Medical system and medical information processing device

Abstract

To provide a novel technique for accurately detecting a symptom accompanying an infectious disease and a sign of increase in severity.SOLUTION: A medical system includes a data acquisition section and a data processing section. The data acquisition section acquires at least one of blood oxygen data, auscultatory sound data and ocular image data, and ocular fundus blood flow data expressing a hemodynamics in ocular fundus blood vessels, from a patient. The ocular fundus blood flow data includes waveform data expressing a time-series change in a blood flow rate in an ocular fundus artery of the patient. The data processing section processes at least one of the blood oxygen data, the auscultatory sound data and the ocular image data, and the ocular fundus blood flow data acquired by the data acquisition section to detect a change in a condition of a circulatory system that accompanies an infectious disease. In particular, the data processing section detects the change in the condition of the circulatory system based on the waveform data included in the ocular fundus blood flow data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] This invention relates to a medical system and a medical information processing apparatus.

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] One object of this invention is to provide a new technique for detecting symptoms associated with infectious diseases and signs of exacerbation with high accuracy.

Means for Solving the Problems

[0005] A medical system according to some exemplary embodiments includes a data acquisition unit that acquires at least two data out of blood oxygen data, auscultation sound data, eye image data, and eye blood flow data from a patient, and a data processing unit that processes the at least two data acquired by the data acquisition unit to detect a change in the state of the circulatory system associated with an infectious disease.

[0006] In a medical system according to some exemplary embodiments, the change in the state of the circulatory system may include at least one of the onset of pneumonia, a change in the state of pneumonia, the onset of hypoxemia, a change in the state of hypoxemia, and a change in the state of cerebral blood flow.

[0007] In a medical system according to some exemplary embodiments, the eye image data may include fundus image data depicting the fundus of the patient.

[0008] In a medical system according to some exemplary embodiments, the data processing unit may be configured to detect a change in the state of the circulatory system based on the pattern of the blood vessels depicted in the fundus image data.

[0009] In a medical system according to some exemplary embodiments, the fundus image data may include at least one of fundus camera image data, slit lamp image data, optical coherence tomography image data, and scanning laser image data.

[0010] In a medical system according to some exemplary embodiments, the eye image data may include color fundus image data depicting the fundus of the patient.

[0011] In a medical system according to some exemplary embodiments, the data processing unit may be configured to detect a change in the state of the circulatory system based on the color information in the color fundus image data.

[0012] In a medical system according to some exemplary embodiments, the color fundus image data may include at least one of fundus camera image data, slit lamp image data, and scanning laser image data.

[0013] In a medical system according to some exemplary embodiments, the data processing unit may include an inference processing unit that performs an inference process of deriving information regarding a change in the state of the circulatory system from the eye image data acquired by the data acquisition unit using a learned model constructed by machine learning using training data including the eye image data and diagnostic result data.

[0014] In a medical system according to some exemplary embodiments, the ocular blood flow data may include fundus blood flow data representing the blood flow dynamics in the fundus blood vessels of the patient.

[0015] In a medical system according to some exemplary embodiments, the fundus blood flow data may include waveform data representing the time-series change in the blood flow velocity in the fundus arteries of the patient, and the data processing unit may be configured to detect a change in the state of the circulatory system based on the waveform data.

[0016] In a medical system according to some exemplary embodiments, the fundus blood flow data may include two or more pieces of waveform data respectively acquired from the patient in two or more different periods, and the data processing unit may be configured to detect a change in the state of the circulatory system by comparing the two or more pieces of waveform data.

[0017] In a medical system according to some exemplary embodiments, the fundus blood flow data may include either or both of the blood flow velocity data and the blood flow volume data in the fundus arteries of the patient, and the data processing unit may be configured to detect a change in the state of the circulatory system based on either or both of the blood flow velocity data and the blood flow volume data.

[0018] In a medical system according to some exemplary embodiments, the data acquisition unit may include an optical coherence tomography device that scans the fundus of the patient to acquire the fundus blood flow data.

[0019] In a medical system according to some exemplary embodiments, the auscultation sound data may include lung sound data acquired from the patient by an electronic stethoscope.

[0020] In a medical system according to some exemplary embodiments, the data acquisition unit may be further configured to acquire either or both of body temperature data and heart rate data from the patient.

[0021] A medical system according to some exemplary embodiments may further include a transmitting unit that transmits the information output from the data processing unit to a doctor terminal located at a remote position with respect to the data acquisition unit.

[0022] A medical system according to some exemplary embodiments may further include an operation unit for remotely operating the data acquisition unit.

[0023] A medical information processing apparatus according to some exemplary embodiments includes a data reception unit that receives at least two pieces of data among blood oxygen data, auscultation sound data, eye image data, and eye blood flow data acquired from a patient, and a data processing unit that processes the at least two pieces of data received by the data reception unit in order to detect a change in the state of the circulatory system accompanying an infectious disease.

[0024] In a medical information processing apparatus according to some exemplary embodiments, the change in the state of the circulatory system may include at least one of the onset of pneumonia, a change in the state of pneumonia, the onset of hypoxemia, a change in the state of hypoxemia, and a change in the state of cerebral blood flow.

[0025] In a medical information processing apparatus according to some exemplary embodiments, the eye image data may include fundus image data depicting the fundus of the patient.

[0026] In a medical information processing apparatus according to some exemplary embodiments, the data processing unit may be configured to detect a change in the state of the circulatory system based on the running pattern of blood vessels depicted in the fundus image data.

[0027] In a medical information processing apparatus according to some exemplary embodiments, the eye image data may include color fundus image data depicting the fundus of the patient.

[0028] In a medical information processing apparatus according to some exemplary embodiments, the data processing unit may be configured to detect a change in the state of the circulatory system based on the color information in the color fundus image data.

[0029] In a medical information processing apparatus according to some exemplary embodiments, the data processing unit may include an inference processing unit that executes an inference process of deriving information regarding a change in the state of the cardiovascular system from the eye image data received by the data reception unit, using a learned model constructed by machine learning using training data including the eye image data and the diagnosis result data.

[0030] In a medical information processing apparatus according to some exemplary embodiments, the ocular blood flow data may include fundus blood flow data representing the blood flow dynamics in the fundus blood vessels of the patient.

[0031] In a medical information processing apparatus according to some exemplary embodiments, the fundus blood flow data may include waveform data representing the time-series change in the blood flow velocity in the fundus artery of the patient, and the data processing unit may be configured to detect a change in the state of the cardiovascular system based on the waveform data.

[0032] In a medical information processing apparatus according to some exemplary embodiments, the fundus blood flow data may include two or more pieces of waveform data respectively acquired from the patient in two or more different periods, and the data processing unit may be configured to detect a change in the state of the cardiovascular system by comparing the two or more pieces of waveform data.

[0033] In a medical information processing apparatus according to some exemplary embodiments, the fundus blood flow data may include either or both of the blood flow velocity data and the blood flow volume data in the fundus artery of the patient, and the data processing unit may be configured to detect a change in the state of the cardiovascular system based on either or both of the blood flow velocity data and the blood flow volume data.

[0034] In a medical information processing apparatus according to some exemplary embodiments, the auscultation sound data may include lung sound data.

[0035] In a medical information processing apparatus according to some exemplary embodiments, the data reception unit may be further configured to receive either or both of body temperature data and heartbeat data acquired from the patient.

[0036] A medical information processing apparatus according to some exemplary embodiments may further include a transmission unit that transmits information generated by the data processing unit to a doctor terminal located at a remote position with respect to at least one device used to acquire the at least two data from the patient.

Advantages of the Invention

[0037] According to an exemplary embodiment, it is possible to improve the accuracy of processing for detecting symptoms associated with an infectious disease and signs of exacerbation.

Brief Description of the Drawings

[0038]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0039] In the present disclosure, some exemplary aspects of a medical system and a medical information processing apparatus will be described. Some exemplary aspects detect changes in the state of the circulatory system associated with an infectious disease by computer-processing at least two types of data among blood oxygen data, auscultatory sound data, eye image data, and eye blood flow data. This computer processing may include diagnostic inference. This diagnostic inference is executed, for example, by one of an algorithm using a learned model (inference model) constructed by machine learning and an algorithm not using a learned model, or by a combination thereof.

