Medical system and medical information processing device

Abstract

To provide a new technology to detect the state of a circulatory system of a patient in a non-invasive manner.SOLUTION: A data acquisition unit of a medical system acquires data from the ocular fundus of a patient using at least one optical method, and a data processing unit processes the data acquired by the data acquisition unit for generating information on the circulatory system of the patient. The data processing unit includes an inference processing part. Using a learned model constructed by machine learning using training data including second data generated by processing first data acquired from the ocular fundus using the at least one optical method, and diagnostic result data, the inference processing part performs inference processing with the data generated by processing the data acquired from the ocular fundus of the patient by the data acquisition unit as input, and the information on the circulatory system of the patient as output.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a medical system and a medical information processing device. [Background technology]

[0002] Symptoms of diseases and signs of worsening are complex, and various technologies have been developed to detect them. For example, Patent Document 1 discloses a technology for determining the risk of infectious diseases without requiring advanced medical knowledge, which determines the risk based on the presence or absence of abnormalities in arterial oxygen saturation, body temperature, and heart rate. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-123605 Summary of the Invention [Problem to be solved by the invention]

[0004] One object of the present invention is to provide a new technique for non-invasively detecting the condition of a patient's circulatory system. [Means for solving the problem]

[0005] According to some exemplary embodiments, a medical system includes a data acquisition unit and a data processing unit. The data acquisition unit acquires data from a fundus of a patient using at least one optical method. The data processing unit processes the data acquired by the data acquisition unit to generate information related to the patient's circulatory system.

[0006] In some exemplary embodiments, the information relating to the circulatory system includes information relating to thrombophilia.

[0007] In some exemplary embodiments, the information regarding thrombophilia includes information regarding blood properties.

[0008] In some exemplary embodiments, the information regarding blood properties includes information indicating changes in blood properties due to an increase in the blood coagulation and fibrinolysis system.

[0009] In some exemplary embodiments, the information relating to the circulatory system includes information relating to a thrombotic condition.

[0010] In some exemplary embodiments, the information regarding the thrombotic condition includes information indicating the distribution of blood flow velocity within a blood vessel.

[0011] In some exemplary embodiments, the information regarding the thrombotic condition includes information regarding structures formed within a blood vessel.

[0012] In some exemplary embodiments, the information relating to the circulatory system includes information relating to a circulatory system condition associated with an infection.

[0013] In some exemplary embodiments, the information relating to the circulatory system includes at least one of information indicative of a condition related to sepsis, information indicative of a condition related to disseminated intravascular coagulation (DIC), information indicative of a condition related to thrombus, and information indicative of a condition related to vascular occlusion.

[0014] In some exemplary embodiments, the at least one optical technique includes at least one of optical coherence tomography flowmetry (OCT flowmetry), optical coherence tomography angiography (OCT-A), and color fundus photography.

[0015] In some exemplary embodiments, the at least one optical technique includes OCT blood flow measurement, and the data processing unit generates information regarding the blood coagulation-fibrinolysis system based at least on the blood flow data acquired by the OCT blood flow measurement.

[0016] In some exemplary embodiments, the data acquisition unit includes an OCT device and a calculation unit. The OCT device collects data by applying an optical coherence tomography (OCT) scan to the fundus of the patient. The calculation unit calculates blood flow velocity and blood vessel diameter based at least on the data collected by the OCT device. The data processing unit generates information related to the blood coagulation-fibrinolysis system based at least on the blood flow velocity and blood vessel diameter calculated by the calculation unit.

[0017] In some exemplary embodiments, the data processor includes a WSR calculator that calculates a wall shear rate (WSR) based at least on the blood flow velocity and the vessel diameter.

[0018] In some exemplary embodiments, the data processing unit includes a memory unit and a WSS calculation unit. The memory unit stores previously acquired blood viscosity information. The WSS calculation unit calculates wall shear stress (WSS) based at least on the wall shear rate and the blood viscosity information.

[0019] In some exemplary embodiments, the data acquisition unit includes an OCT device and a blood flow information generation unit. The OCT device repeatedly applies optical coherence tomography (OCT) scans to a predetermined region of the patient's fundus to collect time-series data. The blood flow information generation unit generates blood flow information representing the spatial distribution and temporal changes of blood flow velocity based at least on the time-series data collected by the OCT device. The data processing unit generates information related to the blood coagulation-fibrinolysis system based at least on the blood flow information generated by the blood flow information generation unit.

[0020] In some exemplary aspects, the data processing unit generates information regarding structures formed within the blood vessel based at least on the blood flow information.

[0021] In some exemplary embodiments, the data processing unit includes a WSR information generating unit that generates WSR information representing a spatial distribution and a temporal change of wall shear rate (WSR) based at least on the blood flow information.

[0022] In some exemplary embodiments, the data processing unit generates information regarding structures formed within the blood vessel based at least on the blood flow information and the WSR information.

[0023] In some exemplary embodiments, the data processing unit includes a storage unit and a WSS information generating unit. The storage unit stores previously acquired blood viscosity distribution information. The WSS information generating unit generates WSS information representing the spatial distribution and temporal change of wall shear stress (WSS) based at least on the WSR information and the blood viscosity distribution information.

[0024] In some exemplary embodiments, the data processing unit generates information regarding structures formed within the blood vessel based at least on the blood flow information and the WSS information.

[0025] In some exemplary embodiments, the data processing unit includes a first inference processing unit that performs inference processing using a first trained model constructed by machine learning using first training data including first data acquired from the fundus using at least one optical method and diagnosis result data, the first inference processing unit receiving data acquired from the fundus of the patient by the data acquisition unit as input and outputting information about the patient's circulatory system.

[0026] In some exemplary embodiments, the data processing unit includes a second inference processing unit that performs inference processing using a second trained model constructed by machine learning using second training data including second data generated by processing first data acquired from the fundus using at least one optical method and diagnosis result data, the second trained model using data generated by processing data acquired from the fundus of the patient by the data acquisition unit as input and information related to the patient's circulatory system as output.

[0027] The medical system according to some exemplary embodiments further includes a transmitting unit that transmits the information about the circulatory system generated by the data processing unit to a doctor's terminal located remotely from the data acquisition unit.

[0028] According to some exemplary embodiments, the medical system further includes a physician terminal.

[0029] The medical system according to some exemplary embodiments further includes an operation unit for remotely operating the data acquisition unit.

[0030] According to some exemplary embodiments, a medical information processing device includes a data receiving unit and a data processing unit. The data receiving unit receives data acquired from a fundus of a patient using at least one optical method. The data processing unit processes the data received by the data receiving unit to generate information related to the patient's circulatory system.

[0031] According to some exemplary embodiments, the medical information processing device further includes a first transmission unit that transmits the information about the circulatory system generated by the data processing unit to a doctor terminal located remotely from the location where the data was acquired.

[0032] A medical system according to some exemplary embodiments includes a medical information processing device according to an exemplary embodiment and a doctor terminal.

[0033] According to some exemplary embodiments, the medical system further includes a data acquisition device and a second transmission unit. The data acquisition device acquires data from the fundus of the patient using at least one optical method. The second transmission unit transmits the data acquired by the data acquisition device to the medical information processing device. The data reception unit receives the data transmitted by the second transmission unit. The data processing unit processes the data transmitted by the second transmission unit and received by the data reception unit to generate information related to the patient's circulatory system. [Effects of the Invention]

[0034] According to exemplary aspects, a new technique can be provided for non-invasively detecting the condition of a patient's cardiovascular system. [Brief explanation of the drawings]

[0035] [Figure 1]1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 2] FIG. 2 is a schematic diagram illustrating an example of the structure of data processed by a medical system according to an exemplary embodiment. [Figure 3] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 4] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 5] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 6] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 7] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 8] 1 is a flowchart illustrating an example of the operation of a medical system according to an exemplary embodiment. [Figure 9] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 10] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 11] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 12] 1 is a schematic diagram illustrating an example of a configuration of a medical system according to an exemplary embodiment. [Figure 13] 1 is a schematic diagram illustrating an example of the configuration of a medical information processing device and a medical system including the same according to an exemplary embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0036] This disclosure describes several exemplary aspects of a medical system and a medical information processing device. Those skilled in the art will understand that the aspects of this disclosure provide various modifications and equivalents, and that the aspects of this disclosure or their modifications or equivalents provide various other aspects, such as a medical method, a system control method, an apparatus control method, a program, and a recording medium.

[0037] In some exemplary embodiments, a computer processes data acquired from the fundus of a patient using at least one optical modality to generate information about the patient's circulatory system. This computer processing may include inference. This inference may be performed, for example, by an algorithm using a trained model (inference model) constructed by machine learning, an algorithm without a trained model, or a combination thereof.

