Methods, apparatus, systems

Abstract

The system automatically diagnoses autonomic nervous system disorders or cardiovascular diseases based on vital data. [Solution] A method comprising: a device that calculates the periodic time of vital data related to the cardiovascular system; calculates a distribution with the nth period and the (n+1)th period as attributes; and, based on the distribution, determines the presence or absence or possibility of autonomic nervous system disease or cardiovascular disease, or performs an evaluation related to the autonomic nervous system or cardiovascular system.

Description

Technical Field

[0001] The present invention relates to a method, an apparatus, and a system.

Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Patent Document 1 discloses an electrocardiogram self-diagnosis and information card creation method and its apparatus.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the inventor recognized that at least the above-described embodiments have a disadvantage in that there is no configuration for automatically determining an autonomic nervous system disease or a cardiovascular disease based on vital data.

Means for Solving the Problems

[0008] These and other aspects, features, and advantages of the Disclosure will become apparent from the following detailed written description of preferred embodiments and aspects taken in conjunction with the following drawings, but variations and modifications thereof may be implemented without departing from the spirit and scope of the novel concepts of the Disclosure. An aspect of one embodiment in the Disclosure may be combined with or replaced by one or more aspects of another embodiment disclosed herein, insofar as they do not conflict. [Brief explanation of the drawing]

[0009] [Figure 1] Block diagram according to one or more embodiments [Figure 2] Flowchart according to one or more embodiments [Figure 3] Figure showing the power spectrum according to one or more embodiments. [Figure 4] Explanatory diagram according to one or more embodiments [Figure 5] Block diagram according to one or more embodiments [Figure 6] End flowchart according to one or more embodiments [Figure 7] Flowchart according to one or more embodiments [Figure 8] Conceptual diagram according to one or more embodiments [Figure 9] Conceptual diagram according to one or more embodiments [Modes for carrying out the invention]

[0010] The following disclosure provides many different embodiments and examples for carrying out different features of the presented subject matter. For the sake of simplicity, specific examples of components and arrangements are disclosed below. Of course, these are merely examples and are not intended to be limiting. For example, a structure in which a first feature is covered by or in contact with a second feature subsequently disclosed may include embodiments in which an additional feature is formed between the first and second features so that they do not come into direct contact, as well as embodiments in which the first and second features are formed so that they do not come into direct contact. Furthermore, the disclosure may repeat reference numbers and / or letters in various examples. This repetition is for the sake of brevity and clarity and does not require in itself to be related to the various embodiments and / or configurations described. Furthermore, when describing the first element as being "connected" or "joined" to the second element, such description includes embodiments in which the first and second elements are directly connected or joined to each other, as well as embodiments in which the first and second elements are indirectly connected or joined to each other by having one or more other elements interposed between them.

[0011] As used herein, the phrase "at least one of" encompasses all exemplary modifications. For example, the phrase "comprises at least one of A, B, or C" is synonymous with "consisting of A, B, C and combinations thereof," and encompasses all conceivable modifications of A, B, C, A+B, A+C, B+C, and A+B+C. In this disclosure, any disclosure of embodiments combining two or more configurations can be implemented as embodiments of any one or more configurations, unless otherwise stated herein, provided that they do not conflict. For example, the phrase "implements A, B, and C" is synonymous with "comprising of A, B, or C and combinations thereof." And it incorporates all conceivable modified embodiments of A, B, C, A+B, A+C, B+C, and A+B+C.

[0012] In this disclosure, disclosures using machines, electronic operators, or computers may include embodiments of methods, recording media, apparatus, or programs. Any statement “A is B” as used herein may be replaced with “A includes B” unless otherwise stated herein, provided that this does not contradict each other. For example, a method by which information is transmitted from a first terminal or means to a second terminal or means may include embodiments in which the first and second terminals are configured to transmit and receive information directly, as well as embodiments in which the first and second terminals do not transmit and receive information directly via an additional terminal, computer, cloud, or internet service system between them.

[0013] The terms used in this disclosure, including those used in the claims, can be interpreted in light of the descriptions and drawings in the specification, and, to the extent that they do not contradict the implication of this disclosure, they can also be interpreted based on what one or more members of the public have called, represented, understood or practiced, or are likely to do so in the past, present, or future. In at least one embodiment, if, upon observation of the object or method in question, one or more members of the public can reasonably understand or recognize that some or all of its components are included in the meaning of the terms used herein, then, to the extent that they do not contradict the implication of this disclosure, they can be determined to be included in the meaning of the terms used herein. If, without performing all of the embodiments, a part of them is performed by another party, domestically or internationally, by using the services of another party, or by a general consumer, and one or more of these actions are combined to perform all of the embodiments, then the embodiments shall be deemed to have been performed. The terms used in this specification include those used as verb stems. In at least one embodiment, technical terms, symbols and reference numerals also include those commonly used in the art.

[0014] The following embodiments can be used for the operating method in at least one embodiment. The following will be explained by reference to the description in JP6456303, which describes at least one embodiment in detail (beginning of reference).

[0015] As used herein, the term "computer", as known in the art, generally includes a processor, a memory, such as a hard drive, disk drive or flash drive or memory stick, or other non-transitory computer-readable medium or non-transitory storage device, at least one information storage / search device, such as a keyboard, mouse, pointing and touch device, touch screen, or microphone, at least one input device, and a display structure such as a well-known computer screen. Additionally, a computer may include one or more network connections, such as a wired or wireless connection. As known in the art, such a computer or computer system may include more or less of the items listed above, and is not limited to, for example, tablet computers or smart devices, but encompasses other electronic media and electronic devices.

[0016] As used herein, the term "cloud" or "cloud computing" refers to centralized and virtualized computing facilities where all computing resources are shared. For application systems and subsystems, since they are all within the "cloud", it is no longer possible to refer to a specific machine.