[0040] The types of data subjected to computer processing are not limited to blood oxygen data, auscultatory sound data, eye image data, and eye blood flow data, and may include, for example, biological data (such as body temperature data and heartbeat data) acquired from a patient by an inspection device, and data (such as electronic medical record data, interview data, and patient background information) stored in a storage device (such as a database). Examples of patient background information include age, treatment history, medical history, medication history, and surgical history.

[0041] Exemplary aspects enable highly accurate detection of complex physiological events such as symptoms of diseases associated with infectious diseases and signs of disease progression by comprehensively processing data such as blood oxygen data, auscultatory sound data, eye image data, and eye blood flow data. In particular, exemplary aspects enable highly accurate detection of changes in the state of the circulatory system associated with an infectious disease. In addition, some exemplary aspects have been devised in consideration of the background as described below and can achieve corresponding effects.

[0042] Medical workers such as doctors and nurses are exposed to the risk of nosocomial infection. For example, during the pandemic of Coronavirus Disease 2019 (COVID-19) that occurred in 2020, cluster infections occurred in medical institutions where a large number of patients flocked, and the risk of infection to medical workers became a major problem. In addition, the increase in the risk of infection to medical workers can occur not only during an infectious disease epidemic but also when a disaster or major accident occurs.

[0043] Generally, to reduce the risk of infection, it is important to ensure sufficient distance between people, so-called social distancing, but it is not easy to achieve this in standard medical care. For example, when using a stethoscope to listen to sounds generated by the heart, lungs, blood vessels, etc., or when using a slit lamp microscope to observe the eyes, doctors and the like need to be right next to the patient to perform the treatment.

[0044] Some exemplary aspects may be configured such that the result of processing based on at least two of the aforementioned data can be provided to a doctor terminal at a remote location with respect to a device (data processing unit, inspection device) that has acquired these data from a patient. Also, some exemplary aspects may be configured such that the data processing unit (inspection device) can be operated from a remote location. According to these configurations, it becomes possible to use the data obtained from examinations (auscultation, slit lamp examination, etc.) that could not be performed conventionally without being right next to the patient for diagnosis. That is, according to some exemplary aspects, it becomes possible to optimize social distancing between the patient and the medical worker, and it also becomes possible to detect complex physiological events such as symptoms and signs of exacerbation with high accuracy.

[0045] Here, the "remote location" only needs to be a positional relationship that can ensure social distancing between the patient and the medical staff. For example, the doctor terminal may be installed in a different room from the inspection device, or may be installed in a different facility from the inspection device. Also, the device (operation device, operation unit) for remotely operating the inspection device may be installed in a different room from the inspection device, or may be installed in a different facility from the inspection device.

[0046] In addition, when the inspection is carried out under a sufficient infectious disease prevention system such as when wearing full protective clothing, it is not necessary to ensure social distancing. In cases where only some inspections (specific inspections) are carried out under a sufficient infectious disease prevention system, some exemplary aspects may be configured to provide information to the doctor terminal at a remote location for each of the inspection devices used in inspections other than the specific inspections.

[0047] The matters described in the documents cited in this specification and any other arbitrary known technologies can be used to modify the exemplary aspects. This modification may be any of addition, combination, substitution, deletion, omission, and other processing, for example.

[0048] At least a portion of the functionality of the elements described in this disclosure may be implemented using circuitry or processing circuitry. The circuitry or processing circuitry may be a general-purpose processor, a dedicated processor, an integrated circuit, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), a programmable logic device (e.g., an SPLD (Simple Programmable Logic Device), a CPLD (Complex Programmable Logic Device), an FPGA (Field Programmable Gate Array)), a conventional circuitry, and any combination thereof, configured and / or programmed to perform at least a portion of the disclosed functionality. A processor may be regarded as a processing circuitry or circuitry including transistors and / or other circuitry. In this disclosure, terms such as circuitry, circuit, computer, processor, unit, means, part, or the like may include hardware that performs at least a portion of the disclosed functionality and / or hardware programmed to perform at least a portion of the disclosed functionality. The hardware may be the hardware disclosed herein or may be known hardware programmed and / or configured to perform at least a portion of the disclosed functionality. Where the hardware is a processor that may be regarded as a type of circuitry, terms such as 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.

[0049] The exemplary aspects described below may be arbitrarily combined. For example, it is possible to at least partially combine two or more exemplary aspects.

[0050] <Configuration of a Medical System> Examples of the configuration of a medical system according to exemplary embodiments will be described. 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 operating device 2.

[0051] 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, for example, or may form a network spanning multiple facilities. The communication technology applied to this communication line may be arbitrary and may be any of various known communication technologies such as wired communication, wireless communication, and short-range communication. The connection mode between the data processing unit 20 and the output unit 30 may be the same. Alternatively, the data processing unit 20 and the output unit 30 may be functional units installed on the same computer.

[0052] The operating device 2 is used for a medical staff member to remotely operate the data acquisition unit 10 (inspection device). Also, the operating device 2 is used for a medical staff member (examiner) to provide instructions and the like to a patient (subject) being examined using the data acquisition unit 10 (inspection device). The operating device 2 includes, for example, a computer, an operation panel, and the like.

[0053] The data acquisition unit 10 is configured to acquire ophthalmic data from a patient, and in particular, is configured to acquire at least two types of data from the patient among blood oxygen data, auscultation sound data, eye image data, and eye blood flow data.

[0054] The device for acquiring blood oxygen data from a patient (blood oxygen measuring device) may be, for example, a pulse oximeter described in Japanese Patent Application Laid-Open No. 2019-111010. The type of blood oxygen data detected by the blood oxygen measuring device is arbitrary and may be, for example, at least one of oxygen saturation data, oxygen content data, and oxygen supply amount data.

[0055] An apparatus for acquiring auscultatory sound data from a patient (auscultatory sound measurement apparatus) may be, for example, an electronic stethoscope described in Japanese Patent Application Laid-Open No. 2017-198. The type of auscultatory sound detected by the auscultatory sound measurement apparatus is arbitrary, and may be, for example, at least one of tracheal breath sound data, bronchial breath sound data, alveolar breath sound data (lung sound data), heart sound data, and blood flow sound data.

[0056] An apparatus for acquiring eye image data from a patient (ophthalmic imaging apparatus) may be any ophthalmic modality apparatus. Applicable ophthalmic modalities may be, for example, a photographic type modality or a scanning type modality. Examples of the types of ophthalmic imaging apparatuses include an optical coherence tomography apparatus, a fundus camera, a slit lamp microscope, a scanning laser ophthalmoscope, and a surgical microscope. Further, the ophthalmic imaging apparatus may be a fundus imaging apparatus capable of acquiring fundus image data. The fundus image data is, for example, image data in which fundus blood vessels are depicted and is used for analysis of blood vessel running patterns and the like.

[0057] The optical coherence tomography apparatus and / or the fundus camera may be, for example, an apparatus in which various imaging preparation operations are automated, as described in Japanese Patent Application Laid-Open No. 2020-44027. The imaging preparation operation is an operation executed to adjust imaging conditions, and examples thereof include alignment adjustment, focus adjustment, optical path length adjustment, polarization adjustment, and light amount adjustment. Further, an operation for maintaining good imaging conditions achieved by the imaging preparation operation may be automatically executable. Examples of such operations include automatic alignment adjustment (tracking) according to eye movement and automatic optical path length adjustment (Z lock) according to eye movement. These automatic operations are effective, for example, in examinations that can be performed without the examiner being present.

[0058] Eye image data (optical coherence tomography image data) acquired by an optical coherence tomography apparatus may be, for example, at least one of three-dimensional image data obtained by applying a three-dimensional scan to the fundus oculi, projection image data of the three-dimensional image data, and optical coherence tomography angiography (OCTA) image data.

[0059] Eye image data (fundus camera image data) acquired by a fundus camera may be, for example, at least one of color fundus image data, infrared fundus image data, and fluorescence angiography fundus image data (such as fluorescein angiography image data and indocyanine green angiography image data).