[0038] In some exemplary embodiments, the data subjected to computer processing may be data acquired during any ophthalmic examination, for example, data acquired by any ophthalmic modality device. The ophthalmic modality device may be, for example, an optical coherence tomography (OCT) device, a fundus camera, a scanning laser ophthalmoscope, a slit lamp microscope, a surgical microscope, etc. In some exemplary embodiments, the optical coherence tomography device is used for, for example, optical coherence tomography blood flow measurement, optical coherence tomography angiography (OCT-A), etc. In some exemplary embodiments, a fundus photography device such as a fundus camera, a scanning laser ophthalmoscope, a slit lamp microscope, or a surgical microscope is used for, for example, color fundus photography. Note that the data subjected to computer processing is not limited to these, and may further include, for example, other types of examination data, electronic medical record data, interview data, patient background information (age, treatment history, medical history, medication history, surgical history, etc.), etc.

[0039] Exemplary embodiments are configured to generate predetermined information regarding the patient's circulatory system from such data. The information generated by some exemplary embodiments may include quantitative and / or qualitative information, such as any of the following: information regarding thrombophilia; information regarding thrombotic symptoms; information regarding circulatory conditions associated with infection; information indicative of a condition related to sepsis; information indicative of a condition related to disseminated intravascular coagulation (DIC); information indicative of a condition related to a thrombus; or information indicative of a condition related to a vascular occlusion.

[0040] The information on thrombosis tendency is information indicating the tendency of thrombi to form in the patient's circulatory system (inside blood vessels, inside the heart), and includes, for example, information on the risk of thrombosis. The information on thrombosis tendency may include either information on blood properties or information indicating changes in blood properties due to an increase in the blood coagulation / fibrinolysis system. The information on blood properties includes information on the properties of blood and / or information on the state of blood. The information indicating changes in blood properties due to an increase in the blood coagulation / fibrinolysis system includes information indicating changes in blood properties due to an increase in the action system that causes blood to clot (coagulation system, blood coagulation factors) and / or information indicating changes in blood properties due to an increase in the action system that dissolves thrombi or clots (fibrinolysis system, fibrinolysis system). The information on thrombosis tendency may include, for example, viscosity, wall shear stress, wall shear rate, the amount or proportion of specific components, the ratio between specific components, information indicating changes in any of these, or information indicating the distribution of any of these.

[0041] The information on thrombotic symptoms is information on symptoms caused by thrombus, and may include, for example, information indicating the distribution of blood flow velocity in a blood vessel and information on structures formed in a blood vessel. The distribution of blood flow velocity in a blood vessel may be, for example, one of a one-dimensional distribution, a two-dimensional distribution, a three-dimensional distribution, and a temporal distribution, or a combination of two or more of these. The structures formed in a blood vessel may be, for example, white thrombus, red thrombus, mixed thrombus, hyaline thrombus, or a substance (e.g., intermediate product) involved in the formation mechanism of any of these.

[0042] Information on circulatory system conditions associated with infectious diseases includes, for example, information on diseases or pathologies associated with or caused by infectious diseases, such as vascular inflammation, thrombosis tendency, blood coagulation tendency, sepsis, DIC, pneumonia, lymphadenitis, lymphangitis, etc. The target infectious disease may be any viral infection, any bacterial infection, or any fungal infection, such as the novel coronavirus disease 2019 (COVID-19) that caused a major pandemic in 2020, severe acute respiratory syndrome (SARS), Middle East respiratory syndrome (MERS), influenza, infective endocarditis, etc.

[0043] Sepsis is a very serious condition caused by infection spreading throughout the body, leading to circulatory shock, DIC, multiple organ failure, etc. Information indicating the state of sepsis includes, for example, information on symptoms such as inflammation and circulatory failure caused by sepsis.

[0044] DIC is a syndrome in which blood coagulation reactions, which should normally occur only at the site of bleeding, occur uncontrollably in blood vessels throughout the body. The pathological condition of DIC is characterized by the sustained and significant activation of coagulation in blood vessels throughout the body, resulting in the formation of numerous microthrombi. As the condition progresses, organ damage due to impaired microcirculation leads to consumptive coagulation disorder, resulting in bleeding. In addition to coagulation activation, fibrinolytic activation also occurs, resulting in excessive fibrinolysis of thrombi, promoting bleeding. Information indicating the condition of disseminated intravascular coagulation (DIC) includes, for example, information indicating the above-mentioned pathological conditions of DIC (hypercoagulation system activation, hyperfibrinolysis system activation, thrombi, bleeding, etc.).

[0045] The information indicating the status of thrombi may be any information regarding thrombi that exist or may exist in the circulatory system (inside blood vessels, inside the heart), including, for example, the presence or absence of thrombi, the degree of thrombi, the distribution of thrombi, the number of thrombi, the probability of thrombi being formed, etc.

[0046] The information indicating the condition related to vascular occlusion may be any information related to vascular occlusion that has occurred or may have occurred in the circulatory system, and may include, for example, the presence or absence of vascular occlusion, the degree of vascular occlusion, the distribution of vascular occlusion sites, the number of vascular occlusion sites, the probability of vascular occlusion occurring, etc.

[0047] Thus, exemplary aspects enable non-invasive detection of the state of a patient's circulatory system by generating information about the patient's circulatory system based on data acquired from the patient's fundus using, for example, any of the above-described exemplary optical modalities. Some exemplary aspects can generate information about one or more of thrombosis tendency (e.g., blood properties and / or changes in blood properties due to increased blood coagulation and fibrinolysis), thrombosis symptoms (e.g., blood flow velocity distribution and / or intravascular structures), circulatory system conditions and / or changes in conditions associated with infection, sepsis, DIC, thrombus, vascular occlusion, matters similar to any of these, matters derived from any of these, and matters related to any of these mechanisms. Note that the types of information that can be generated by exemplary aspects are not limited to these, and may be any type of information that can be generated (e.g., derived, estimated, etc.) by a combination of the employed optical modality and the employed data processing.

[0048] Some exemplary embodiments have been devised taking into consideration the background described below and can achieve corresponding effects. Medical professionals, such as doctors and nurses, are at risk of hospital-acquired infections. For example, during the 2020 COVID-19 pandemic, cluster infections occurred at medical institutions overwhelmed with patients, making the risk of infection among medical professionals a major issue. The increased risk of infection among medical professionals can occur not only during infectious disease outbreaks, but also during disasters or major accidents. While maintaining sufficient distance between people, known as social distancing, is generally considered important for reducing the risk of infection, achieving this in standard medical care is not easy. For example, when conducting examinations, doctors and other medical professionals often perform treatment while staying close to the patient.

[0049] Some exemplary embodiments may be configured to provide information generated by computer processing of data acquired by an optical modality to a doctor's terminal located in a remote location. Furthermore, some exemplary embodiments may be configured to enable the examination device (optical modality device) and computer to be operated from a remote location. These configurations enable data obtained from examinations that previously required the doctor to be close to the patient to be used for diagnosis. In other words, some exemplary embodiments enable social distancing between patients and medical professionals to be maintained while also enabling non-invasive and highly accurate detection of complex physiological events, such as symptoms and signs of aggravation.

[0050] Here, the "remote location" may be any location that allows social distancing between the patient and the medical staff. For example, the doctor's terminal may be installed in a room separate from the testing device, or in a facility separate from the testing device. Furthermore, the device for remotely operating the testing device (operating device, operating unit) may be installed in a room separate from the testing device, or in a facility separate from the testing device. Note that social distancing does not need to be ensured if the test is performed under a sufficient infection prevention system, such as when full protective clothing is worn.

[0051] Modifications to the exemplary embodiments can be made by the matters described in the documents cited in this specification or by any other known techniques, and these modifications may be, for example, additions, combinations, substitutions, deletions, omissions, and other modifications.

[0052] At least a portion of the functionality of the elements described in this disclosure may be implemented using circuitry or processing circuitry, such as a general-purpose processor, a special-purpose processor, an integrated circuit, 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), a field programmable gate array (FPGA)), or a combination of these devices configured and / or programmed to perform at least a portion of the disclosed functionality. The term "circuitry," "circuit," "computer," "processor," "unit," "means," "part," or the like may include any of conventional circuitry, including transistors and / or other circuitry. In this disclosure, the terms "circuitry," "circuit," "computer," "processor," "unit," "means," "part," or the like may include hardware that performs at least some of the disclosed functions and / or hardware that is programmed to perform at least some of the disclosed functions. The hardware may be the hardware disclosed herein or known hardware that is programmed and / or configured to perform at least some of the disclosed functions. In the case of a processor, where the hardware can be considered a type of circuitry, the terms "circuitry," "circuit," "computer," "processor," "unit," "means," "part," or the like may be a combination of hardware and software, and the software may be used to configure the hardware and / or the processor.

[0053] The exemplary aspects described below may be combined in any manner, for example, two or more exemplary aspects may be at least partially combined.