[0017] As used herein, the term "Distributed Internet Service System" refers to a distributed Internet service platform that transforms Internet applications for execution in various computing environments. The DIS system delivers Internet applications, including content, data, and logic, to any number and any type of device, to whatever extent appropriate, and along the network, via a Component Distribution Server / Asset Distribution Server. Through DIS, Internet applications can be hosted and centrally managed as services based on each user's needs, locally cached and executed at the user's device or nearby location while maintaining their integrity. Web-enabled computing devices can be upgraded with DIS software to become DIS-compliant for enjoying and executing distributed Internet services. The Distributed Internet Service System is fully described in any one of the patent families of U.S. Patent Nos. 7,136,857; 7,150,015; 7,181,731; 7,209,921; 7,430,610; 7,685,183; 7,685,577; 7,752,214; 8,326,883; 8,386,525; 8,443,035; 8,458,142; 8,458,222; 8,473,468; 8,527,545; and 8,650,226, and U.S. Patent Publications Nos. 2012 / 0005205 and 2013 / 0091252, all of which are owned and shared by OPI 40, Holdings, Inc., and all of which are incorporated by reference. (End of citation)

[0018] Regarding the operating method used in at least one embodiment, the following embodiments can be taken for conventional internet systems that do not use a distributed internet. The following will be explained by reference to the description in JP7113047, which describes at least one embodiment in detail (beginning of reference).

[0019] Embodiments including those specifically disclosed herein can provide an automated response system based on artificial intelligence that is implemented in a manner that mimics actual human conversation, thereby enabling more natural communication with users while quickly and conveniently handling inquiries, reservations, delivery orders, and more.

[0020] The multiple electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented by a computer system. Examples of the multiple electronic devices 110, 120, 130, and 140 include AI speakers, smartphones, mobile phones, navigation systems, PCs (personal computers), notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablets, game consoles, wearable devices, IoT (Internet of Things) devices, VR (virtual reality) devices, and AR (augmented reality) devices. As an example, Figure 1 shows an AI speaker as electronic device 110, but in embodiments of the present invention, electronic device 110 may mean one of a variety of physical computer systems that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via a network 170 using substantially wireless or wired communication methods.

[0021] The communication method is not limited, and may include not only communication methods that utilize communication networks that can be included in network 170 (for example, mobile communication networks, wired internet, wireless internet, broadcasting networks, satellite networks, etc.), but also short-range wireless communication between devices. For example, network 170 may include one or more arbitrary networks such as PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Furthermore, network 170 may include, but is not limited to, one or more network topologies, including bus networks, star networks, ring networks, mesh networks, starbus networks, tree or hierarchical networks.

[0022] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via a network 170 to provide instructions, code, files, content, services, etc. For example, server 150 may be a system that provides a first service to multiple electronic devices 110, 120, 130, and 140 connected via a network 170, and server 160 may also be a system that provides a second service to multiple electronic devices 110, 120, 130, and 140 connected via a network 170. As a more specific example, server 150 may provide the multiple electronic devices 110, 120, 130, and 140 as a first service through an application, which is a computer program installed and executed on the multiple electronic devices 110, 120, 130, and 140, with the service targeted by that application (for example, an automated response service). As another example, server 160 may provide a second service that distributes files for installing and running the aforementioned application to multiple electronic devices 110, 120, 130, and 140.

[0023] Figure 2 is a block diagram illustrating the internal configuration of an electronic device and a server in one embodiment of the present invention. In Figure 2, the internal configuration of electronic device 110 and server 150 are described as examples of electronic devices. Other electronic devices 120, 130, 140 and server 160 may also have the same or similar internal configuration as the electronic device 110 or server 150 described above.

[0024] The electronic device 110 and the server 150 may include memory 211, 221, processors 212, 222, communication modules 213, 223, and input / output interfaces 214, 224. The memory 211, 221 may be a non-temporary computer-readable recording medium and may include non-temporary mass storage devices such as RAM (random access memory), ROM (read-only memory), disk drives, SSDs (solid-state drives), and flash memory. Here, non-temporary mass storage devices such as ROM, SSDs, flash memory, and disk drives may be included in the electronic device 110 and the server 150 as separate non-temporary storage devices distinct from the memory 211, 221. The memory 211, 221 may also store an operating system and at least one program code (for example, code for a browser installed and run on the electronic device 110, or code for an application installed on the electronic device 110 to provide a specific service). Such software components may be loaded from a computer-readable recording medium separate from the memory 211, 221. Such other computer-readable recording media may include computer-readable recording media such as floppy® drives, disks, tapes, DVD / CD-ROM drives, and memory cards. In other embodiments, software components may be loaded into memories 211, 221 through communication modules 213, 223 which are not computer-readable recording media. For example, at least one program may be loaded into memories 211, 221 based on a computer program (for example, the application described above) that is installed by a file provided over the network 170 by a file distribution system (for example, the server 160 described above) that distributes installation files for a developer or application.

[0025] Processors 212 and 222 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to processors 212 and 222 by memory 211 and 221 or by communication modules 213 and 223. For example, processors 212 and 222 may be configured to execute instructions received according to program code recorded in a recording device such as memory 211 and 221.

[0026] Communication modules 213 and 223 may provide functionality for the electronic device 110 and the server 150 to communicate with each other via the network 170, or they may provide functionality for the electronic device 110 and / or the server 150 to communicate with other electronic devices (for example, electronic device 120) or other servers (for example, server 160). For example, a request generated by the processor 212 of the electronic device 110 according to program code recorded in a recording device such as memory 211 may be transmitted to the server 150 via the network 170 under the control of the communication module 213. Conversely, control signals, instructions, content, files, etc., provided under the control of the processor 222 of the server 150 may be received by the electronic device 110 via the communication module 223 and the network 170 through the communication module 213 of the electronic device 110. For example, control signals, commands, content, and files from the server 150 received through the communication module 213 may be transmitted to the processor 212 and memory 211, and the content and files may be recorded on a recording medium (the non-temporary recording device described above) that the electronic device 110 may further include.

[0027] The input / output interface 214 may be a means for interface with an input / output device 215. For example, an input device may include a keyboard, mouse, microphone, camera, etc., and an output device may include a display, speaker, haptic feedback device, etc. As another example, the input / output interface 214 may be a means for interface with a device that integrates input and output functions into one, such as a touchscreen. The input / output device 215 may consist of the electronic device 110 and one other device. Also, the input / output interface 224 of the server 150 may be a means for interface with an input or output device (not shown) that connects to or can be included in the server 150. As a more specific example, when the processor 212 of the electronic device 110 processes instructions for a computer program loaded into memory 211, a service screen or content configured using data provided by the server 150 or electronic device 120 may be displayed on the display via the input / output interface 214.