[0060] The scanning laser ophthalmoscope may be, for example, the apparatus described in JP-A-2014-226156. Eye image data (scanning laser image data) acquired by the scanning laser ophthalmoscope may be, for example, at least one of color fundus image data, monochromatic fundus image data, and fluorescence angiography fundus image data.

[0061] The slit lamp microscope may be, for example, the apparatus described in JP-A-2019-213734, which is effective for remote imaging. Eye image data acquired by the slit lamp microscope may be, for example, at least one of color fundus image data, anterior segment cross-sectional image data, and anterior segment three-dimensional image data.

[0062] Regarding other types of ophthalmic imaging devices, any known device can be adopted. For example, the surgical microscope described in JP-A-2002-153487, which is effective for remote surgery, can be used as an ophthalmic imaging device.

[0063] An apparatus (ocular blood flow measurement apparatus) for obtaining ocular blood flow data from a patient may be an apparatus of any measurement method. The ocular blood flow data includes, for example, data representing blood flow dynamics in the fundus blood vessels of the patient (fundus blood flow data). The ocular blood flow measurement apparatus may be, for example, an optical coherence tomography apparatus described in Japanese Patent Application Laid-Open No. 2019-54994, Japanese Patent Application Laid-Open No. 2020-48730, etc. Ocular blood flow measurement apparatuses in some exemplary embodiments can acquire waveform data representing the time-series change in blood flow velocity in the fundus artery of the patient, and blood flow velocity data and / or blood flow volume data in the fundus artery of the patient by utilizing these known techniques. The waveform data is typically a time-series change graph of blood flow velocity represented by a two-dimensional coordinate system with time on the horizontal axis and blood flow velocity on the vertical axis. Note that the apparatus that can be used as the ocular blood flow measurement apparatus is not limited to an optical coherence tomography apparatus, and may be, for example, a laser speckle flowgraphy (LSFG) apparatus described in Japanese Patent Application Laid-Open No. 2017-504836, etc.

[0064] As described above, the types of data that can be acquired by the data acquisition unit 10 in exemplary embodiments are not limited to blood oxygen data, auscultatory sound data, ocular image data, and ocular blood flow data. In some exemplary embodiments, the data acquisition unit 10 may be able to acquire body temperature data and / or heartbeat data. The body temperature data of the patient is acquired, for example, using a thermometer in the system described in Japanese Patent Application Laid-Open No. 2018-29964. The heartbeat data (heart rate, electrocardiogram waveform, etc.) of the patient is acquired, for example, using a heartbeat / electrocardiograph described in Japanese Patent Application Laid-Open No. 2017-148577.

[0065] Some exemplary aspects may be capable of acquiring any type of data such as blood flow data, pulse data, respiratory function data, blood pressure data, etc. For example, using any one of an ultrasonic blood flow meter described in Japanese Patent Application Laid-Open No. 2008-36095, a laser blood flow meter described in Japanese Patent Application Laid-Open No. 2008-154804, and an electromagnetic blood flow meter described in Japanese Patent Application Laid-Open No. 10-328152, it is possible to acquire blood flow data (such as blood flow velocity data, blood flow volume data, blood flow velocity distribution data, etc.) and pulse data (such as pulse rate, etc.). Also, for example, using a respiratory monitoring system described in Japanese Patent Application Laid-Open No. 2019-527117, it is possible to acquire respiratory function data (such as respiratory rate data, tidal volume data, minute ventilation volume data, intratracheal pressure data, air velocity and air flow rate data, ventilation work volume data, inhaled gas concentration data, inhaled water vapor data, etc.). Also, for example, using a blood pressure meter in a system described in Japanese Patent Application Laid-Open No. 2018-29964, it is possible to acquire blood pressure data (such as blood pressure value, etc.) and pulse data (such as pulse rate, etc.).

[0066] Some exemplary aspects may be configured to process eye characteristic data acquired by an ophthalmic measurement device. The eye characteristic data is data indicating the state of the eye (characteristic data such as numerical data, evaluation data, etc.). As types of ophthalmic measurement devices, in addition to the aforementioned eye blood flow measurement device, there are an eye refraction measurement device, a tonometer, a corneal endothelial cell inspection device (specular microscope), a higher-order aberration measurement device (wavefront analyzer), a visual acuity test device, a perimeter, a microperimeter, an axial length measurement device, an electroretinogram test device, a binocular vision function test device, a color vision test device, etc. Examples of an eye refraction measurement device (refractometer, keratometer), a tonometer (non-contact tonometer), a specular microscope, and a wavefront analyzer are each described in Japanese Patent Application Laid-Open No. 2018-38518. The visual acuity test device may be, for example, a device capable of remote visual acuity testing described in Japanese Patent Application Laid-Open No. 2018-110687. For other types of ophthalmic measurement devices, any known device can be adopted.

[0067] In this aspect, at least one of the inspection devices (for example, an electronic stethoscope, an ophthalmic imaging device, an ophthalmic measuring device, etc.) included in the data acquisition unit 10 may be capable of remote operation and remote control.

[0068] As an example, considering the risk of infection to medical staff, the examination room where an examination using an inspection device is performed and the operation room where the operation of this inspection device is performed can be separated. In the examination room, in addition to the inspection device, there are provided a speaker and a display for outputting instructions (such as voice, image, video, etc.) of the operator in the operation room, a video camera for photographing the subject (patient) in the examination room, a microphone for inputting the voice of the subject, a computer connected to the inspection device, and the like.

[0069] On the other hand, in the operation room, an operating device 2 for remotely operating the inspection device is provided. The operating device 2 is provided with a computer, an operation panel, a display, a video camera, a microphone, and the like. The computer executes processing for remote operation. The computer is connected to the inspection device in the examination room. The operation panel, the video camera, and the microphone are used for inputting instructions to the subject. The display displays the data acquired by the inspection device and information for remote operation (such as a screen, information from the examination room, etc.).

[0070] With such a configuration, the operator (medical staff) in the operation room can remotely operate the inspection device in the examination room using, for example, an application programming interface (API), and can send instructions to the subject using a videophone or the like. As a result, the subject can undergo the examination alone according to the instructions of the operator at a remote location, and thus it is possible to significantly reduce the risk of infection from the subject to the operator.

[0071] In order to more suitably perform an examination on a single patient (subject), the above-described examination apparatus with automated preparation operations can be used. In this case, it is considered that the examination can be performed without requiring instructions from an operator. In some cases, it may not be necessary to arrange an assistant (such as an operator). However, since it is also assumed that it may be difficult for some patients to undergo the examination alone, for example, an assistant may be made to wait at a remote location, or an 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 an anthropomorphic computer system (typically, an automatic response system using artificial intelligence technology).

[0072] FIG. 2 shows an example of a data structure for processing (recording, transmitting, etc.) various data acquired by the data acquisition unit 10. The data structure 100 in this example includes a blood oxygen data section 110, a heart sound data section 120, an eye image data section 130, an eye blood flow data section 140, a body temperature data section 150, a heart rate data section 160, and an arbitrary data section 170.

[0073] The blood oxygen data section 110 is an area (such as a folder) where blood oxygen data acquired by a blood oxygen measuring device in the data acquisition unit 10 is recorded.

[0074] The heart sound data section 120 is an area where heart sound data acquired by a heart sound measuring device in the data acquisition unit 10 is recorded.

[0075] A lung sound data section 121 is provided in the heart sound data section 120. The lung sound data section 121 is an area where lung sound data acquired by a heart sound measuring device is recorded. Note that the sub-area provided in the heart sound data section 120 is not limited to the lung sound data section 121, and may be an area where any type of heart sound data is recorded.

[0076] The eye image data section 130 is an area where eye image data acquired by an ophthalmic imaging device in the data acquisition unit 10 is recorded. A fundus image data section 131 and a color fundus image data section 132 are provided in the eye image data section 130.

[0077] The fundus image data section 131 records image data used, for example, in the analysis of the running pattern of fundus blood vessels. Examples of the fundus image data recorded in the fundus image data section 131 include optical coherence tomography image data (3D image data, projection image data, optical coherence tomography angiography image data, etc.), fundus camera image data (color fundus image data, infrared fundus image data, fluorescence angiography fundus image data, etc.), scanning laser image data (color fundus image data, monochromatic fundus image data, fluorescence angiography fundus image data, etc.), and color fundus image data obtained by a slit lamp microscope.