[0054] <Structure of the medical system> Several examples of the configuration of a medical system according to an exemplary embodiment will be described below. The exemplary medical system 1 shown in Fig. 1 includes a data acquisition unit 10, a data processing unit 20, and an output unit 30. The medical system 1 may further include an operation device 2.

[0055] In a typical example, the data acquisition unit 10 and the data processing unit 20 are connected via a communication line. This communication line may form a network within a medical institution, or may form a network spanning multiple facilities. Any communication technology may be applied to this communication line, and may be any of various known communication technologies such as wired communication, wireless communication, and short-range communication. The connection between the data processing unit 20 and the output unit 30 may be similar. Alternatively, the data processing unit 20 and the output unit 30 may be functional units installed in the same computer.

[0056] The operation device 2 is used by a medical professional to remotely operate the data acquisition unit 10 (examination device, optical modality device). The operation device 2 is also used by a medical professional (examiner) to provide instructions to a patient (subject) undergoing an examination using the data acquisition unit 10. The operation device 2 may also be usable to remotely operate the data processing unit 20. The operation device 2 includes, for example, a computer, an operation panel, etc.

[0057] The data acquisition unit 10 is configured to acquire data from the fundus of a patient using at least one optical modality. The data acquisition unit 10 may include any optical fundus imaging modality, such as an optical coherence tomography device, a fundus camera, a scanning laser ophthalmoscope, a slit lamp microscope, or a surgical microscope. The data acquisition unit 10 may also acquire other types of examination data, electronic medical record data, medical interview data, patient background information, and the like.

[0058] The optical coherence tomography device and / or fundus camera may be, for example, a device in which various imaging preparation operations are automated, as described in Japanese Patent Application Laid-Open No. 2020-44027. The imaging preparation operations are operations performed to prepare imaging conditions, and examples thereof include alignment adjustment, focus adjustment, optical path length adjustment, polarization adjustment, and light intensity adjustment. The device may also be capable of automatically executing operations to maintain favorable imaging conditions achieved by the imaging preparation operations. Examples of such operations include automatic alignment adjustment (tracking) in accordance with eye movement and automatic optical path length adjustment (Z-lock) in accordance with eye movement. These automatic operations are effective, for example, in examinations performed without the presence of an examiner.

[0059] The data (optical coherence tomography data) acquired by the optical coherence tomography device may be, for example, at least one of three-dimensional image data obtained by applying a three-dimensional scan to the fundus, projection image data of the three-dimensional image data, optical coherence tomography angiography image data, and optical coherence tomography blood flow data.

[0060] Optical coherence tomography angiography is an optical modality that visualizes blood vessels using motion contrast technology, and is capable of visualizing minute blood vessels. Optical coherence tomography angiography image data is acquired using an optical coherence tomography device described in, for example, Japanese Patent Application Laid-Open No. 2019-58495 and Japanese Patent Application Laid-Open No. 2019-154988.

[0061] Optical coherence tomography blood flow measurement is an optical modality that measures blood circulation conditions (hemodynamics). Optical coherence tomography blood flow data is acquired using an optical coherence tomography device described, for example, in Japanese Patent Application Laid-Open No. 2019-54994 and Japanese Patent Application Laid-Open No. 2020-48730. In some exemplary embodiments, optical coherence tomography blood flow measurement can acquire blood flow velocity, blood flow volume, blood vessel diameter, waveform data representing time-series changes in blood flow velocity (time change, time-dependent change), waveform data representing time-series changes in blood flow volume, and the like, as optical coherence tomography blood flow data. The waveform data is typically a graph of time-series changes in blood flow velocity expressed in a two-dimensional coordinate system with time on the horizontal axis and blood flow velocity on the vertical axis. The optical modality used for measuring fundus blood flow is not limited to optical coherence tomography blood flow measurement, and may be, for example, laser speckle flowgraphy (LSFG) as described in Japanese Patent Publication No. 2008 / 069062.

[0062] Image data that can be acquired by a fundus camera (fundus camera image data) include, for example, color fundus image data, infrared fundus image data, and fluorescence angiography fundus image data (fluorescein angiography image data, indocyanine green angiography image data, etc.) In some exemplary embodiments, color fundus image data is acquired using a fundus camera.

[0063] The scanning laser ophthalmoscope may be, for example, the device described in Japanese Patent Application Laid-Open No. 2014-226156. Image data (scanning laser image data) that can be acquired by a scanning laser ophthalmoscope include, for example, color fundus image data, monochromatic fundus image data, and fluorescent angiographic fundus image data. In some exemplary embodiments, color fundus image data is acquired using a scanning laser ophthalmoscope.

[0064] The slit lamp microscope may be, for example, a device effective for remote imaging, as described in Japanese Patent Application Laid-Open No. 2019-213734. The image data acquired by the slit lamp microscope may be, for example, at least one of color fundus image data, cross-sectional image data of the anterior segment, and three-dimensional image data of the anterior segment. In some exemplary embodiments, color fundus image data is acquired using the slit lamp microscope.

[0065] The surgical microscope may be, for example, a device useful for remote surgery, such as that described in Japanese Patent Application Laid-Open No. 2002-153487. In some exemplary embodiments, color fundus image data is acquired using the surgical microscope.

[0066] In this embodiment, at least one of the examination devices (for example, an optical coherence tomography device, a fundus camera, etc.) included in the data acquisition unit 10 may be remotely operated and / or remotely controllable.

[0067] For example, in consideration of the risk of infection to medical personnel, the examination room where tests using testing equipment are performed can be separated from the control room where the testing equipment is operated. In addition to the testing equipment, the examination room is equipped with speakers and displays for outputting instructions (voice, images, videos, etc.) from the operator in the control room, a video camera for filming subjects (patients) in the examination room, a microphone for inputting the subject's voice, and a computer connected to the testing equipment.

[0068] Meanwhile, an operation device 2 for remotely operating the examination device is provided in the operation room. The operation device 2 is equipped with a computer, an operation panel, a display, a video camera, a microphone, etc. The computer executes processing for remote operation. The computer is connected to the examination device in the examination room. The operation panel, video camera, and microphone are used to input instructions to the subject. The display shows data acquired by the examination device and information for remote operation (screen, information from the examination room, etc.).

[0069] With this configuration, an operator (medical worker) in the control room can remotely operate the testing equipment in the testing room using, for example, an application programming interface (API), and can also send instructions to the subject using a videophone, etc. This allows the subject to undergo testing alone, following the instructions of the operator in a remote location, thereby significantly reducing the risk of infection from the subject to the operator.

[0070] To more effectively allow a patient (subject) to perform an examination alone, an examination device with automated preparatory operations (as described above) can be used. In this case, it is considered possible to perform the examination without instructions from an operator. In some cases, it may not be necessary to assign an assistant (such as an operator). However, since it is expected that some patients will find it difficult to perform the examination alone, for example, an assistant may be placed on standby at a remote location, or the assistant may monitor the examination status from a remote location. Note that the assistant (such as an operator) who sends instructions to the patient may be a personified computer system (typically, an automatic response system using artificial intelligence technology).

[0071] The data processing unit 20 performs various data processing operations. The data processing unit 20 of this embodiment is configured to process the data acquired by the data acquisition unit 10 to generate information about the patient's circulatory system.

[0072] The information generated by the data processing unit 20 in this embodiment may be, for example, at least one of the following information: information regarding thrombosis tendency (information regarding blood properties, and / or information indicating changes in blood properties due to increased blood coagulation and fibrinolysis); information regarding thrombosis symptoms (a method of indicating blood flow velocity distribution within blood vessels, and / or information regarding structures formed within blood vessels); information regarding the state (and / or changes in state) of the circulatory system accompanying infection; information indicating a state related to sepsis; information indicating a state related to DIC; information indicating a state related to thrombosis; information indicating a state related to vascular occlusion.

[0073] The following describes some examples of the processing executed by the data processing unit 20. The data processing unit 20 may or may not use a trained model (inference model) constructed by machine learning.

[0074] 2 shows an example of a data structure for processing (recording, transmitting, etc.) data generated by the data processing unit 20. The data structure 100 in this example includes a thrombosis tendency data section 110, a thrombosis symptom data section 120, an infection-associated data section 130, a sepsis data section 140, a DIC data section 150, a thrombosis data section 160, and a vascular occlusion data section 170.

[0075] The thrombus formation tendency data section 110 is an area (e.g., a folder) in which information related to thrombus formation tendency generated by the data processing unit 20 is recorded. The thrombus formation tendency data section 110 includes a blood property data section 111. The blood property data section 111 is an area in which information related to blood property generated by the data processing unit 20 is recorded. The blood property data section 111 includes a blood property change data section 112. The blood property change data section 112 is an area in which information indicating changes in blood property due to an increase in the blood coagulation-fibrinolysis system generated by the data processing unit 20 is recorded.