[0028] Furthermore, in other embodiments, the electronic device 110 and the server 150 may include more components than those shown in Figure 2. However, it is not necessary to explicitly show most of the conventional components in the figure. For example, the electronic device 110 may be implemented to include at least some of the input / output devices 215 described above, and may further include other components such as transceivers, cameras, various sensors, and databases. As a more specific example, if the electronic device 110 is an AI speaker, the electronic device 110 may be implemented to further include a variety of components that are generally included in an AI speaker, such as various sensors, camera modules, various physical buttons, buttons using a touch panel, input / output ports, and vibrators for vibration. (End of quote)

[0029] The machine is disclosed. According to at least one embodiment, the user terminal consists of a control unit, RAM, storage unit, graphics processing unit, communication interface, and interface unit, each connected by an internal bus. In at least one embodiment, the user terminal includes terminals owned by the user. On the other hand, it includes not only terminals owned by the user, but also terminals owned by persons other than the user (including sellers and traders of goods and services, and the government and local authorities). For example, it includes terminals (including those transferred or leased) made available for use by persons receiving the provision or advertising / promotion of goods or services (hereinafter referred to as "such provision, etc." in this paragraph), terminals used for such provision, etc., and terminals related to the provision, etc. of such goods or services by persons receiving such provision, etc. In other words, it includes terminals owned by others that the user is only temporarily permitted to use, and terminals that the user is lent.

[0030] According to at least one embodiment, the control unit consists of a CPU and ROM. The control unit executes programs stored in the storage unit and controls the user terminal. RAM is the work area of ​​the control unit. The storage unit is a memory area for saving programs and data. The control unit reads programs and data from RAM and processes them. By processing the programs and data loaded into RAM, the control unit outputs drawing commands to the graphics processing unit.

[0031] According to at least one embodiment, the graphics processing unit is connected to the display unit. The display unit has a display screen. When the control unit outputs a drawing command to the graphics processing unit, the graphics processing unit outputs a video signal for displaying an image on the display screen. Here, the display unit may be a touch panel equipped with a touch sensor. The touch panel of this display unit functions as an input unit.

[0032] According to at least one embodiment, the communication interface can be connected to a communication network wirelessly or via a wired connection, and can send and receive data with a server device via the communication network. The data received via the communication interface is loaded into RAM and processed by the control unit. External memory (e.g., an SD card) is connected to the interface unit.

[0033] According to at least one embodiment, the user terminal is not particularly limited as long as it is a computer device having a display screen and an input unit. Examples of user terminals include conventional mobile phones, tablet devices, smartphones, and desktop or notebook personal computers. A VR goggle, i.e., a screen (or two display panels, one for each eye) attached to a frame (or headset) that is fixed or attached to the head with a strap, may also be used. The user terminal has an audio output unit.

[0034] According to at least one embodiment, a user terminal can communicate with a server device via a communication network. It can transmit or receive information by establishing a communication connection via the communication network.

[0035] According to at least one embodiment, the server device comprises at least a control unit, RAM, a storage unit, and a communication interface, each connected by an internal bus.

[0036] According to at least one embodiment, the control unit consists of a CPU and ROM, executes programs stored in the storage unit, and controls the server device. The control unit also has an internal timer for timing. RAM is the work area of ​​the control unit. The storage unit is a memory area for saving programs and data. The control unit reads programs and data from RAM and performs program execution processing based on information received from the user terminal, etc.

[0037] This document discloses AI. According to at least one embodiment, artificial intelligence includes machine learning, deep learning, generative AI, large-scale language models (LLMs), foundational models, and generative AI. Generative AI uses transformers and employs numerous attention mechanisms. It uses self-supervised learning and Extract Prediction. In this case, the AI ​​can predict the next word. Given a sentence, it predicts the next word from the sentence up to that point. It generates a large number of supervised learning problems. These enable an AI that can predict the next word. Generative AI can predict grammatical structure, topic connections, and what kind of sentences people with a certain writing style are likely to write. Furthermore, by simply predicting the next sentence, generative AI can learn the underlying structure, causal relationships, and knowledge. Generative AI scales quickly, and its accuracy improves as the number of parameters increases. Ordinary statistics and machine learning overfit if the model parameters are too large compared to the data sample size. LLMs become more accurate as the number of parameters increases. One generative AI has 175 billion parameters. Generative AI is overlaid with supervised learning to facilitate smooth conversation. They are taught not to say anything strange. They write essays and act as call center operators.

[0038] A machine is disclosed. In at least one embodiment, the machine may exist as a combination of one or more embodiments or functions described herein.

[0039] The term "cluster" in cluster analysis refers to a group of similar data points, meaning a cluster or cluster of similar characteristics. Therefore, cluster analysis is a method for grouping similar data (those with similar features) into several sets. The process of creating groups of similar data using this method is called "clustering." Clustering is a classification method without ground truth data. While classification is possible, the meaning of each group may not be clear. The results may require human interpretation. There are two types of cluster analysis: "hierarchical clustering," used when there are few items to classify, and "non-hierarchical clustering," applied when there are many items. Hierarchical clustering groups similar data points one by one in a hierarchical order, repeating this process until one large cluster is formed. This process is visualized using a diagram similar to a tournament bracket (tree diagram), making it an easy method to understand the data's characteristics. Non-hierarchical clustering, on the other hand, does not have a hierarchical structure. The number of clusters to be formed is predetermined, and the data is divided according to that number of clusters. There are also methods where the machine automatically divides the items without specifying the number of items to divide.

[0040] The following disclosure concerns measuring devices. In at least one embodiment, A includes a measuring device or method that, in any form, indicates vital data as quantifiable numerical values. Vital data, in any form, includes numerical or informational representations of physical or chemical reactions produced by living organisms. Vital data includes reactions originating from any living organism. Examples include vital data relating to humans, but also vital data of other animals. Examples include domesticated animals (pets, dogs, cats, etc.) and livestock (cattle, pigs, horses, etc.). Vital data, in any form, includes data relating to cardiovascular rhythms. Examples include electrocardiograms and pulse waves. On the other hand, when simply referring to vital data, any data originating from a living organism is acceptable, so electroencephalograms, respiration, eye movements, chemical substances in the blood, and genetic information and amounts of mRNA or ncRNA are also included in vital data. When referring to "vital data relating to cardiovascular rhythms," it includes vital data originating from the circulatory system, in any form. Examples include electrocardiograms, pulse waves, and pulse rate. "Rhythmic" refers to vital data that exhibits some kind of regularity or periodicity in its appearance, regardless of the nature of that regularity. Electrocardiograms (where QRS waves appear regularly), heart rate, pulse rate, electroencephalograms, fluctuations in the amount of specific substances in body fluids, blood concentrations of hormones indicating the circadian rhythm of the body clock, and the periodicity of protein phosphorylation and dephosphorylation are all, of course, "rhythmic." The measuring device includes devices capable of acquiring these vital data. Examples include electrocardiograms and pulse rate monitors. On the other hand, the device does not need to be a dedicated device solely for the purpose of such measurement. A user terminal may be configured to acquire these vital data by being equipped with additional measuring devices, either within the device itself or with an attached device. Examples include smartphones, tablet devices, smartwatches, and wearable devices.