[0078] The color fundus image data section 132 records image data used, for example, in the analysis of the color tone of the fundus. Examples of the fundus image data recorded in the color fundus image data section 132 include fundus camera image data (color fundus image data), scanning laser image data (color fundus image data), and color fundus image data obtained by a slit lamp microscope.

[0079] When the same image data is used for both the blood vessel running pattern analysis and the color tone analysis, it is not necessary to record this image data in both the fundus image data section 131 and the color fundus image data section 132. For example, by recording the image data in either the fundus image data section 131 or the color fundus image data section 132 and attaching information (such as a tag) indicating that it can also be used for the corresponding application to the other, it becomes possible to provide a single image data for both applications.

[0080] The eye blood flow data section 140 is an area where the eye blood flow data obtained by the eye blood flow measurement device in the data acquisition section 10 is recorded. The eye blood flow data section 140 is provided with a fundus blood flow data section 141. The fundus blood flow data section 141 records data representing the blood flow dynamics in the fundus blood vessels (fundus blood flow data).

[0081] The fundus blood flow data unit 141 is provided with a waveform data unit 142, a blood flow velocity data unit 143, and a blood flow volume data unit 144. The waveform data unit 142 records waveform data representing the time-series change in the blood flow velocity obtained by blood flow measurement of the fundus artery. The blood flow velocity data unit 143 records the blood flow velocity data obtained by blood flow measurement of the fundus artery. The blood flow volume data unit 144 records the blood flow volume data obtained by blood flow measurement of the fundus artery.

[0082] In consideration of the fact that waveform data is generated from blood flow velocity data at a plurality of different times, blood flow velocity data at a specific time can be obtained from the waveform data, and blood flow volume data can be calculated from the waveform data and the blood flow velocity data, etc., it is not necessary to provide all of the waveform data unit 142, the blood flow velocity data unit 143, and the blood flow volume data unit 144. Typically, it is possible to configure to record only the types of data provided for the processes executed by the data processing unit 20 in the eye blood flow data unit 140. Alternatively, for example, only the waveform data may be recorded in the eye blood flow data unit 140, and the data processing unit 20 may be configured to obtain blood flow velocity data and blood flow volume data from this waveform data.

[0083] The body temperature data unit 150 is an area where the body temperature data obtained by the thermometer in the data acquisition unit 10 is recorded. The heart rate data unit 160 is an area where the heart rate data obtained by the heart rate meter (electrocardiograph) in the data acquisition unit 10 is recorded.

[0084] The arbitrary data unit 170 is an area where arbitrary types of data are recorded. For example, in the arbitrary data unit 170, data obtained by inspection devices other than the above in the data acquisition unit 10 may be recorded. Also, in the arbitrary data unit 170, electronic medical record data, interview data, etc. may be recorded. Further, in the arbitrary data unit 170, information about the patient (subject) may be recorded. Examples of patient information include identifiers, patient background information, etc.

[0085] The data processing unit 20 executes various data processes. The data processing unit 20 of the present aspect is configured to process the data acquired by the data acquisition unit 10 in order to detect changes in the state of the circulatory system associated with infectious diseases.

[0086] Examples of the state of the circulatory system (diseases, symptoms, physiological events, etc.) associated with infectious diseases include pneumonia, hypoxemia, circulatory dysfunction (such as abnormal cerebral blood flow), etc. associated with coronavirus disease 2019 (COVID-19). The present aspect is configured to be able to detect changes in at least one of these states.

[0087] According to the Japanese Journal of Internal Medicine, Vol. 109, pp. 392-395 (2020), the severity distribution of coronavirus disease 2019 (COVID-19) was 80.9% for mild cases (no pneumonia to mild pneumonia), 13.8% for moderate cases (dyspnea, respiratory rate ≥ 30 times / min, oxygen saturation (SpO2) ≤ 93%, or rapid deterioration of lung shadow), 4.7% for severe cases (any of respiratory failure, shock, and multiple organ failure), and 0.6% for unknown cases. Referring to this, it is considered that the oxygen saturation decreases as the hypoxemia (hypoxemia associated with pneumonia) associated with coronavirus disease 2019 (COVID-19) progresses. Against this background, in the present aspect, the blood oxygen data acquired by the blood oxygen measuring device in the data acquisition unit 10 can be used as an evaluation index for hypoxemia associated with coronavirus disease 2019 (COVID-19). The same may apply to other infectious diseases.

[0088] In the case report of the Japanese Society of Infectious Diseases, "One case where COVID-19 infection was not detected at the time of hospitalization. 'The biggest weapon of the new coronavirus is a stealth attack' - A warning bell for general hospitals -" (Japanese Society of Infectious Diseases homepage: http: / / www.kansensho.or.jp / uploads / files / topics / 2019ncov / covid19_casereport_200403_2.pdf), there is a reported case where, despite being an infected person with coronavirus disease 2019 (COVID-19), no significant decrease in oxygen saturation or increase in body temperature was observed during the follow-up hospitalization for other diseases. It should be noted that the occurrence of pneumonia associated with coronavirus disease 2019 (COVID-19) was confirmed by chest plain CT. On the other hand, fever and palpitations are listed as the main symptoms of coronavirus disease 2019 (COVID-19). Considering such a background, in this aspect, data other than blood oxygen data (for example, body temperature data, heart rate data, etc.) can be used as an evaluation index for pneumonia associated with coronavirus disease 2019 (COVID-19). The same may be true for other infectious diseases. It should be noted that, as in the above case report, for data affected by other factors, such as body temperature data during the use of antipyretics and analgesics, care must be taken in handling.

[0089] According to Irena Tsui et al., "Retinal Vascular Patterns in Adults with Cyanotic Congenital Heart Disease", Journal Seminars in Ophthalmology, Volume 24, 2009, Issue 6, it is known that the tortuosity of fundus blood vessels increases due to the continuation of hypoxemia. Therefore, it is assumed that the vascular pattern grasped from fundus image data changes as hypoxemia progresses. Considering such a background, in this aspect, the fundus image data acquired by the ophthalmic imaging device in the data acquisition unit 10 can be used as an evaluation index for hypoxemia associated with coronavirus disease 2019 (COVID-19). The same may be true for other infectious diseases.

[0090] According to Adrian Spiteri, "The blue patient" (http: / / dx.doi.org / 10.1136 / emerged-2016-205729), it is known that hypoxemia can change the color tone of biological tissues. This phenomenon is due to the decrease in oxygenated hemoglobin in arterial blood as a result of the decrease in blood oxygen concentration, resulting in a color similar to that of venous blood. Considering that the color tone changes are prominent in areas where capillaries can be seen through, such as the tongue and lips, it is assumed that the color tone of the fundus of the eye also changes significantly. Considering such a background, in this aspect, the color fundus image data obtained by the ophthalmic imaging device in the data acquisition unit 10 can be used as an evaluation index for hypoxemia associated with coronavirus disease 2019 (COVID-19). The same may be true for other infectious diseases.

[0091] In the early (mild) stage of coronavirus disease 2019 (COVID-19), it is considered that the sympathetic nerve becomes dominant due to fever, dehydration, and hypoxemia. As a result, the heart rate and cardiac output increase, the heart sound becomes stronger, and the blood pressure rises. According to Kui Liu et al., "Clinical characteristics of novel cononavirus cases in tertiary hospitals in Hubei Province", Chinese Medical Journal, 2020; Vol(No), (DOI:10.1097 / CM9.0000000000000744), in a study of 137 patients with coronavirus disease 2019 (COVID-19), the initial symptom (early symptom) of 7.3% of the patients was palpitations.

[0092] When an increase in arterial blood flow is observed in this way, it is considered that the waveform of arterial blood flow tends to be "Large & bounding" among the five pulse types in the following literature: Zhaopeng Fan et al., "Pulse Wave Analysis", Advanced Biomedical Engineering, Dr. Gaetano Gargiulo (Ed), 2011 (ISBN: 978-953-307-555-6).