[0076] The thrombus symptom data section 120 is an area where information related to thrombus symptoms generated by the data processing unit 20 is recorded. The thrombus symptom data section 120 includes a blood flow velocity distribution data section 121 and an intravascular structure data section 122. The blood flow velocity distribution data section 121 is an area where information indicating the distribution of blood flow velocities in blood vessels generated by the data processing unit 20 is recorded. The intravascular structure data section 122 is an area where information related to structures formed in blood vessels generated by the data processing unit 20 is recorded.

[0077] The infection-associated data section 130 is an area where information relating to the state of the circulatory system accompanying an infection, generated by the data processing unit 20, is recorded. The sepsis data section 140 is an area where information indicating a state relating to sepsis, generated by the data processing unit 20, is recorded. The DIC data section 150 is an area where information indicating a state relating to DIC, generated by the data processing unit 20, is recorded. The thrombus data section 160 is an area where information indicating a state relating to a thrombus, generated by the data processing unit 20, is recorded. The vascular occlusion data section 170 is an area where information indicating a state relating to a vascular occlusion, generated by the data processing unit 20, is recorded.

[0078] In some exemplary embodiments, the data structure 100 includes at least one of the above-described data sections 110 to 170. In some exemplary embodiments, the data structure 100 may include data sections other than the above-described data sections 110 to 170. For example, the data structure 100 may include a fundus data section in which data acquired from the fundus by the data acquisition unit 10 is recorded, a processed data section in which data obtained by performing predetermined processing on the data acquired from the fundus by the data acquisition unit 10 is recorded, and an optional data section in which any type of data is recorded. The optional data section may record, for example, data acquired by an optional examination device, electronic medical record data, interview data, patient information (e.g., patient identifier, patient background information), etc.

[0079] Some background of this embodiment configured to generate these data will be explained. "Is disseminated intravascular coagulation (DIC) involved in deaths from COVID-19 pneumonia?" (Nihon Iji Shimpo website: https: / / www.jmedj.co.jp / Journal / paper / detail.php?id=14500) states that DIC (thromboembolism due to DIC) induced by COVID-19 is thought to be one of the causes of death from severe COVID-19 pneumonia, that myocarditis may also occur, that cardiac and vascular echocardiograms, which are performed in closed and close spaces, are rarely performed, and therefore the formation of thrombi in deep veins and the heart is unknown, and that DIC is It has been pointed out that the combination of myocarditis makes it easier for intracardiac blood clots to form, which can lead to thromboembolism and multiple organ failure; that infection with the new coronavirus can lead to sepsis; that imaging diagnosis of microthrombotic disorders caused by sepsis and other conditions is difficult; that early circulatory abnormalities involve the microvasculature, making diagnosis difficult; that tests of the blood coagulation system, including D-dimers, and cardiac and vascular echocardiograms are thought to be effective for patients with new coronavirus pneumonia; that if DIC can be diagnosed, anticoagulant therapy can be expected to dramatically improve symptoms; and that prevention of thrombosis could be the basis for treating new coronavirus pneumonia.

[0080] "It is estimated that many severely ill COVID-19 patients have developed sepsis" (Nihon Iji Shimpo website: https: / / www.jmedj.co.jp / Journal / paper / detail.php?id=14563) points out that many of the severe cases and deaths due to novel coronavirus disease (COVID-19) have developed sepsis. This embodiment provides a non-invasive method for providing information on sepsis.

[0081] The Ministry of Health, Labour and Welfare's "Manual for Treating Serious Adverse Reaction Diseases: Disseminated Intravascular Coagulation (Systemic Hypercoagulability Disorder, Consumption Coagulopathy)" published in June 2007 points out that in sepsis, the balance between blood coagulation and thrombolysis is disrupted, resulting in the development of a syndrome with poor prognosis known as DIC, in which thrombi form throughout the body and bleeding occurs in microvessels. This embodiment provides a non-invasive method for providing information on DIC, blood coagulation, thrombolysis, thrombi, bleeding, etc.

[0082] "COVID-19 and Coagulopathy: Frequently Asked Questions" (AMERICAN SOCIETY OF HEMATOLOGY website: https: / / www.hematology.org / covid-19-and-coagulopathy) points out that in patients infected with novel coronavirus disease (COVID-19), DIC can lead to thrombus formation in various microvessels, mainly in the lungs, that the correlation between blood test values ​​indicating increased blood coagulation and the severity of the disease strongly suggests this possibility, that frequent damage to the heart and kidneys, as well as the lungs, is thought to be due to thrombus formation in blood vessels, and that there have been cases where vasculitis symptoms similar to Kawasaki disease have been present as skin symptoms. This aspect provides a noninvasive method for providing information on thrombus, blood coagulation, vascular inflammation, etc.

[0083] The "Guidelines for the Treatment of Novel Coronavirus Infection 2020 19-COVID, Second Edition" (Ministry of Health, Labour and Welfare website: https: / / www.mhlw.go.jp / content / 000631552.pdf) points out that D-dimer, CRP (C-reactive protein), LDH (serum lactate dehydrogenase), ferritin, lymphocytes, creatinine, and other factors may be useful as markers for the worsening of COVID-19. In particular, a correlation between blood test values ​​indicating increased blood coagulation and the worsening of the disease has been noted. In addition to these, some literature also points out the usefulness of cardiac troponin (Tn), IL-1β, IL-6, IL-8, TNFα, IFNa, and other factors. This embodiment provides a non-invasive method for providing information on changes in blood properties that are reflected in these markers for the worsening of the disease.

[0084] The data processing unit 20 of this embodiment may be designed and configured taking this background into consideration. Some exemplary embodiments of the data processing unit 20 will be described later. Note that the data processing unit 20 (and the data structure 100) can be designed and configured in the same manner even when targeting other infectious diseases.

[0085] An example of the configuration of the data processing unit 20 of this embodiment is shown in Fig. 3. The data processing unit 20 of this embodiment includes an eye image data processing unit 21 and an eye blood flow data processing unit 22.

[0086] The eye image data processing unit 21 may include, for example, a processor that operates according to a program created at least based on the medical knowledge described above. In this case, the eye image data processing unit 21 can generate information about the patient's circulatory system by processing image data (eye image data) acquired from the patient's fundus by the data acquisition unit 10 with at least this processor.

[0087] The eye image data input to the processor may be, for example, optical coherence tomography image data, color fundus image data, etc. The information output from the processor may be, for example, as described above, any of information on thrombosis tendency, information on thrombosis symptoms, information on a circulatory system condition accompanying an infection, information indicating a condition related to sepsis, information indicating a condition related to DIC, information indicating a condition related to thrombosis, and information indicating a condition related to vascular occlusion.

[0088] The eye image data processing unit 21 may include, for example, a trained model constructed by machine learning based at least on the medical knowledge as described above. In this case, the eye image data processing unit 21 can generate information about the patient's circulatory system by processing image data (eye image data) acquired from the fundus of the patient by the data acquisition unit 10 using at least this trained model.

[0089] The eye image data input to the trained model may be, for example, optical coherence tomography image data, color fundus image data, etc. The information output from the trained model may be, for example, as described above, any of information on thrombosis tendency, information on thrombosis symptoms, information on a circulatory system condition accompanying an infection, information indicating a condition related to sepsis, information indicating a condition related to DIC, information indicating a condition related to thrombosis, and information indicating a condition related to vascular occlusion.

[0090] An example of the eye image data processing unit 21 configured using machine learning is shown in Figure 4. The eye image data processing unit 21 of this example includes an inference processing unit 210. The inference processing unit 210 is configured to perform inference processing to derive information about the patient's circulatory system from the eye image data acquired by the data acquisition unit 10, using a trained model constructed by machine learning using training data including clinical data (eye image data and diagnosis result data).

[0091] The eye image data included in the training data may be, for example, image data acquired using the same optical modality as the optical modality of the data acquisition unit 10, but may also be other modalities, such as an optical modality different from the optical modality of the data acquisition unit 10, an ultrasound modality, an electrical modality, a magnetic modality, or an electromagnetic modality. The diagnosis result data included in the training data may be, for example, data obtained by a doctor or other inference model (trained model) based on the associated eye image data.

[0092] By performing machine learning (supervised learning) based on such training data, a trained model (inference model) can be created that uses the eye image data acquired by the data acquisition unit 10 as input and outputs estimated diagnostic data related to the circulatory system. The training data used for machine learning may include data created by a computer based on clinical data. The machine learning may include transfer learning.

[0093] The inference processing unit 210 includes the trained model obtained in this manner, inputs the eye image data acquired by the data acquisition unit 10 into the trained model, and sends the estimated diagnostic data output from the trained model to the output unit 30.

[0094] Machine learning algorithms that can be used in exemplary embodiments are not limited to supervised learning, but may be any algorithm such as unsupervised learning, semi-supervised learning, reinforcement learning, transduction, multi-task learning, etc., or may be a combination of any two or more algorithms.