[0041] Electrocardiography (ECG) is one method for measuring the movement of the heart or the cycle of vital data related to the cardiovascular system. Electrodes are attached to the body surface to measure the electrical activity of the heart and record its waveform. The electrical signals from the heart are captured and displayed as waveforms on a recording device. A standard ECG test is called a 12-lead ECG, and it records 12 different waveforms. A 12-lead ECG consists of a total of 12 leads: four limb leads and six chest leads. A Holter monitor includes a portable ECG device that records ECGs. Electrodes are attached to the chest to record the electrical activity of the heart and save it to a recording device. Leads in which the P wave can be clearly recorded are advantageous for diagnosing supraventricular premature contractions and atrioventricular block, and electrodes may be attached to the manubrium and xiphoid process (NASA), or the manubrium and V5 (CM5), etc. Leads that record high-amplitude QRS complexes (waveforms) are advantageous for beat detection during automated analysis, and electrodes may be attached to leads such as CM5, V5R, and V5 (CC5). CM5 is sometimes used when looking at leads where the source of ventricular premature contractions can be estimated, or when ST-T changes are easily observed (determining ST-T changes originating from myocardial ischemia). Holter electrocardiographs have a built-in rechargeable unit and can function autonomously for several hours to about a week. Therefore, subjects (including patients) can use Holter electrocardiographs not only in medical facilities but also at home. There are two types of photoplethysmography: transmissive and reflective. Transmissive types irradiate the body surface with infrared or red light and measure the pulse wave by measuring the change in blood flow that changes with the heart's pulsation as the amount of light transmitted through the body. Reflective pulse wave sensors irradiate the body with infrared, red light, or green wavelength light around 550 nm, and measure the light reflected from within the body using a photodiode or phototransistor. Arterial blood contains oxyhemoglobin, which has the property of absorbing incident light. Therefore, pulse wave signals are measured by sensing the blood flow rate (changes in blood vessel volume) that changes in accordance with the heart's pulsation over time. The pulse wave includes the waveform of the change in blood vessel volume that occurs as the heart pumps blood. The pulse rate includes the length of the wavelength calculated by analyzing the period of the pulse wave. Heart sound measurement methods include methods that measure heart sounds by placing a microphone on the sternum or other areas, and then obtaining data on heart rate and heart murmurs by analyzing those heart sounds.A cardiac pulsation measuring device or cardiac pulsation diagram, regardless of its form, includes devices that measure minute vibrations generated in the body due to the contraction of the heart. By measuring the vibrations of the circulatory system, heart rate or pulse rate can be measured. Such measuring devices can be realized by equipping them with vibration sensors. For example, by placing a user terminal (including smartphones and smartwatches) on the wrist or sternum, pulse rate or heart rate can be acquired by a vibration sensor. By analyzing the interval of vibrations, the rhythm of one beat can be measured. A cardiac sound measuring device or cardiac phonogram, regardless of its form, includes devices that measure sounds emitted from the circulatory system. In at least one embodiment, heart rate and pulse rate can be treated as separate data. This is because, in the peripheral vascular system, the same beat rate as the heart rate may not necessarily be maintained. On the other hand, in at least one embodiment, heart rate and pulse rate can be treated as the same data. In this case, the analysis is performed under the assumption that the heart rate and pulse rate are the same or similar. In this case, the method for measuring the movement of the heart or the periodicity of vital data related to the cardiovascular system is sufficient if one or more pulses or heartbeats are measured.

[0042] [First Embodiment] (Configuration of Heart Sound Analysis System 1) Based on Figure 1, the configuration of the heart sound analysis system 1 will be explained. Figure 1 is a block diagram showing the functional configuration of the heart sound analysis system 1.

[0043] As shown in Figure 1, the heart sound analysis system 1 comprises a heart sound measurement unit 10, a control processing unit 100, and a display unit 50. The heart sound measurement unit 10 is the part used to measure heart sounds, and specifically it is a microphone.

[0044] Here, heart sounds are sounds produced when the heart valves close, and consist of sounds such as the first heart sound, the second heart sound, and heart murmurs. For blood to be pumped from the heart, the atrioventricular valves between the atria and ventricles, and the arterial valves between the ventricles and arteries must open and close. When the atria contract and blood fills the ventricles, the atrioventricular valves (mitral valve and tricuspid valve) close, and the ventricles begin to contract accordingly. The first heart sound is the sound produced at this time.

[0045] Furthermore, when the ventricles contract and pump blood into the arteries, the arterial valves (aortic valve and pulmonary valve) close. This is the second heart sound. Furthermore, if there is valve dysfunction or stenosis, abnormal sounds may occur in addition to the clear heart sounds. These sounds are called heart murmurs. The first heart sound (I) is best heard at the apex of the heart, and the second heart sound (II) is best heard at the sternal border at the level of the second intercostal space on both sides. The first heart sound is heard as a dull, low-pitched sound, while the second heart sound is heard as a sharp, high-pitched sound.

[0046] The control processing unit 100 includes a CPU, ROM, RAM, I / O, a heart sound data storage unit 20, a heart sound spectrum calculation unit 30, and an abnormal state determination unit 40 (not shown). The heart sound data storage unit 20 is the part that stores the heart sounds measured by the heart sound measurement unit 10 as time-series heart sound data, and is specifically a memory.

[0047] The heart sound spectrum calculation unit 30 calculates the power spectrum of the heart sound data based on the heart sound data stored in the heart sound data storage unit 20. Specifically, it is implemented as a program (abnormal state determination process) executed by the CPU. The abnormal state determination process will be described later.

[0048] The abnormal state determination unit 40 determines abnormal conditions related to the heart based on the heart sound data calculated by the heart sound spectrum calculation unit 30. Specifically, it is implemented as a program (abnormal state determination process) executed by the CPU. The abnormal state determination process will be described later.

