information and vital data of the subject; Extracting disease candidates based on the vital data; estimating a degree of pathology corresponding to each of the candidate diseases based on the clinical information of the subject and medical knowledge regarding each of the candidate diseases; presenting a recommended action corresponding to the disease candidate based on the degree of the pathological condition; A medical information processing method comprising:

Images