[0093] On the other hand, according to Yasemin Saplakoglu, "The mysterious connection between the coronavirus and the heart", LIVE SCIENCE (https: / / www.livescience.com / how-coronavirus-affects-heart.html), as the severity of coronavirus disease 2019 (COVID-19) progresses, it is known that blood vessels dilate due to systemic inflammation, blood pressure decreases, and cardiomyocytes are damaged by inflammation and hypoxia, resulting in reduced cardiac function. The contractility of the myocardium decreases, sufficient cardiac output cannot be achieved, heart sounds become weak, and the stroke volume decreases. In this case, it is considered that the arterial blood flow waveform shape tends to be "small & weak" among the five waveform types described above. At this time, it is considered that the oxygen saturation (SpO2) is further decreased.

[0094] Considering such a background, in this aspect, the ocular blood flow data acquired by the ocular blood flow measuring device in the data acquisition unit 10 and the blood oxygen data acquired by the blood oxygen measuring device can be used as evaluation indicators for the symptoms associated with coronavirus disease 2019 (COVID-19). The same may apply to other infectious diseases.

[0095] According to the following literature, it is known that abnormalities in cardiac function are reflected in the shape of the waveform representing the time-series changes in the blood flow velocity of the retinal artery obtained by optical coherence tomography blood flowmeter: Kana Minamide et al., "What We Can Learn from Fundus Blood Flow Measurement Using Optical Coherence Tomography (OCT)", The Frontier of Computational Science Connecting 23 Advanced Cases, Understanding and Predicting Things by Computation (Modern Science), Chapter 21, 2020. For example, Figure 21.6 (page 255) of the same literature shows a comparison of the retinal artery waveforms of patients with aortic valve stenosis (before and after treatment) and those of normal individuals. Thus, in diseases that cause abnormalities in cardiac output, the shape of the retinal artery waveform changes. Similarly, changes in cardiac function associated with the exacerbation of infectious diseases are thought to appear in the shape of the waveform per heartbeat obtained by optical coherence tomography blood flowmeter. For example, a delay in the time from the start of the heartbeat to reaching the peak indicates a decrease in the systolic function of the heart. Also, a decrease in the waveform bottom area per heartbeat indicates a decrease in cardiac output.

[0096] Considering such a background, in this aspect, the ocular blood flow data obtained by the ocular blood flow measurement device (optical coherence tomography blood flowmeter) in the data acquisition unit 10 can be used as an evaluation index for cardiac function abnormalities (circulatory function abnormalities) associated with coronavirus disease 2019 (COVID-19). The same may apply to other infectious diseases.

[0097] According to the following literature, it is known that the blood flow state of the intracerebral artery (middle cerebral artery) changes due to infectious diseases: Haring HP et al., "Time course of cerebral blood flow velocity in central nervous system infections. A transcranial Doppler sonography study.", Arch Neurol. 1993 Jan;50(1):98-101. In coronavirus disease 2019 (COVID-19), central nervous system symptoms may occur, and a pathological condition similar to encephalitis occurs (viral meningitis). At that time, it is considered that the blood flow throughout the body increases due to systemic inflammation, resulting in an increase in cerebral blood flow. Considering that the ophthalmic artery branches from the same blood vessel as the middle cerebral artery, it is highly likely that blood flow changes also occur in the ophthalmic artery and the retinal artery beyond it. Therefore, it may be possible to detect changes in cerebral blood flow accompanying the exacerbation of infectious diseases from the blood flow velocity values and blood flow volume values of an optical coherence tomography blood flowmeter.

[0098] Considering such a background, in this aspect, the ocular blood flow data acquired by the ocular blood flow measurement device (optical coherence tomography blood flowmeter) in the data acquisition unit 10 can be used as an evaluation index for cerebral blood flow abnormalities associated with coronavirus disease 2019 (COVID-19). The same may apply to other infectious diseases.

[0099] Regarding auscultatory sound data, for example, by applying the technology disclosed in Japanese Patent Application Laid-Open No. 2018-516616 (International Publication No. 2016 / 166318), it can be used as an evaluation index for pneumonia associated with coronavirus disease 2019 (COVID-19). The same may apply to other infectious diseases.

[0100] The data processing unit 20 is configured to execute data processing based on, for example, the above findings in order to detect changes in the cardiovascular system associated with infectious diseases. An example of the configuration of the data processing unit 20 in this aspect is shown in FIG. 3. The data processing unit 20 in this example includes a blood oxygen data processing unit 21, a heart sound data processing unit 22, an eye image data processing unit 23, and an eye blood flow data processing unit 24. The data processing unit 20 may be configured to generate a final output based on outputs from at least two of these processing units 21 to 24.

[0101] The blood oxygen data processing unit 21 may be configured to perform an inferential diagnosis regarding the state (change) of the cardiovascular system associated with an infectious disease by processing the blood oxygen data recorded in the blood oxygen data section 110 of the data structure 100 in FIG. 2 by a processor that operates according to a program created based at least on the above findings regarding blood oxygen. For example, the blood oxygen data processing unit 21 can perform an inferential diagnosis by comparing the oxygen saturation value indicated by the blood oxygen data with a predetermined threshold value.

[0102] Further, the blood oxygen data processing unit 21 may be configured to perform an inferential diagnosis regarding the state (change) of the cardiovascular system associated with an infectious disease by processing the blood oxygen data recorded in the blood oxygen data section 110 using a trained model constructed by, for example, machine learning based at least on the above findings regarding blood oxygen. This machine learning is executed using, for example, training data including clinically collected blood oxygen data and diagnostic result data therefor. This diagnostic result data is obtained, for example, by a doctor or another inference model (trained model) based on the relevant blood oxygen data. The constructed trained model takes the blood oxygen data recorded in the blood oxygen data section 110 as an input and outputs estimated diagnosis data regarding the state (change) of the cardiovascular system associated with an infectious disease.

[0103] The auscultatory sound data processing unit 22 may be configured to perform an inferential diagnosis regarding the state (change) of the cardiovascular system associated with an infectious disease by processing the auscultatory sound data (e.g., the lung sound data recorded in the lung sound data unit 121) recorded in the auscultatory sound data unit 120 of the data structure 100 in FIG. 2 by a processor that operates according to a program created at least based on the above findings regarding auscultatory sounds (such as breathing sounds and heart sounds). For example, the auscultatory sound data processing unit 22 can perform an inferential diagnosis based on the characteristics (sound profile) of the waveform indicated by the auscultatory sound data.

[0104] Further, the auscultatory sound data processing unit 22 may be configured to perform an inferential diagnosis regarding the state (change) of the cardiovascular system associated with an infectious disease by processing the auscultatory sound data (e.g., the lung sound data recorded in the lung sound data unit 121) recorded in the auscultatory sound data unit 120 using a trained model constructed by machine learning based at least on the above findings regarding auscultatory sounds (such as breathing sounds and heart sounds). This machine learning is executed, for example, using training data including clinically collected auscultatory sound data and diagnostic result data therefor. This diagnostic result data is obtained, for example, by a doctor or another inference model (trained model) based on the relevant auscultatory sound data. The constructed trained model takes as input the auscultatory sound data (e.g., the lung sound data recorded in the lung sound data unit 121) recorded in the auscultatory sound data unit 120 and outputs estimated diagnostic data regarding the state (change) of the cardiovascular system associated with an infectious disease.

[0105] The eye image data processing unit 23 may be configured to perform an inferential diagnosis regarding the state (change) of the cardiovascular system associated with an infectious disease by processing the eye image data (for example, the fundus image data recorded in the eye image data unit 130 of the data structure 100 in FIG. 2, such as the fundus image data recorded in the fundus image data unit 131 and / or the color fundus image data recorded in the color fundus image data unit 132) by a processor that operates according to a program created based at least on the above findings regarding the eye image (such as a fundus image). For example, the eye image data processing unit 23 can perform an inferential diagnosis based on the characteristics of the eye image data (such as blood vessel tortuosity, color information, etc.).