[0049] The display unit 50 is the part that displays the abnormal state determined by the abnormal state determination unit 40, and specifically, it is a display device such as a liquid crystal display.

[0050] (Abnormal state detection process) Next, the abnormality detection procedure performed in the control processing unit 100 will be described based on Figure 2. Figure 2 is a flowchart showing the flow of the abnormal state detection procedure. The abnormal state detection process is stored as a program in ROM and is read by the CPU and processed when the heart sound analysis system 1 is powered on.

[0051] As shown in Figure 2, in the abnormal state detection procedure, the CPU acquires heart sound data (time-series data of heart sounds) from the heart sound measurement unit 10 in S100, and in the subsequent S105, stores the heart sound data acquired in S100 into the heart sound data storage unit 20.

[0052] In the subsequent S110, it is determined whether a predetermined time (1 minute in this embodiment) has elapsed. If it is determined that the predetermined time has elapsed (S110: Yes), the process proceeds to S115; if it is determined that the predetermined time has not elapsed (S110: No), the process returns to S100.

[0053] In S115, features such as PSD are extracted from the heart sound data acquired in S100 to S110. Specifically, the following processes (a) to (e) are performed to calculate the features. As an example of feature calculation, we will explain by referring to the example of heart sound data acquired in S100 to S110 and the power spectrum of that heart sound data shown in Figure 3. Figure 3 is a diagram showing an example of heart sound data acquired by the heart sound analysis system 1 and the power spectrum of that heart sound data. Note that in Figure 3, the graph indicated by "A" is the heart sound data, and the graph indicated by "B" is the power spectrum.

[0054] (a) Calculate the PSD (Power Spectral Density) for a specific frequency band. (i) Pick out the peaks from the calculated PSD that exceed a certain value. The peak groups obtained in (c)(b) are classified into single tones, two tones, and noise.

[0055] For the single tone group obtained in (E)(U), the characteristics of atrial fibrillation, premature contractions (arrhythmia), and pauses (arrhythmia) are calculated using an algorithm for analyzing cardiovascular rhythm disturbances. The algorithm for analyzing cardiovascular rhythm disturbances (hereinafter referred to as the "analysis algorithm") includes an algorithm for evaluating cardiovascular rhythm disturbances based on heart rate, pulse rate, or combinations thereof, and includes an arrhythmia analysis algorithm. The analysis algorithm will be described later. For the single tone group obtained in (O) and (U), the LF / HF ratio is calculated using an autonomic nervous system analysis algorithm to determine signs of autonomic nervous system dysfunction. The autonomic nervous system analysis algorithm will be described later.

[0056] In the following step S120, an abnormal state is determined based on the calculation results from S115. In the following step S125, the abnormal state determination result (indications of an abnormal state) is displayed on the display unit 50 using a Lorentz plot, after which the process ends. Here, we will explain how to display signs of abnormal conditions using a Lorentz plot, based on Figure 4. Figure 4 is an explanatory diagram of signs of abnormal conditions and their representation using a Lorentz plot.

[0057] A Lorentz plot, regardless of its form, is a graph plotting the nth heartbeat or pulse on the horizontal axis and the (n+1)th heartbeat or pulse on the vertical axis. The heartbeat or pulse includes the interval between heart sounds or the wavelength of the pulse wave. As shown in Figures 4(a) and 4(b), if the heart sound data is determined to be "normal," the Lorenz plot will show a graph where the distribution of heart rate intervals is upward sloping (the slope of the linear curve approximated by the least squares method is positive), and the variability in the vertical, horizontal, or a combination thereof (hereinafter referred to as "up, down, horizontal, etc.") is within a predetermined range.

[0058] As shown in Figure 4(c), if "signs of atrial fibrillation are present," the distribution of heart rate intervals will diverge, resulting in a graph where the variability in the up, down, left, and right directions is outside the predetermined range. "Outside the predetermined range" means, for example, that clusters on the upward-sloping line shown in Figures 4(a) and 4(b) do not appear, resulting in a graph where the distribution of heart rate intervals in the up, down, left, and right directions relative to the upward-sloping linear curve exceeds the predetermined range, and includes combinations of these. As shown in Figure 4(d), if "signs of premature contractions are present," the graph will show three or more upward-sloping linear approximation curves of the heart rate interval distribution.

[0059] As shown in Figure 4(e), if a patient is judged to have "signs of autonomic neuropathy such as diabetes or Parkinson's disease," the distribution of heart rate intervals in the up, down, left, and right directions relative to the upward-sloping linear curve will be below a predetermined value.

[0060] (Analysis algorithm) Here, we will explain the analysis algorithm based on Figure 8. Figure 8 is a conceptual diagram used to explain the analysis algorithm using an actual electrocardiogram. As shown in Figure 8, the analysis algorithm calculates the characteristics of atrial fibrillation, premature contractions (arrhythmia), and pauses (arrhythmia) using the following (a) to (d).

[0061] (a) Detect the QRS complex from the electrocardiogram waveform shown in Figure 8(A) (indicated as "C" in Figure 8(A)). The QRS complex represents a characteristic point on the electrocardiogram from ventricular excitation to the completion of depolarization, and is the region indicated as "E" in Figure 8(B). Note that Figure 8(B) is an enlarged view of the "C" portion in Figure 8(A).

[0062] (i) Calculate the time interval between adjacent QRS complexes (this time interval is called the RR interval and is indicated by "D" in Figure 8(A)). (c) For a given QRS complex, compare it with the RR interval of the preceding few to tens of beats to determine whether an eccentric contraction has occurred.

[0063] After eliminating the influence of items (e) and (c), the presence or absence of atrial fibrillation is determined from the variability of the RR interval in a specific section. In this invention, when performing similar processing using heart sound data instead of electrocardiograms, the characteristics of atrial fibrillation, premature contractions (arrhythmias), and pauses (arrhythmias) are calculated by replacing the interval between adjacent heart sounds with the RR Interval. This makes it possible to analyze arrhythmias using heart sound data based on the arrhythmia analysis algorithm using electrocardiograms.

[0064] (Analysis algorithm related to the autonomic nervous system) Next, we will explain the analysis algorithm for the autonomic nervous system based on Figure 9. Figure 9 is a conceptual diagram used to explain the analysis algorithm for the autonomic nervous system using an actual electrocardiogram.