[0095] Any machine learning technique can be used in the exemplary embodiments, such as neural networks, support vector machines, decision tree learning, association rule learning, genetic programming, clustering, Bayesian networks, representation learning, extreme learning machines, or a combination of any two or more techniques.

[0096] An example of the configuration of the inference processing unit 210 is shown in Figure 5. The inference processing unit 210 of this example includes a first trained model 211 and a second trained model 212. Note that, in some exemplary aspects, the inference processing unit 210 may include only one of the first trained model 211 and the second trained model 212.

[0097] The first trained model 211 is constructed by machine learning using training data including eye image data and diagnosis result data. For example, the first trained model 211 includes a convolutional neural network (CNN). This convolutional neural network includes, for example, an input layer to which eye image data is input, a convolutional layer that applies filtering (convolution) to the input eye image data to create a feature map, a pooling layer that compresses data while preserving features obtained in the convolutional layer, a fully connected layer that extracts and determines characteristic findings from all data obtained in the pooling layer, and an output layer that outputs data obtained in the fully connected layer. By inputting eye image data acquired by the data acquisition unit 10 into the first trained model 211, information about the circulatory system is generated taking into account predetermined features.

[0098] The features considered by the first trained model 211 may include, for example, features related to the rendering state, features related to the rendering object, etc. Features related to the rendering state include color tone, brightness, etc. Features related to the rendering object include features related to the fundus blood vessels, features related to the optic disc, features related to the macula, etc.

[0099] In this embodiment, in order to generate information about the circulatory system, characteristics of the retinal blood vessels are particularly taken into consideration. Characteristics of the retinal blood vessels include distribution, thickness (vascular diameter), tortuosity (pattern), bleeding, etc. For example, characteristics such as rupture, bleeding, and abnormal pattern of retinal microvessels may be detected from eye image data of a patient with sepsis or DIC.

[0100] As one embodiment, an example will be described in which image data representing the morphology (structure) of the fundus, such as optical coherence tomography angiography image data, is acquired. In this case, the first trained model 211 includes a convolutional neural network constructed by machine learning using training data including, for example, optical coherence tomography angiography image data and diagnosis result data. Note that the training data may include any image data, such as fluorescent fundus angiography image data. The convolutional neural network of this embodiment includes, for example, an input layer to which optical coherence tomography angiography image data is input, a convolutional layer that applies filtering (convolution) to the input optical coherence tomography angiography image data to create a feature map of the vascular structure, a pooling layer that compresses the data while preserving the features of the vascular structure obtained in the convolutional layer, a fully connected layer that extracts and determines characteristic findings of the vascular structure from all the data obtained in the pooling layer, and an output layer that outputs the data obtained in the fully connected layer. By inputting the optical coherence tomography angiography image data acquired by the data acquisition unit 10 into the first trained model 211, information about the circulatory system is generated that takes into account the vascular structure of the fundus.

[0101] As another example, a case where color fundus image data is acquired will be described. In this case, the first trained model 211 includes, for example, a convolutional neural network constructed by machine learning using training data including color fundus image data and diagnosis result data. The convolutional neural network of this example includes, for example, an input layer to which the color fundus image data is input, a convolutional layer that applies filtering (convolution) to the input color fundus image data to create a feature map related to color information (e.g., R value, G value, B value), a pooling layer that compresses the data while preserving the characteristics of the color information obtained in the convolutional layer, a fully connected layer that extracts and determines characteristic findings of the color information from all data obtained in the pooling layer, and an output layer that outputs the data obtained in the fully connected layer. By inputting the color fundus image data acquired by the data acquisition unit 10 into the first trained model 211, information related to the circulatory system is generated taking into account the color tone of the fundus.

[0102] The second trained model 212 is constructed by machine learning using training data including data generated by processing eye image data acquired from the fundus using a specified modality and diagnostic result data.

[0103] When the data generated by processing the eye image data is image data, the second trained model 212 includes, for example, a convolutional neural network. This convolutional neural network includes, for example, an input layer to which image data generated by processing the eye image data is input, a convolutional layer that applies filtering (convolution) to the input eye image data to create a feature map, a pooling layer that compresses the data while preserving the features obtained in the convolutional layer, a fully connected layer that extracts and determines characteristic findings from all the data obtained in the pooling layer, and an output layer that outputs the data obtained in the fully connected layer. By inputting data generated by processing the eye image data acquired by the data acquisition unit 10 into the second trained model 212, information about the circulatory system that takes into account predetermined features is generated. The features considered by the second trained model 212 may be the same as or different from the features considered by the first trained model 211.

[0104] The data input to the second trained model 212 is not limited to image data and may be, for example, numerical data, distribution data, time series data, etc. When data in a form other than image data is input to the second trained model 212, the second trained model 212 is constructed according to the form of the input data and the characteristics to be considered. For example, when processing time series data such as waveform data or follow-up observation data, the second trained model 212 may include a recurrent neural network (RNN).

[0105] When the data input to the inference processing unit 210 is video data, the trained model for processing the video data may have a structure that combines, for example, a convolutional neural network and a recurrent neural network.

[0106] The ocular blood flow data processing unit 22 may include, for example, a processor that operates according to a program created at least based on the medical knowledge described above. In this case, the ocular blood flow data processing unit 22 can generate information about the patient's circulatory system by processing data (ocular blood flow data) acquired from the patient's fundus by the data acquisition unit 10 with at least this processor.

[0107] The ocular blood flow data input to the processor may be, for example, data acquired by optical coherence tomography blood flow measurement. The data acquired by optical coherence tomography blood flow measurement may be, for example, waveform image data representing time-series changes in hemodynamics (blood flow velocity, blood volume, etc.), map image data representing the spatial distribution of hemodynamics, image data representing both the spatial distribution and time-series changes in hemodynamics, a series of pairs of values ​​and time representing time-series changes in hemodynamics, a series of pairs of values ​​and coordinates representing the spatial distribution of hemodynamics, or a series of triplets of values, coordinates, and time representing both the spatial distribution and time-series changes in hemodynamics. The information output from the processor may be, for example, any of the following: information on thrombosis tendency, information on thrombosis symptoms, information on circulatory system conditions associated with infection, information indicating a sepsis condition, information indicating a DIC condition, information indicating a thrombus condition, and information indicating a vascular occlusion condition, as described above.

[0108] The ocular blood flow data processing unit 22 may include, for example, a trained model constructed by machine learning based at least on the medical knowledge as described above. In this case, the ocular blood flow data processing unit 22 can generate information about the patient's circulatory system by processing data (ocular blood flow data) acquired from the patient's fundus by the data acquisition unit 10 using at least this trained model.

[0109] The ocular blood flow data input to the trained model may be, for example, data acquired by optical coherence tomography blood flow measurement, as in the case of the above-mentioned processor. The information output from the trained model may also be, for example, information similar to that in the case of the above-mentioned processor.

[0110] An example of the ocular blood flow data processing unit 22 configured using machine learning is shown in Fig. 6. The ocular blood flow data processing unit 22 of this example includes an inference processing unit 220. The inference processing unit 220 is configured to perform inference processing to derive information about the patient's circulatory system from the ocular blood flow data acquired by the data acquisition unit 10, using a trained model constructed by machine learning using training data including clinical data (ocular blood flow data and diagnosis result data).

[0111] The ocular blood flow data included in the training data may be, for example, data acquired using the same optical modality as the optical modality of the data acquisition unit 10, but may also be data acquired using other modalities. Examples of other modalities include an optical modality different from the optical modality of the data acquisition unit 10, an ultrasound modality, an electrical modality, a magnetic modality, an electromagnetic modality, etc. The diagnosis result data included in the training data may be, for example, data obtained by a doctor or other inference model (trained model) based on the associated ocular blood flow data.

[0112] By machine learning (supervised learning) based on such training data, a trained model (inference model) can be created that uses the ocular blood flow data acquired by the data acquisition unit 10 as input and estimates diagnostic data related to the circulatory system as output. The training data used for machine learning may include data created by a computer based on clinical data. The machine learning may include transfer learning. The machine learning algorithm and the machine learning technique may be the same as those of the eye image data processing unit 21.

[0113] The inference processing unit 220 includes the trained model obtained in this manner, inputs the ocular blood flow data acquired by the data acquisition unit 10 into the trained model, and sends the estimated diagnostic data output from the trained model to the output unit 30.

[0114] An example of the configuration of the inference processing unit 220 is shown in Figure 7. The inference processing unit 220 in this example includes a first trained model 221 and a second trained model 222. In some exemplary embodiments, the inference processing unit 220 may include only one of the first trained model 221 and the second trained model 222. Unless otherwise specified, various aspects related to the learning model provided in the inference processing unit 220 may be the same as the corresponding aspects in the learning model provided in the inference processing unit 210.