[0106] Further, the eye image data processing unit 23 may be configured to perform an inferential diagnosis regarding the state (change) of the cardiovascular system associated with an infectious disease by processing the eye image data (for example, the fundus image data recorded in the eye image data unit 130 of the data structure 100 in FIG. 2, such as the fundus image data recorded in the fundus image data unit 131 and / or the color fundus image data recorded in the color fundus image data unit 132) using a learned model constructed by machine learning based at least on the above findings regarding the eye image (such as a fundus image). This machine learning is executed, for example, using training data including clinically collected eye image data and diagnostic result data corresponding thereto. This diagnostic result data is obtained, for example, by a doctor or another inference model (learned model) based on the relevant eye image data. The constructed learned model takes as input the eye image data (for example, the fundus image data recorded in the fundus image data unit 131 and / or the color fundus image data recorded in the color fundus image data unit 132) recorded in the eye image data unit 130 and outputs estimated diagnostic data regarding the state (change) of the cardiovascular system associated with an infectious disease.

[0107] An example of the eye image data processing unit 23 configured using machine learning is shown in FIG. 4. The eye image data processing unit 23 in this example includes an inference processing unit 230. As described above, the inference processing unit 230 uses a learned model constructed by machine learning using training data including clinical data (eye image data and diagnosis result data) to perform an inference process for deriving information regarding the change in the state of the circulatory system from the eye image data acquired from a patient by the data acquisition unit 10.

[0108] Through such machine learning (supervised learning) based on such training data, a learned model (inference model) is created that takes the eye image data acquired from a patient by the data acquisition unit 10 as input and outputs estimated diagnosis data regarding the change in the state of the circulatory system.

[0109] The inference processing unit 230 includes the learned model obtained in this way, inputs the eye image data acquired from a patient by the data acquisition unit 10 into the learned model, and sends the estimated diagnosis data output from the learned model to the output unit 30.

[0110] The machine learning algorithms that can be used in the exemplary embodiments are not limited to supervised learning, and may be, for example, 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.

[0111] The machine learning techniques that can be used in the exemplary embodiments are arbitrary, and may be, for example, any technique such as neural networks, support vector machines, decision tree learning, association rule learning, genetic programming, clustering, Bayesian networks, representation learning, extreme learning machines, etc., or may be a combination of any two or more techniques.

[0112] An example of the configuration of the inference processing unit 230 is shown in FIG. 5. The inference processing unit 230 in this example includes a first learned model 231 and a second learned model 232.

[0113] The first trained model 231 is constructed by machine learning using training data including fundus image data and diagnostic result data. For example, the first trained model 231 includes a convolutional neural network. This convolutional neural network includes, for example, an input layer into which fundus image data is input, a convolutional layer that applies filtering (convolution) to the input fundus image data to create a feature map regarding the curvature of blood vessels, a pooling layer that performs data compression while retaining the features obtained in the convolutional layer, a fully connected layer that extracts characteristic findings from all the data obtained in the pooling layer and makes a determination, and an output layer that outputs the data obtained in the fully connected layer. By inputting the fundus image data acquired from a patient by the data acquisition unit 10 into the first trained model 231, information regarding the state change of the circulatory system considering the curvature state of blood vessels is generated. By using such a first trained model 231, the data processing unit 20 can detect the state change of the circulatory system based on the running pattern of the blood vessels depicted in the fundus image data of the patient.

[0114] Note that the features regarding blood vessels are not limited to the running pattern. For example, in order to acquire information regarding the state change of the circulatory system, the change in blood vessel diameter (dilation / constriction) can be considered. The blood vessel diameter can be obtained, for example, by analyzing fundus image data or optical coherence tomography image data. Regarding blood vessel diameter measurement, for example, the techniques described in JP-A-2016-43155, JP-A-2020-48730, etc. can be used.

[0115] The second trained model 232 is constructed by machine learning using training data including color fundus image data and diagnosis result data. For example, the second trained model 232 includes a convolutional neural network. This convolutional neural network includes, for example, an input layer into which 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 regarding color information (e.g., R value, G value, B value), a pooling layer that performs data compression while retaining the features obtained in the convolutional layer, a fully connected layer that extracts characteristic findings from all the data obtained in the pooling layer and makes a determination, and an output layer that outputs the data obtained in the fully connected layer. By inputting the color fundus image data acquired from a patient by the data acquisition unit 10 into the second trained model 232, information regarding the change in the state of the circulatory system considering the color tone of the fundus is generated. By using such a second trained model 232, the data processing unit 20 can detect the change in the state of the circulatory system based on the color information in the color fundus image data of the patient.

[0116] A trained model that processes data of types other than eye image data may have the same configuration as described above. When processing time-series data such as waveform data, progress observation data, video data, or audio data, the trained model may include a recurrent neural network. Also, the training data used for machine learning may include data created by a computer based on clinical data. Further, the machine learning may include transfer learning.

[0117] The ocular blood flow data processing unit 24 may be configured to perform inferential diagnosis regarding the state (change) of the cardiovascular system accompanying an infectious disease by processing the ocular blood flow data (for example, at least one of the waveform data recorded in the waveform data unit 142, the blood flow velocity data recorded in the blood flow velocity data unit 143, and the blood flow volume data recorded in the blood flow volume data unit 144) recorded in the ocular blood flow data unit 140 of the data structure 100 in FIG. 2 by a processor that operates according to a program created based at least on the above findings regarding ocular blood flow (such as fundus blood flow). For example, the ocular blood flow data processing unit 24 can perform inferential diagnosis based on the characteristics of the ocular blood flow data (for example, parameters indicating the characteristics of the waveform).

[0118] Further, the ocular blood flow data processing unit 24 may be configured to perform inferential diagnosis regarding the state (change) of the cardiovascular system accompanying an infectious disease by processing the ocular blood flow data (for example, at least one of the waveform data recorded in the waveform data unit 142, the blood flow velocity data recorded in the blood flow velocity data unit 143, and the blood flow volume data recorded in the blood flow volume data unit 144) recorded in the ocular blood flow data unit 140 using a learned model constructed by machine learning based at least on the above findings regarding ocular blood flow (such as fundus blood flow). This machine learning is executed using, for example, training data including clinically collected ocular blood flow data and diagnostic result data therefor. This diagnostic result data is obtained by a doctor or another inference model (learned model) based on the relevant ocular blood flow data, for example. The constructed learned model takes as input the ocular blood flow data (for example, at least one of the waveform data recorded in the waveform data unit 142, the blood flow velocity data recorded in the blood flow velocity data unit 143, and the blood flow volume data recorded in the blood flow volume data unit 144) recorded in the ocular blood flow data unit 140 and outputs estimated diagnostic data regarding the state (change) of the cardiovascular system accompanying an infectious disease.

[0119] When the fundus blood flow data includes waveform data, the data processing unit 20 can detect changes in the state of the circulatory system based on this waveform data. In this process, typically, parameters indicating the characteristics of the waveform are considered.

[0120] When two or more pieces of waveform data respectively obtained from a patient in two or more different periods are included in the fundus blood flow data (for example, two or more pieces of waveform data are obtained by follow-up observation), the data processing unit 20 can detect changes in the state of the circulatory system by comparing these waveform data. In this process, typically, changes in parameters indicating the characteristics of the waveform are considered.

[0121] When either or both of the blood flow velocity data and the blood flow volume data in the fundus artery of a patient are included in the fundus blood flow data, the data processing unit 20 can detect changes in the state of the circulatory system based on either or both of the blood flow velocity data and the blood flow volume data. In this process, typically, the magnitude of the value is considered.

[0122] When two or more pieces of blood flow velocity data respectively obtained from a patient in two or more different periods are included in the fundus blood flow data (for example, two or more pieces of blood flow velocity data are obtained by follow-up observation), the data processing unit 20 can detect changes in the state of the circulatory system by comparing these blood flow velocity data. In this process, typically, changes in the value of the blood flow velocity are considered.

[0123] When two or more pieces of blood flow volume data respectively obtained from a patient in two or more different periods are included in the fundus blood flow data (for example, two or more pieces of blood flow volume data are obtained by follow-up observation), the data processing unit 20 can detect changes in the state of the circulatory system by comparing these blood flow volume data. In this process, typically, changes in the value of the blood flow volume are considered.