[0065] As shown in Figure 9, the autonomic nervous system analysis algorithm calculates the characteristics of autonomic disorders such as diabetes and Parkinson's disease using the following (O) and (Ka). (e) The RR interval group (indicated as "F" in Figure 9) calculated by electrocardiogram arrhythmia analysis is subjected to frequency analysis to calculate the PSD.

[0066] Of the terms (k) and (o), find the integral values ​​of High Frequency (HF: 0.15~0.4Hz) and Low Frequency (LF: 0.05~0.15Hz), and calculate their ratio as LF / HF.

[0067] In this invention, instead of using an electrocardiogram, when performing similar processing with heart sound data, the characteristics of autonomic nervous system disorders are calculated by replacing the interval between adjacent heart sounds with the RR interval. This makes it possible to perform autonomic nervous system analysis using heart sound data, based on the autonomic nervous system analysis algorithm that uses electrocardiograms.

[0068] (Features of the heart sound analysis system) The above-described heart sound analysis system 1 can determine and present abnormal conditions related to the heart based on heart sound data acquired from the user, who is the subject of the analysis. Therefore, compared to determining abnormal conditions related to the heart based on an electrocardiogram, which requires a probe to acquire an electrocardiogram, this system only requires a microphone, making it simpler and less burdensome for the subject during measurement.

[0069] Furthermore, it can identify and present signs of arrhythmia as an abnormal condition. In addition, it can identify and present signs of at least one of the following abnormal conditions: atrial fibrillation, premature contractions, and autonomic neuropathy (such as diabetes or Parkinson's disease).

[0070] [Second Embodiment] Next, the heart sound analysis system 1 in the second embodiment will be described. Since the functions of the constituent elements and the abnormal state determination process of the heart sound analysis system 1 in the second embodiment are the same as those in the first embodiment, their descriptions will be omitted.

[0071] The heart sound analysis system 1 in the second embodiment is configured using components of a user terminal (including so-called smartphones or wearable devices; hereinafter simply referred to as "smartphone" in the second embodiment). Specifically, the heart sound measurement unit 10 is the smartphone's microphone, the control processing unit 100 is the smartphone's CPU, and the display unit 50 is the smartphone's display.

[0072] Then, the abnormal state detection process is stored as an application in the smartphone's memory, the heart sound data measured by the heart sound measurement unit 10 (microphone) is stored in the memory, the CPU calculates the power spectrum and performs abnormal state detection, and the result of the abnormal state detection is displayed on the display unit 50 (display).

[0073] In addition to the features of the heart sound analysis system 1 in the first embodiment, this heart sound analysis system can be configured using a smartphone, resulting in a very simple and user-friendly system.

[0074] [Third Embodiment] Next, the heart sound analysis system 2 in the third embodiment will be described based on Figure 5. Figure 5 is a block diagram showing the functional configuration of the heart sound analysis system 2 in the third embodiment.

[0075] As shown in Figure 5, the heart sound analysis system 2 comprises a terminal 110 and a server 120, and data is transmitted and received between the terminal 110 and the server 120 via a communication line 5 such as the internet.

[0076] In addition, components of the heart sound analysis system 2 in the third embodiment that are the same as those of the heart sound analysis system 1 in the first embodiment are denoted by the same reference numerals, and their descriptions are omitted. Terminal 110 is the part of the heart sound analysis system 2 that is held and used by the user. It measures heart sound data, transmits it to the server 120 via the communication line 5, and receives and displays the abnormal condition determination result from the server 120 via the communication line 5.

[0077] The terminal 110 includes a heart sound measurement unit 10, a display operation unit 51, a transmission / reception unit 60, and a CPU, ROM, RAM, and I / O (not shown). The display operation unit 51 includes a liquid crystal display for displaying information and a touch panel on its surface for operation input.

[0078] The transmitting / receiving unit 60 is a transceiver for sending and receiving data to and from the server 120 via the communication line 5. The CPU also performs terminal processing, which will be described later. Server 120 stores heart sound data transmitted from terminal 110 via communication line 5, calculates heart sound spectrum and determines abnormal condition results based on the stored heart sound data, and transmits the results to terminal 110 via communication line 5.

[0079] The server 120 includes a heart sound data storage unit 20, a heart sound spectrum calculation unit, an abnormal state determination unit 40, a transmission / reception unit 61, and a CPU, ROM, RAM, and I / O (not shown). The transceiver unit 61 is a transceiver for sending and receiving data to and from the terminal 110 via the communication line 5. The CPU also performs server processing, which will be described later.

[0080] (Terminal processing) Based on Figure 6, the terminal processing performed on terminal 110 will be explained. Figure 6 is a flowchart showing the flow of terminal processing.

[0081] As shown in Figure 6, in terminal processing, first, in S200, the input status of the operation mode is obtained from the display operation unit 51. In other words, it is obtained whether the user has selected to "measure heart sound data," "display the abnormal state judgment result," or "terminate the process."

[0082] In the subsequent S205, the system determines which mode the mode state input obtained in S200 corresponds to. If the input state mode is "heart sound data measurement", the process moves to 210; if it is "abnormal state determination result", the process moves to S220; and if it is "processing complete", the terminal process is terminated.

[0083] In S210, heart sound data is acquired, and in the subsequent S215, the heart sound data acquired in S210 is transmitted to the server 120 via the communication line 5. When transmitting, start data is sent at the beginning of the heart sound data, and end data is sent at the end after a predetermined time has elapsed.

[0084] In S220, it is determined whether a predetermined time (1 minute in this embodiment) has elapsed. If it is determined that the predetermined time has elapsed (S220: Yes), the process returns to S200; if it is determined that the predetermined time has not elapsed (S220: No), the process returns to S210.

[0085] In S225, the abnormal state determination result is input from the server 120 via the communication line 5. In the subsequent S230, the abnormal state determination result input in S225 is displayed on the display operation unit 51, and then the process returns to S200.

[0086] (Server processing) Based on Figure 7, the server processing performed on server 120 will be explained. Figure 7 shows the flow of server processing.

[0087] As shown in Figure 7, in the server processing, first, S300 receives heart sound data from terminal 110 via communication line 5 and stores it in heart sound data storage unit 20. When inputting data, data from start data to end data is input and stored in heart sound data storage unit 20.

[0088] In the subsequent S305, features such as heart sound PSD are calculated from the heart sound data acquired in S300. In the subsequent S310, signs of an abnormal state are determined from the characteristic quantities such as heart sound PSD calculated in S305. The determination method is the same as the abnormal state determination process (S115, S120) in Embodiment 1.