[0115] The first trained model 221 is constructed by machine learning using training data including ocular blood flow data and diagnosis result data. The first trained model 221 includes, for example, models according to the type (mode) of input data and the type (mode) of output data. For example, the first trained model 221 may include a convolutional neural network similar to the first trained model 211 of the ocular image data processing unit 21. Information about the circulatory system is generated by inputting ocular blood flow data acquired by the data acquisition unit 10 into the first trained model 221. The features considered by the first trained model 221 may be the same as or different from the features considered by the first trained model 211 of the ocular image data processing unit 21.

[0116] The second trained model 222 is constructed by machine learning using training data including data generated by processing data acquired from the fundus using a predetermined modality and diagnostic result data. The type of data generated by processing the data acquired from the fundus may be any type, such as image data, numerical data, distribution data, or time-series data. The second trained model 222 includes, for example, models according to the type (mode) of input data and the type (mode) of output data. Information about the circulatory system is generated by inputting data obtained by processing data acquired by the data acquisition unit 10 into the second trained model 222. The features considered by the second trained model 222 may be the same as or different from the features considered by the second trained model 212 of the eye image data processing unit 21. Furthermore, the data input to the second trained model 222 may be, for example, any of the following types: ocular blood flow data generated by processing ocular blood flow data acquired from the fundus using a specified modality; data of a type other than ocular blood flow data generated by processing ocular blood flow data acquired from the fundus using a specified modality; ocular blood flow data generated by processing data of a type other than ocular blood flow data acquired from the fundus using a specified modality.

[0117] The output unit 30 outputs the results of the processing executed by the data processing unit 20. The form of the output processing is arbitrary, and may be, for example, any of transmission, display, recording, and printing. The information output by the output unit 30 may be the result of the processing executed by the data processing unit 20 itself (information about the patient's circulatory system), information including the processing result, or information obtained by processing the processing result. For example, the medical system 1 may further include a report creation unit (not shown) that creates a report based on the information about the circulatory system obtained by the data processing unit 20. In this case, the output unit 30 can output the created report.

[0118] 1 includes a transmission unit 31. The transmission unit 31 transmits the results of the processing executed by the data processing unit 20 to the doctor terminal 3. The doctor terminal 3 is located remotely from the data acquisition unit 10.

[0119] Data may be transmitted directly or indirectly from the output unit 30 to the doctor terminal 3. Direct transmission is a mode in which the processing results (information about the circulatory system, reports, etc.) are transmitted from the output unit 30 to the doctor terminal 3. Indirect transmission is a mode in which the processing results are transmitted to a device (server, database, etc.) other than the doctor terminal 3 and the processing results are provided to the doctor terminal 3 via that device.

[0120] In this example, by placing the doctor's terminal 3 at a remote location relative to the data acquisition unit 10 and configuring the data acquisition unit 10 to provide the doctor's terminal 3 with information (or information based on this) generated by the data processing unit 20 based on data acquired from the patient's fundus, social distance can be maintained between the doctor (medical worker) and the patient, thereby reducing the risk of infection for the doctor (medical worker).

[0121] <Medical system usage patterns> A usage pattern of the medical system 1 according to an exemplary embodiment will be described. The flowchart in Fig. 8 shows an example usage pattern of the medical system 1. In this example, a trained model is used, but in an example that does not use a trained model, the construction and installation of the trained model (steps S1 and S2) is not necessary, and instead, for example, a processing program is created and installed.

[0122] (S1: Build a trained model) In preparation for operation of the medical system 1, a trained model to be used in the data processing unit 20 is constructed. Note that the processing performed at this stage may be updating (adjusting and updating parameters) of a trained model that is already in operation.

[0123] (S2: Load the trained model into the data processing unit) As a further preparation for the operation of the medical system 1, the trained model constructed in step S1 is loaded into the data processing unit 20. In this process, for example, the trained model constructed in step S1 is transmitted to the medical system 1 via a communication line.

[0124] (S3: Acquire data from the patient's fundus) The subject may be, for example, a patient who has been confirmed to have COVID-19 or a patient who is suspected of having COVID-19. The data acquisition unit 10 of the medical system 1 acquires data from the fundus of the patient using at least one optical modality.

[0125] The data acquisition unit 10 can apply, for example, optical coherence tomography and / or color fundus photography to the fundus. Data acquired by optical coherence tomography may be, for example, any of three-dimensional image data, projection image data, optical coherence tomography angiography image data, and optical coherence tomography blood flow data. Data acquired by color fundus photography may be, for example, color frontal image data representing the morphology of the fundus.

[0126] At least part of the inspection carried out in this step may be a remote inspection using the operation device 2.

[0127] (S4: Input data into the data processing unit) The data acquired in step S3 is sent to the data processing unit 20. In this example, at least a part of the data input to the data processing unit 20 is input to the trained model constructed in step S1.

[0128] (S5: Generate information about the circulatory system) The data processing unit 20 processes the data input in step S4 to generate information about the patient's circulatory system. This allows, for example, obtaining at least one of the following information: information about thrombosis tendency (information about blood properties and / or information indicating changes in blood properties due to increased blood coagulation and fibrinolysis); information about thrombotic symptoms (a method for indicating blood flow velocity distribution in blood vessels and / or information about structures formed in blood vessels); information about the state (and / or changes in state) of the circulatory system accompanying infection; information indicating a state related to sepsis; information indicating a state related to DIC; information indicating a state related to thrombosis; and information indicating a state related to vascular occlusion.

[0129] The information generated by the data processing unit 20 is recorded, for example, according to the data structure 100 of Figure 2. This results in a data package relating to the circulatory system of the patient.

[0130] (S6: Create a report) The medical system 1 (the aforementioned report creation unit, not shown) creates a report based on the information about the patient's circulatory system created in step S5.

[0131] (S7: Send report) The transmitting unit 31 of the output unit 30 transmits the report created in step S6 to the doctor terminal 3 located remotely from the data acquiring unit 10, or to a computer capable of providing information to the medical terminal 3. The doctor terminal 3 is not limited to a computer used by a doctor, but may also be a computer (medical worker terminal) used by a medical worker other than a doctor.

[0132] Such a medical system 1 can ensure social distancing between medical workers and patients and reduce the risk of infection from patients to medical workers. Furthermore, the medical system 1 is configured to acquire data from the fundus of a patient using a non-invasive optical modality such as optical coherence tomography or color fundus photography and generate information about the patient's circulatory system from the data, thereby providing a technology for non-invasively detecting the condition of a patient's circulatory system. The detected condition of the circulatory system is based on, for example, the medical knowledge described above and / or other medical knowledge, and examples of such information include symptoms, signs of aggravation, and the risk of aggravation.

[0133] <First embodiment of the medical system> An exemplary embodiment of the medical system 1 described above will be described. In this embodiment, the case where the data acquisition unit 10 performs optical coherence tomography, particularly optical coherence tomography blood flow measurement, will be described. Based on the medical knowledge described above, this embodiment is configured to generate information about the blood coagulation and fibrinolysis system from ocular blood flow data acquired by optical coherence tomography blood flow measurement. Unless otherwise specified, the medical system of this embodiment may have the same configuration as the medical system 1 described above.

[0134] An example of the configuration of a medical system according to this embodiment is shown in Fig. 9. The medical system 1A of this example includes a data acquisition unit 10A, a data processing unit 20A, and an output unit 30. The output unit 30 and the transmission unit 31 are similar to the output unit 30 and the transmission unit 31 in the above-described medical system 1. The same applies to the operation device 2 and the doctor terminal 3.

[0135] The data acquisition unit 10A is an example of the data acquisition unit 10 of the medical system 1 described above, and includes an optical coherence tomography (OCT) device 11 and a calculation unit 12.

[0136] The optical coherence tomography device 11 applies a scan to the fundus of the patient for optical coherence tomography blood flow measurement. The calculation unit 12 calculates ocular blood flow data based on data collected by the optical coherence tomography device 11 through this scan. The ocular blood flow data includes blood flow velocity and blood vessel diameter at the position where the scan was applied. The scanning method performed by the optical coherence tomography device 11 and the calculation method performed by the calculation unit 12 may be any known method, and for example, the method described in JP 2020-48730 A can be used.

[0137] The data processing unit 20A processes the ocular blood flow data acquired by the data acquisition unit 10A to generate information related to the blood coagulation and fibrinolysis system. An example of the configuration of the data processing unit 20A is shown in FIG. 10. The data processing unit 20A in this example includes a wall shear rate (WSR) calculation unit 231, a memory unit 232, a wall shear stress (WSS) calculation unit 233, and an information generation unit 234.