[0124] Similarly, for other types of data (such as body temperature data, heart rate data, blood pressure data, etc.), processing can be performed using a processor that operates according to a program created based at least on corresponding findings, and / or a trained model constructed by machine learning based at least on corresponding findings.

[0125] According to the data processing unit 20 of this embodiment having such a configuration, as state changes of the circulatory system accompanying an infectious disease, it is possible to detect the onset of pneumonia, changes in the state of pneumonia (aggravation, alleviation, asymptomatic), the onset of hypoxemia, changes in the state of hypoxemia (aggravation, alleviation, asymptomatic), and changes in the state of cerebral blood flow (aggravation, alleviation, asymptomatic), etc. Note that the data processing unit 20 may be configured to be able to detect other state changes accompanying an infectious disease, or may be configured to be able to detect arbitrary state changes (regardless of the relationship with an infectious disease).

[0126] Also, the subject (disease, symptom, etc.) of the inferential diagnosis executed by the data processing unit 20 may be arbitrary. For example, the data processing unit 20 may be configured to execute inferential processing regarding pneumonia. More specifically, the data processing unit 20 may be configured to execute inferential processing for obtaining the probability that the target patient has pneumonia (pneumonia prevalence probability), inferential processing for obtaining the probability that the target patient has an infectious disease accompanied by pneumonia (infectious disease prevalence probability), inferential processing for obtaining the severity of pneumonia of the target patient (pneumonia severity), inferential processing for obtaining the severity of an infectious disease accompanied by pneumonia of the target patient (infectious disease severity), etc.

[0127] The infectious disease accompanied by pneumonia may be, for example, coronavirus disease 2019 (COVID-19). Also, the severity of the infectious disease accompanied by pneumonia may be related to, for example, arbitrary symptoms (such as cytokine storm, fever, conjunctival congestion, nasal congestion, headache, cough, sore throat, sputum, bloody sputum, fatigue, shortness of breath, nausea, vomiting, diarrhea, muscle pain, joint pain, chills, etc.), and may be related to arbitrary underlying diseases (such as diabetes, heart failure, respiratory diseases (such as chronic obstructive pulmonary disease (COPD)), application of hemodialysis, administration of specific drugs (such as immunosuppressants, anticancer drugs, etc.)).

[0128] The output unit 30 outputs the result of the process executed by the data processing unit 20. The mode of the output process is arbitrary and may be any of, for example, transmission, display, recording, and printing. The information output by the output unit 30 may be the result of the process itself executed by the data processing unit 20 (the detection result of the change in the cardiovascular system state associated with the infectious disease), information including the process result, or information obtained by processing the process result. For example, the medical system 1 may further include a report creation unit (not shown) that creates a report based on the detection result of the change in the cardiovascular system state obtained by the data processing unit 20. In this case, the output unit 30 can output the created report.

[0129] A configuration example of the output unit 30 is shown in FIG. 1. The output unit 30 in this example includes a transmission unit 31. The transmission unit 31 transmits the result of the process executed by the data processing unit 20 toward the doctor terminal 3 at a remote location with respect to the data acquisition unit 10.

[0130] Here, the transmission from the output unit 30 to the doctor terminal 3 may be direct transmission or indirect transmission. Direct transmission is a mode of transmitting the result of the process (detection result, report, etc.) from the output unit 30 to the doctor terminal 3. Indirect transmission is a mode of transmitting the result of the process to a device other than the doctor terminal 3 (such as a server, database, etc.) and providing the result of the process to the doctor terminal 3 via the device.

[0131] In this way, by arranging the doctor terminal 3 at a remote location with respect to the data acquisition unit 10 and configuring to provide the doctor (medical staff) with the process result (or information based thereon) acquired by the data processing unit 20 based on the data acquired from the patient by the data acquisition unit 10, it is possible to ensure social distancing between the doctor (medical staff) and the patient and reduce the infection risk of the doctor (medical staff).

[0132] <Usage form of the medical system> An example of the usage mode of the medical system 1 according to the exemplary embodiment will be described with reference to the flowchart of FIG. 6.

[0133] (S1: Construct a trained model) As a preparation for the operation of the medical system 1, a trained model used in the data processing unit 20 is constructed. Note that the processing performed at this stage may be an update (parameter adjustment / updating) of the already-operated trained model.

[0134] (S2: Install the trained model in the data processing unit) As a further preparation for the operation of the medical system 1, the trained model constructed in step S1 is installed in the data processing unit 20. In this step, for example, the trained model constructed in step S1 is transmitted to the medical system 1 through a communication line.

[0135] (S3: Acquire data from the patient) The subject may be, for example, a patient with a confirmed diagnosis of coronavirus disease 2019 (COVID-19) or a suspected patient with coronavirus disease 2019 (COVID-19). The data acquisition unit 10 of the medical system 1 acquires data of predetermined items from the patient. In this embodiment, the data acquisition unit 10 acquires at least two types of data among blood oxygen data, auscultation sound data, eye image data, and eye blood flow data from the patient. In addition to these types, any type of data such as body temperature data, heart rate data, blood pressure data, and eye characteristic data can be acquired from the patient.

[0136] At least a part of the examinations performed in this step may be remote examinations using the operating device 2.

[0137] The acquired data is recorded, for example, according to the data structure 100 of FIG. 2. Thereby, a data package about the patient is obtained.

[0138] As described above, in this embodiment, two or more types of data are acquired from the patient, but the timing of acquiring these data is arbitrary. For example, the second data may be acquired after the first data is acquired, the first data may be acquired after the second data is acquired, or the acquisition of the first data and the acquisition of the second data may be performed in parallel.

[0139] Also, the difference (time difference) in the acquisition timing of two or more types of data is also arbitrary. For example, when acquiring at least fundus blood flow data and heartbeat data, there is originally a time lag between the state of fundus blood flow and the state of heartbeat, so it is not necessary to acquire both simultaneously, and there may be a time difference of about 10 minutes, for example. However, regarding conditions (such as posture) that affect the blood circulation state, it is considered desirable to have the same conditions at the time of acquiring both pieces of data. The same applies to conditions (such as diet, time zone, drug administration, etc.) that affect other test parameters.

[0140] (S4: Input data to the data processing unit) The data acquired in step S3 is sent to the data processing unit 20. At least a part of the data input to the data processing unit 20 is input to the learned model constructed in step S1.

[0141] (S5: Generate detection data on changes in the state of the circulatory system) The data processing unit 20 processes the data input in step S4 to detect changes in the state of the circulatory system associated with infectious diseases. As a result, the data processing unit 20 generates, for example, data indicating the onset of pneumonia, data indicating changes in the state of pneumonia, data indicating the onset of hypoxemia, data indicating changes in the state of hypoxemia, data indicating changes in the state of cerebral blood flow, etc. The data generated in this step is called detection data.

[0142] (S6: Create a report) The medical system 1 (the report creation unit not shown above) creates a report based on the detection data generated in step S5.

[0143] (S7: Send report) The transmission unit 31 of the output unit 30 transmits the report created in step S6 to the doctor terminal 3 at a remote location with respect to the data acquisition unit 10, or to a computer capable of providing information to the medical terminal 3. The doctor terminal 3 is not limited to the computer used by the doctor, and may be a computer (medical staff terminal) used by medical staff other than the doctor.

[0144] According to such a medical system 1, it is possible to ensure the social distance between medical staff and patients and reduce the risk of infection from patients to medical staff. Furthermore, since the medical system 1 is configured to automatically perform diagnostic inferences based on at least two of the blood oxygen data, auscultation sound data, eye image data, and eye blood flow data, it is possible to detect symptoms and signs of exacerbation associated with infectious diseases with higher accuracy than conventional techniques.