[0089] In the subsequent S315, the determination result from S310 is transmitted to the terminal 110 via the communication line. At this time, the determination result may also be transmitted to the terminal 110 as a Lorentz plot as in S125 of Embodiment 1.

[0090] In this type of heart sound analysis system 2, the terminal 110 can be miniaturized by consisting only of a heart sound measurement unit 10, a display operation unit 51, and a transmitting / receiving unit 60, making it a user-friendly system.

[0091] Furthermore, since abnormal state detection processing can be performed using the communication line 5 and the server 120, it becomes possible to process multiple terminals 110 with a single server 120, enabling large-scale system implementation.

[0092] Any of the methods described herein can be used to obtain vital data related to cardiovascular rhythms.

[0093] In at least one embodiment, vital data includes pulse rate. Pulse rate can be measured by a user terminal, wearable device, or smartwatch. For example, an optical heart rate monitor (OHR) sensor is used. A sensor on a device worn on the wrist (including sensors built into smartwatches and detachable sensors that can be connected to a user terminal via wired or wireless connection) shines light onto the blood flow, and the pulse rate is measured from the change in the reflection. The wearable device is worn so that it fits snugly on the wrist. The closer the sensor is to the skin, the more accurately it can receive reflected light. The app included with the device or a connected smartphone app is launched to measure the heart rate. When light emitted by the optical sensor hits the skin, some is absorbed and some is reflected. Hemoglobin in the blood absorbs light, so as the amount of blood changes due to the heartbeat, the intensity of the reflected light also changes. The optical sensor detects the intensity of this reflected light. By analyzing the period of this intensity and calculating the time between peak wavelengths, vital data (pulse rate) related to the rhythm of the cardiovascular system can be obtained. To achieve more accurate heart rate measurement, multiple optical sensors may be incorporated. This allows for the acquisition of more data points and the calculation of a more accurate heart rate. Combining optical sensors with sensors such as accelerometers and gyroscopes enables even more accurate heart rate measurement. This allows for a more accurate understanding of heart rate fluctuations during exercise and daily life. For methods after acquiring vital data, refer to the descriptions relating to some or all of the embodiments of this specification. According to this embodiment, there is the convenience and industrial applicability of being able to perform primary screening using at least the user's own user terminal.

[0094] In at least one embodiment, the device calculates the period of vital data related to the cardiovascular system. As already described, it calculates the period of vital data such as pulse waves, pulse rate, and electrocardiograms. For example, it calculates the time difference between peaks of the R wave (RR interval). In the measurement of heart sounds and pulse rate, it calculates the time between each sound or pulse.

[0095] In at least one embodiment, a distribution (hereinafter referred to as "the distribution") is calculated using the nth period and the (n+1)th period as attributes. For example, based on the period of vital data (e.g., heart rate interval), the nth period can be plotted on the horizontal axis and the (n+1)th period on the vertical axis to visualize the overall distribution. The distribution, regardless of its form, includes a set of data that allows for the evaluation or calculation of the data distribution based on information indicating the nth period and the (n+1)th period. That is, it includes a set of data that does not directly represent a numerical value indicating the period, but whose distribution can be calculated based on numerical values ​​or measurement data that can be converted into numerical values ​​of the period. "Calculating the distribution" does not necessarily require representing the distribution as a table and then evaluating the distribution; it includes the act of directly evaluating the distribution from the set of data by calculation. If the distribution is represented as a table, that table can be transmitted to the terminal of the person whose vital data is measured or the medical professional. When representing minutes as a table or calculating / evaluating the distribution, embodiments of the distribution include Lorenz plots and Poincaré plots. When examining the subject, anything that can be evaluated as a Lorenz plot or Poincaré plot is considered to be a "distribution with the nth period and the (n+1)th period as attributes."

[0096] In at least one embodiment, the presence or possibility of autonomic nervous system disorders or cardiovascular diseases is determined based on the distribution. After good faith consideration by the inventors, this determination is made possible by a newly named concept called CPL: Closest Points Length. In this disclosure, CPL includes the distance of each plot to its neighboring plots. CPL includes the "minimum distance," which is the distance to the closest plot in relation to neighboring plots. On the other hand, CPL does not necessarily have to be limited to the minimum distance; if other plots that are relatively close in relation to other plots are identified and the distance to those plots is determined, it will be considered to fall under CPL. Below, an embodiment in which CPL is the minimum distance is illustrated. The minimum distance between adjacent plots is determined for each plot in the distribution. For example, if there are 100 plots, the distance to the plot closest to a given plot is determined. This distance is the minimum distance between plots on the Lorenz plot. If there are 100 plots, a minimum distance exists for each plot. The determination is made based on at least one piece of minimum distance information. When the minimum distance is zero, there is no variation in the period. When the minimum distance is relatively large, the variation in the period is greater than when the minimum distance is small. Users of this system can define distance thresholds and categorize data accordingly. For example, by referring to the distribution of data for patients with cardiovascular disorders as ground truth data and performing statistical analysis on the distribution of a large number of patients, it is possible to determine a numerical range of the minimum distance that can be predicted with high confidence as indicating cardiovascular disorder. If a data point falls within that numerical range, it can be evaluated as potentially indicating cardiovascular disorder and categorized as "disease present," etc. When the minimum distance is smaller than that numerical range, the numerical range can be divided into two or more patterns, and attributes can be weighted and categorized as "pre-disease" or "no disease." "No disease" corresponds to a considerably small minimum distance. "Pre-disease" categorizes data within the numerical range between "no disease" and "disease present."According to this embodiment, accurate diagnosis of cardiac disease can be made based on a distribution with at least the nth period and the (n+1)th period as attributes, offering both convenience and industrial applicability. This effect was not known in the prior art and therefore possesses novelty and remarkable effectiveness.