[0138] The WSR calculation unit 231 calculates the wall shear rate (WSR) based on the blood flow velocity and vascular diameter calculated by the calculation unit 12 of the data acquisition unit 10A. Any method can be used to calculate the wall shear rate from the blood flow velocity and vascular diameter. For example, the method described in the following document can be used: Taiji Nagaoka and Akitoshi Yoshida, "Noninvasive Evaluation of Wall Shear Stress on Retinal Microcirculation in Humans," IOVS.2006, Vol.47, pp.1113-1119. While this document uses laser Doppler velocimetry (LDV) to measure the blood flow velocity and vascular diameter, it will be clear to those skilled in the art that a similar wall shear rate calculation method can also be applied to blood flow velocity and vascular diameter obtained using optical coherence tomography, as in this embodiment.

[0139] Based on this document, the optical coherence tomography device 11 of the data acquisition unit 10A applies a scan over at least one cardiac cycle to collect data. The calculation unit 12 calculates the blood flow velocity by calculating the time average (V mean The calculation unit 12 also calculates the vascular diameter (D) from the cross-sectional image data constructed from the data collected by the scan over one cardiac cycle. The WSR calculation unit 231 calculates the wall shear rate (WSR) using the following formula: WSR=8×V mean / D.

[0140] The calculation unit 12 can calculate the cross-sectional area (Area) of the blood vessel from the cross-sectional image data constructed from the data collected by the scan over one cardiac cycle. Furthermore, the calculation unit 12 can calculate the time average of the blood flow velocity (V mean The blood flow (BF) can be calculated by multiplying the blood vessel cross-sectional area (Area) by the blood flow rate (V): BF = V mean ×Area.

[0141] The memory unit 232 stores blood viscosity information 232a. The blood viscosity information 232a includes a blood viscosity value η. The blood viscosity value η may be an actually measured value or a standard value. Blood viscosity is measured using, for example, a cone and plate viscometer. Blood viscosity may also be estimated from data obtained by a blood test, such as hematocrit (Ht), red blood cell count, and red blood cell constants (mean corpuscular volume (MCV), mean corpuscular volume (MCH), etc.). Alternatively, blood viscosity may be estimated by substituting a specified value for a blood parameter such as plasma viscosity. The standard value may be a normal value or a disease value determined from a range of blood viscosity values ​​obtained from clinical data or experimental data.

[0142] The WSS calculation unit 233 calculates the wall shear stress (WSS) based on at least the wall shear rate calculated by the WSR calculation unit 231 and the blood viscosity value included in the blood viscosity information 232a. Any method may be used to calculate the wall shear rate from the wall shear rate and the blood viscosity value. For example, using the method described in the above-mentioned literature (Nagaoka and Yoshida), the WSS calculation unit 233 calculates the wall shear stress (WSS) using the following formula: WSS = η × WSR.

[0143] The information generating unit 234 generates information about the patient's circulatory system based at least on the wall shear stress calculated by the WSS calculating unit 233. In this embodiment, information about the blood coagulation and fibrinolysis system can be generated as the information about the patient's circulatory system.

[0144] According to Michael R. Condon et al., "Appearance of an erythrocyte population with decreased deformability and hemoglobin content following sepsis," Am J Physiol Heart Circ Physiol 284:H2177-2184, 2003, it has been shown that the deformability of red blood cells is impaired and wall shear stress is increased in the blood of sepsis model animals. Increased wall shear stress promotes vascular endothelial injury and is therefore thought to be associated with a tendency to form thrombus. Based on this background, the information generation unit 234 is capable of evaluating the value of wall shear stress calculated by the WSS calculation unit 233 and generating information including the result.

[0145] When a standard value (predetermined value, default value) is used as the blood viscosity, that is, when η is assumed to be constant in the above formula "WSS = η × WSR," the WSR value and the WSS value correspond one-to-one. Therefore, in this case, it is not necessary to provide the storage unit 232 and the WSS calculation unit 233, and further, the information generation unit 234 may be configured to generate information about the patient's circulatory system (information about the blood coagulation-fibrinolysis system) based on the wall shear rate value calculated by the WSR calculation unit 231.

[0146] <Second embodiment of the medical system> Another exemplary embodiment of the medical system 1 will now be described. In this embodiment, similar to the first embodiment, the data acquisition unit 10 performs optical coherence tomography blood flow measurement, and generates information about the blood coagulation and fibrinolysis system from the ocular blood flow data acquired thereby, as well as information about structures formed within blood vessels. Unless otherwise specified, the medical system of this embodiment may have the same configuration as the above-described medical system 1 and / or 1A.

[0147] An example of the configuration of a medical system according to this embodiment is shown in Fig. 11. A medical system 1B of this example includes a data acquisition unit 10B, a data processing unit 20B, and an output unit 30. The output unit 30 and the transmission unit 31 are similar to the output unit 30 and the transmission unit 31 in the above-described medical system 1. The same applies to the operation device 2 and the doctor terminal 3.

[0148] The data acquisition unit 10B is an example of the data acquisition unit 10 of the medical system 1, and includes an optical coherence tomography (OCT) device 13 and a blood flow information generation unit 14.

[0149] The optical coherence tomography device 13 applies a scan to the fundus of the patient for optical coherence tomography blood flow measurement. The optical coherence tomography device 13 repeatedly applies optical coherence tomography scans to a predetermined region of the fundus of the patient to collect time-series data. This optical coherence tomography scan includes an A-scan for at least one position (A-line), and may be, for example, an A-scan, a B-scan, a circle scan, etc. for multiple positions. This allows time-series data corresponding to each scan application position to be obtained.

[0150] The blood flow information generating unit 14 generates ocular blood flow data based on the time series collected by the optical coherence tomography device 13. The ocular blood flow data includes blood flow information representing the spatial distribution and temporal change of blood flow velocity. The space in which the blood flow velocity distribution is defined may be one-dimensional, two-dimensional, or three-dimensional. The temporal change of blood flow velocity is defined for each point (each position) in the space. In this way, the blood flow information obtained by the blood flow information generating unit 14 represents the temporal change of blood flow velocity at each point in one-dimensional, two-dimensional, or three-dimensional space inside the blood vessel to which optical coherence tomography blood flow measurement is applied. Such blood flow information is described, for example, in Robert S. Reneman and Arnold P.G. Hoeks, "Wall shear stress as measured in vivo: consequences for the design of the arterial system," Med Biol Eng Comput (2008) 46:499-507.

[0151] The data processing unit 20B can generate information about the blood coagulation and fibrinolysis system by processing the ocular blood flow data (blood flow information) acquired by the data acquiring unit 10A. The data processing unit 20B can also generate information about structures formed in blood vessels by processing the ocular blood flow data (blood flow information) acquired by the data acquiring unit 10A.

[0152] 12 shows an example of the configuration of the data processing unit 20B. The data processing unit 20B of this example includes a wall shear rate (WSR) information generator 235, a storage unit 236, a wall shear stress (WSS) information generator 237, and an information generator 238.

[0153] The WSR information generator 235 generates WSR information representing the spatial distribution and temporal change of wall shear rate (WSR) based at least on the blood flow information generated by the blood flow information generator 14 of the data acquirer 10B. Any method can be used to generate the WSR information representing the spatial distribution and temporal change of wall shear rate from the blood flow information representing the spatial distribution and temporal change of blood flow rate, and for example, the method described in the above-mentioned literature (Robert S. Reneman and Arnold P.G. Hoeks) can be used.

[0154] The storage unit 236 stores blood viscosity information 236a. The blood viscosity information 236a may be a single value (η) like the blood viscosity information 232a of the first embodiment, or may be a distribution of blood viscosity values ​​in at least the target space (a space in which the distribution of blood flow velocity is defined). Note that the single blood viscosity value (η) corresponds to a case where the blood viscosity distribution in the target space is uniform (constant).

[0155] The WSS information generator 237 generates WSS information representing the spatial distribution and temporal change of wall shear stress (WSS) based at least on the WSR information generated by the WSR information generator 235 and the blood viscosity distribution information 236a. Any method for generating WSS information may be used. For example, as in the first embodiment, the WSS information generator 237 can generate WSS information by multiplying the value of wall shear rate by the value of blood viscosity for each point in the target space.

[0156] The information generating unit 238 can generate information about structures formed in blood vessels (thrombi, thrombus formation tendency, etc.) based at least on the blood flow information generated by the blood flow information generating unit 14 of the data acquiring unit 10B and the WSS information generated by the WSS information generating unit 237. The information generating unit 238 can generate information about structures formed in blood vessels based at least on the blood flow information generated by the blood flow information generating unit 14 of the data acquiring unit 10B and the WSR information generated by the WSR information generating unit 235. The information generating unit 238 can generate information about the blood coagulation-fibrinolysis system based on any one (and other information) of the blood flow information generated by the blood flow information generating unit 14 of the data acquiring unit 10B, the WSR information generated by the WSR information generating unit 235, and the WSS information generated by the WSS information generating unit 237.