[0145] In addition, the examinations performed in the medical system of some exemplary embodiments are non-invasive. For example, all of the following devices exemplified as inspection devices that can be used in the medical system 1 acquire data from patients in a non-invasive manner: pulse oximeter, electronic stethoscope, optical coherence tomography device, fundus camera (in the case of a non-mydriatic type), slit lamp microscope, scanning laser ophthalmoscope, laser speckle flowgraphy, thermometer, electrocardiogram, blood flow meter, respiratory monitoring system, sphygmomanometer, eye refraction measuring device, tonometer, specular microscope, wavefront analyzer, visual acuity testing device, perimeter, microperimeter, axial length measuring device, electroretinogram testing device, binocular vision function testing device, color vision testing device. The non-invasive inspection devices that can be used in the medical system of the exemplary embodiment are not limited to these. Note that at least some of the inspection devices (for example, a mydriatic type fundus camera) may be invasive.

[0146] <Medical information processing device> An example of a medical information processing device according to an exemplary embodiment will be described. The exemplary medical information processing device 5 shown in FIG. 7 includes a data reception unit 51, a data processing unit 52, and an output unit 53.

[0147] Outside the medical information processing device 5 of this embodiment, a data acquisition system 6, an operation device 7, and a doctor terminal 8 are provided.

[0148] The data acquisition system 6 is configured to acquire at least two types of data out of blood oxygen data, auscultation sound data, eye image data, and eye blood flow data from a patient. The data acquisition system 6 may further be configured to acquire either or both of body temperature data and heart rate data from the patient.

[0149] At least a part of the configuration of the data acquisition system 6 may be the same as at least a part of the data acquisition unit 10 of the medical system 1 described above. It is possible to combine any matters described for the data acquisition unit 10 with the data acquisition system 6. The data acquired by the data acquisition system 6 may be recorded, for example, according to the data structure 100 shown in FIG. 2.

[0150] The operation device 7 is used for medical staff to remotely operate the data acquisition system 6 (inspection device). The operation device 7 includes, for example, a computer, an operation panel, and the like. At least a part of the configuration of the operation device 7 may be the same as at least a part of the operation device 2 described above. It is possible to combine any matters described for the operation device 2 with the operation device 7.

[0151] The doctor terminal 8 is arranged at a remote position with respect to the data acquisition system 6. At least a part of the configuration of the doctor terminal 8 may be the same as at least a part of the doctor terminal 3 described above. It is possible to combine any matters described for the doctor terminal 3 with the doctor terminal 8.

[0152] The data reception unit 51 is configured to receive at least two pieces of data among blood oxygen data, auscultation sound data, eye image data, and eye blood flow data acquired from a patient. In the example of FIG. 7, data is input from the data acquisition system 6 to the data reception unit 51, but it is not limited thereto. For example, the data acquired by the data acquisition system 6 may be stored in a database or the like, and the data may be input from this database to the data reception unit 51. The data reception 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.

[0153] The data processing unit 52 is configured to process at least two pieces of data received by the data reception unit 51 in order to detect changes in the state of the circulatory system associated with an infectious disease. At least a part of the configuration of the data processing unit 52 may be the same as at least a part of the data processing unit 20 of the medical system 1 described above. It is possible to combine any matters described for the data processing unit 20 with the data processing unit 52.

[0154] The output unit 53 outputs the result of the process executed by the data processing unit 52. The output unit 53 in this example includes a transmission unit 54. The transmission unit 54 transmits the result of the process executed by the data processing unit 52 to the doctor terminal 8 at a remote location with respect to the data acquisition system 6. At least a part of the configuration of the output unit 53 may be the same as at least a part of the output unit 30 of the medical system 1 described above. It is possible to combine any matters described for the output unit 30 with the output unit 53. Similarly, at least a part of the configuration of the transmission unit 54 may be the same as at least a part of the transmission unit 41 of the medical system 1 described above, and it is possible to combine any matters described for the transmission unit 41 with the transmission unit 54.

[0155] It is possible to combine any matters described for the medical system 1 described above with the medical information processing device 5.

[0156] According to such a medical information processing device 5, it is possible to ensure the social distance between medical staff and patients and reduce the risk of infection from patients to medical staff. Furthermore, since the medical information processing device 5 is configured to automatically perform diagnostic inferences based on at least two types of data among blood oxygen data, auscultation sound data, eye image data, and eye blood flow data, it is possible to detect symptoms associated with infectious diseases and signs of exacerbation with higher accuracy than conventional techniques.

Explanation of Signs

[0157] 1 Medical system 2 Operating device 3 Physician terminal 10 Data acquisition unit 20 Data processing unit 21 Blood oxygen data processing unit 22 Auscultation sound data processing unit 23 Eye image data processing unit 230 Inference processing unit 231 First pre-trained model 232 Second pre-trained model 24 Eye blood flow data processing unit 30 Output unit 31 Transmission unit 100 Data structure 110 Blood oxygen data section 120 Auscultation sound data section 130 Eye image data section 140 Eye blood flow data section

Claims

1. A data acquisition unit that acquires at least one of blood oxygen data, auscultatory sound data, and eye image data from a patient, and fundus blood flow data that represents blood flow dynamics in fundus blood vessels; a data processing unit that processes the at least one data acquired by the data acquisition unit and the fundus blood flow data in order to detect a change in a state of the circulatory system associated with an infection; Including, The fundus blood flow data includes waveform data representing a time series change in blood flow velocity in the fundus artery of the patient, The data processing unit detects a change in a state of the circulatory system based on the waveform data. Healthcare system.

2. The fundus blood flow data includes two or more waveform data acquired from the patient during two or more different time periods, The data processing unit detects a change in the state of the circulatory system by comparing the two or more waveform data. The medical system of claim 1.

3. A data acquisition unit that acquires at least one of blood oxygen data, auscultatory sound data, and eye image data from a patient, and fundus blood flow data that represents blood flow dynamics in fundus blood vessels; a data processing unit that processes the at least one data acquired by the data acquisition unit and the fundus blood flow data in order to detect a change in a state of the circulatory system associated with an infection; Including, The fundus blood flow data includes either or both of blood flow velocity data and blood flow rate data in the fundus artery of the patient, The data processing unit detects a change in a state of the circulatory system based on either or both of the blood flow velocity data and the blood flow volume data. Healthcare system.

4. The fundus blood flow data includes two or more blood flow velocity data obtained from the patient during two or more different time periods, The data processing unit detects a change in the state of the circulatory system by comparing the two or more blood flow velocity data. The medical system of claim 3.

5. The fundus blood flow data includes two or more blood flow data obtained from the patient during two or more different periods of time, The data processing unit detects a change in the state of the circulatory system by comparing the two or more blood flow rate data. The medical system of claim 3.

6. The change in the state of the circulatory system includes at least one of the following: onset of pneumonia, a change in the state of pneumonia, onset of hypoxemia, a change in the state of hypoxemia, and a change in the state of cerebral blood flow; The medical system according to any one of claims 1 to 5.

7. The data processing unit detects information related to a change in the state of the circulatory system from the fundus blood flow data acquired by the data acquisition unit, using a trained model constructed by machine learning using training data including fundus blood flow data and diagnosis result data, the trained model receiving fundus blood flow data as an input and outputting estimated diagnosis data related to a state of the circulatory system associated with an infection. The medical system of claim 1 or 3.

8. A data receiving unit that receives at least one of blood oxygen data, auscultatory sound data, and eye image data obtained from a patient, and eye blood flow data representing blood flow dynamics in fundus blood vessels obtained from the patient; a data processing unit that processes the at least one data and the fundus blood flow data received by the data receiving unit in order to detect a change in a state of the circulatory system associated with an infection; Including, The fundus blood flow data includes waveform data representing a time series change in blood flow velocity in the fundus artery of the patient, The data processing unit detects a change in a state of the circulatory system based on the waveform data. Medical information processing device.

9. A data receiving unit that receives at least one of blood oxygen data, auscultatory sound data, and eye image data obtained from a patient, and eye blood flow data representing blood flow dynamics in fundus blood vessels obtained from the patient; a data processing unit that processes the at least one data and the fundus blood flow data received by the data receiving unit in order to detect a change in a state of the circulatory system associated with an infection; Including, The fundus blood flow data includes either or both of blood flow velocity data and blood flow rate data in the fundus artery of the patient, The data processing unit detects a change in a state of the circulatory system based on either or both of the blood flow velocity data and the blood flow volume data. Medical information processing device.

Images