[0157] <Medical information processing device and medical system> An example of a medical information processing device and a medical system including the same according to an exemplary embodiment will be described below. Unless otherwise specified, the elements according to the following embodiment may be the same as the elements of any of the medical systems 1, 1A, and 1B described above.

[0158] 13 includes a data receiving unit 51, a data processing unit 52, and an output unit 53. A data acquisition unit 6, an operation unit 7, a communication unit 8, and a doctor terminal 9 are provided outside the medical information processing device 5 of this embodiment.

[0159] The data acquisition device 6 acquires data from the patient's fundus using at least one optical method. The operation device 7 is used by a medical professional to operate the data acquisition device 6 (examination device). In some exemplary embodiments, the operation device 7 is provided in a location remote from the data acquisition device 6 and is used to remotely operate the data acquisition device 6. The communication device 8 transmits data acquired by the data acquisition device 6 to the medical information processing device 5. In some exemplary embodiments, the doctor's terminal 9 is located in a remote location relative to the data acquisition device 6.

[0160] The data accepting unit 51 of the medical information processing device 5 accepts data acquired from the fundus of a patient using at least one optical method. In this embodiment, the data accepting unit 51 accepts data acquired by the data acquisition device 6 and transmitted by the communication device 8. In the example of FIG. 13 , data is sent from the data acquisition device 6 to the data accepting unit 51 via the communication device 8, but the manner of data input to the medical information processing device 5 is not limited to this. For example, the data acquired by the data acquisition device 6 may be stored in a database or the like, and the data may be sent from this database to the data accepting unit 51. The data accepting unit 51 may include, for example, a communication device for connecting to a communication line, a drive device for reading data recorded on a recording medium, and the like.

[0161] The data processing unit 52 is configured to process the data accepted by the data accepting unit 51 in order to generate information relating to the patient's circulatory system. The output unit 53 outputs the information relating to the patient's circulatory system generated by the data processing unit 52. The output unit 53 in this example includes a transmitting unit 54. The transmitting unit 54 can transmit the information relating to the patient's circulatory system generated by the data processing unit 52 to a doctor's terminal 9 located remotely from the data acquisition device 6.

[0162] Any of the items described with respect to any of the medical systems 1, 1A, and 1B can be combined with the medical information processing device 5 or a medical system including the same.

[0163] Such a medical information processing device 5 and a medical system including the same can ensure social distancing between medical professionals and patients, thereby reducing the risk of infection from patients to medical professionals. Furthermore, the medical information processing device 5 and a medical system including the same are configured to acquire data from a patient's fundus using a non-invasive optical modality such as optical coherence tomography or color fundus photography and generate information about the patient's circulatory system from the data, thereby providing a technology for non-invasively detecting the condition of a patient's circulatory system. The detected condition of the circulatory system is based on, for example, the medical knowledge described above and / or other medical knowledge, and examples of such information include symptoms, signs of aggravation, and the risk of aggravation.

[0164] <Summary> As described above, the technology disclosed herein uses non-invasive optical ophthalmic modalities, such as optical coherence tomography blood flow measurement, optical coherence tomography angiography, and color fundus photography, to detect circulatory system conditions, such as vascular inflammation, thrombus formation, sepsis, and DIC. For example, changes in blood properties associated with blood clotting due to infections can be detected based on wall shear velocity and wall shear stress calculated from blood flow velocity and vascular diameter obtained by optical coherence tomography blood flow measurement, or based on the spatial distribution and temporal changes in blood flow velocity across vascular cross sections (temporal changes in blood flow velocity profiles). Furthermore, these data can be input into a trained model constructed using machine learning to output indicators related to the severity of infections, etc. This enables non-invasive early detection of disease changes and the provision of various diagnostic support information.

[0165] For example, it has been noted that patients with COVID-19 develop blood clots in the microvessels of various organs, particularly the lungs. Furthermore, a correlation has been noted between various vascular test values ​​indicating increased vascular coagulation, which contributes to blood clots, and the severity of the disease. The progression of COVID-19 is thought to occur as follows: (1) infection; (2) rapid immune response and inflammation; (3) DIC; (4) angiogenesis in multiple organs; and (5) death due to cerebral infarction, myocardial infarction, multiple organ failure, etc. There are also known cases in which (2) to (4) progress rapidly. In the case of (2) rapid immune response and inflammation, various coagulation system abnormalities, such as decreased platelets, elevated D-dimer levels, decreased fibrinogen, and prolonged prothrombin time (PT), are detected by blood tests.

[0166] The technology disclosed herein non-invasively detects the hemodynamics of retinal blood vessels (blood flow velocity, blood volume, blood flow waveform shape, etc.) and uses the data to evaluate wall shear stress, thrombus (peripheral vascular occlusion), etc., thereby detecting the risk of severe COVID-19 at an early stage.

[0167] When evaluation is performed using a trained model constructed using machine learning, for example, correlations between various blood test values ​​and hemodynamic information (blood flow velocity, blood volume, blood flow waveform shape, etc.) are used as training data. This allows the construction of a trained model that takes hemodynamic information as input and outputs blood test values. By inputting ocular blood flow data (hemodynamic information) obtained from the patient's fundus using optical coherence tomography blood flow measurement into this trained model, it becomes possible to estimate blood test values.

[0168] The combination of input data and output data is not limited to this example and can be arbitrarily determined based on medical knowledge and background. For example, the input data may be color fundus image data, optical coherence tomography angiography image data, other optical coherence tomography image data (e.g., morphological image data and / or functional image data), etc. Furthermore, the output data may be severity, magnitude of serious risk, numerical values ​​of tests other than blood tests, etc.

[0169] In this way, the technology disclosed herein makes it possible to detect abnormalities in microvessels and blood flow in diseases that cause vascular and circulatory disorders throughout the body at an early stage using a non-invasive modality. [Explanation of symbols]

[0170] 1, 1A, 1B Health Systems 2 Control device 3. Doctor's terminal 10, 10A, 10B Data acquisition section 11, 13 Optical coherence tomography device 12 Calculation section 14 Blood flow information generation section 20, 20A, 20B Data processing section 21 Eye image data processing unit 210 Inference processing unit 211 First trained model 212 Second trained model 22 Ocular blood flow data processing unit 220 Inference processing unit 221 First trained model 222 Second trained model 231 WSR calculation section 232 Storage section 232a Blood viscosity information 233 WSS calculation section 234 Information generation section 235 WSR information generation section 236 Memory section 236a Blood viscosity information 237 WSS information generation section 238 Information generation section 30 Output section 31 Transmitter

Claims

1. a data acquisition unit for acquiring data from the fundus of the patient using at least one optical method; a data processing unit that processes the data acquired by the data acquisition unit to generate information about the patient's circulatory system; Including, the data processing unit includes an inference processing unit that executes inference processing using a trained model constructed by machine learning using training data including second data generated by processing first data acquired from the fundus using the at least one optical method and diagnostic result data, with data generated by processing the data acquired from the fundus of the patient by the data acquisition unit as input and information about the circulatory system of the patient as output. Healthcare system.

2. the inference processing unit executes inference processing in which ocular blood flow data generated by processing the data acquired from the fundus of the patient by the data acquisition unit is used as an input and information about the circulatory system of the patient is output. The medical system of claim 1.

3. the inference processing unit performs inference processing in which the ocular blood flow data generated by processing data collected by the data acquisition unit by applying optical coherence tomography to the fundus of the patient is used as an input and information about the circulatory system of the patient is output. The medical system of claim 2.

4. The ocular blood flow data includes any of waveform image data representing time-series changes in hemodynamics, map image data representing the spatial distribution of hemodynamics, image data representing both the spatial distribution and time-series changes in hemodynamics, a series of pairs of values ​​and time representing the time-series changes in hemodynamics, a series of pairs of values ​​and coordinates representing the spatial distribution of hemodynamics, and a series of pairs of values, coordinates, and time representing both the spatial distribution and time-series changes in hemodynamics. The medical system of claim 3.

5. the inference processing unit outputs, as the information on the patient's circulatory system, any of information on thrombosis tendency, information on thrombosis symptoms, information on a circulatory system condition accompanying an infection, information indicating a condition related to sepsis, information indicating a condition related to disseminated intravascular coagulation, information indicating a condition related to thrombosis, and information indicating a condition related to vascular obstruction. The medical system of claim 4.

6. a data receiving unit that receives data acquired from the fundus of the patient using at least one optical method; a data processing unit that processes the data accepted by the data accepting unit to generate information about the patient's circulatory system; Including, the data processing unit includes an inference processing unit that executes inference processing using a trained model constructed by machine learning using training data including second data generated by processing first data acquired from the fundus using the at least one optical method and diagnostic result data, with data generated by processing the data acquired from the fundus of the patient by the data acquisition unit as input and information about the circulatory system of the patient as output. Medical information processing equipment.

Images