[0097] In at least one embodiment, the determination is made by calculating the minimum distance between adjacent plots in the Lorenz plot and making a determination based on the sum of the minimum distances between at least two plots. As a result of good faith consideration by the inventor, the presence or possibility of autonomic nervous system disorders or cardiovascular diseases can be correctly determined by calculating the sum of CPLs for at least two plots and evaluating based on that value. Distributions with relatively large sums have greater variability in the overall period of vital data compared to distributions with relatively small sums. As already explained, by referring to the distribution of patients with cardiovascular disorders as ground truth data and taking statistics on the distribution of a large number of patients, a range of numerical values ​​for the sum that can predict cardiovascular disorders with high reliability can be determined. If a data point falls within that range, it can be evaluated as potentially indicating a cardiovascular disorder and categorized as "disease present," etc. If the sum is smaller than that range, the range can be divided into two or more patterns, and attributes can be weighted and categorized as "pre-disease" or "no disease." The sum for "no disease" is considerably small. "Pre-disease" categorizes individuals into numerical ranges between the numerical ranges of "no disease" and "disease present." In this case, by using the same number of plots for summing as the number of plots used in the ground truth data, the numerical range of the sum calculated using the ground truth data can be used as is. On the other hand, if the number of plots used to calculate the sum in the ground truth data differs from the number of plots used to calculate the sum in the data to be predicted, adjustments can be made by the ratio of the number of plots used. For example, if the numerical range is defined using 50 plots in the ground truth data, but there are only 25 plots in the data to be predicted, the sum of the CPLs of the 25 plots in the data to be predicted can be doubled to compare with the numerical range defined in the ground truth data. In at least one embodiment, the sum of the minimum distances of all plots is calculated. After careful consideration by the inventor, it has been determined that in this case, the overall variability of the vital data can be evaluated. Therefore, by referring to the distribution of this case among patients with cardiovascular disorders as ground truth data and statistically analyzing the distribution of this case among a large number of patients, it became possible to accurately predict cardiovascular disorders.This effect is unprecedented and possesses novelty and remarkable efficacy, as it was not known in any conventional technology.

[0098] In at least one embodiment, the minimum distance between plots where the nth period and the (n+1)th period are approximately identical is excluded from the calculation of the sum. After good faith consideration by the inventor, it was found that excluding the minimum distance between plots where the nth period and the (n+1)th period are approximately identical from the calculation of the sum does not substantially affect the accuracy of predicting the diagnosis. Rather, these minimum distances are undesirable because, even if the heartbeats are not particularly abnormal, a large number of plots can push up the sum. Excluding these from the calculation allows the sum to be calculated only from plots with large minimum distances that indicate premature contractions, so the difference in the sum becomes more apparent. As a result, a more accurate diagnosis or prediction can be achieved. "Approximately identical" does not require that the plots be completely identical. For example, plots on or near the y=x line in a Lorentz plot fall into this category. If, upon checking the target, at least one plot with the minimum distance between the nth period and the (n+1)th period being approximately the same is excluded from the calculation of the sum, then it will be considered that the action of "excluding the plot with the minimum distance between the nth period and the (n+1)th period being approximately the same from the calculation of the sum" has been performed.

[0099] This invention discloses a method for transmitting categorized evaluations based on minimum distance information to the terminal of a person whose vital data is being measured or a healthcare professional. In at least one embodiment, the description relating to some or all of any embodiment of this specification will be incorporated by reference. As previously described, numerical ranges for diagnoses such as CPL can be determined for CPL and the sum of CPLs by statistical or information processing classification of the ground truth data. A corresponding categorization is made for each numerical range. Categorization, in whatever form, includes medical comments or diagnoses that can be predicted within that numerical range, the difference from other numerical ranges shown in ordered letters or numbers, and any other letters, numbers, figures, photographs, colors or combinations thereof as defined by the user of this system. These agreed-upon categories are called categorized data. For example, if CPL is between 0 and 100, the categorized data would be "A," "No signs of premature contractions were found." If CPL is between 100 and 200, the categorized data would be "B," "Signs of premature contractions were found." If the CPL is 200 or higher, the categorization data will be "C," indicating "significant signs of premature contractions were found." This categorization data is merely an example; any text or numerical value that indicates or serves as a reference for some kind of medical judgment, regardless of its form, is sufficient. When the device calculates a value such as CPL, it determines which numerical range it belongs to and identifies the categorization data corresponding to that numerical range. The device can store this categorization data linked to vital data. On the other hand, it is not necessary to store them linked; an application or program can simply be created that makes the categorization data and numerical range searchable and retrievalable. The device transmits the categorization data to the terminal of the person whose vital data is being measured or the medical professional. The terminal displays the categorization data. During this transmission and display, in addition to the categorization data, vital data, the distribution in question, a Lorenz plot, and processed versions of this data may also be transmitted and displayed.After careful consideration by the inventor, it was found that in this case, the subject of measurement or healthcare professional can intuitively understand the basis for the categorization, which is the evaluation or diagnosis result, through distribution charts, etc., resulting in increased confidence in this automated diagnosis. This effect was not known in any conventional technology and therefore possesses novelty and remarkable effectiveness.

[0100] In at least one embodiment, an upper limit is set on the number of plots used when determining the distribution, or an upper limit is set on the number of CPLs used to calculate the sum. After careful consideration by the inventors, it was discovered that if the number of plots used when determining the distribution, or the number of CPLs used to calculate the sum, is too large, the difference in the sum for each subject decreases. Therefore, noise is generated when too many data points are used. It was discovered that this can actually decrease the accuracy of the diagnosis. Therefore, setting an upper limit on the number of data points used improves the accuracy of the diagnosis. In systems and programs, the accuracy of the diagnosis can be ensured by implementing a process that sets an upper limit on the number of data points used. This effect is unprecedented in the conventional art and has novelty and remarkable benefits.

[0101] In at least one embodiment, the determination is made by analyzing the clusters of each plot in the Lorentz plot. After good faith consideration by the inventors, this determination is made possible by a newly named concept called LSA: Local Skewed Area. In this disclosure, LSA is synonymous with "cluster". An analysis of the clusters of each plot in the distribution is performed. If no clusters are found, it means that the period is dispersed, and it can be predicted that premature contractions or the like are occurring.

[0102] In at least one embodiment, the determination is made by analyzing the clusters of each plot in the Lorenz plot. If no clusters are found or the cluster density is low, it is determined that there is or is likely to be an autonomic nervous system disorder or a cardiovascular disorder. Even if the inventors have examined the case in good faith and found that clusters are found, if the density is low, there is still a possibility of a disorder. As already explained, by referring to the distribution of patients with cardiovascular disorders as ground truth data and statistically analyzing the distribution of a large number of patients, a numerical range of cluster density that can reliably predict cardiovascular disorders can be determined. If a data point falls within that numerical range, it can be evaluated as a suspected cardiovascular disorder and categorized as "disordered." If the sum is smaller than that numerical range, the numerical range can be divided into two or more patterns, and attributes can be weighted and categorized as "pre-disease" or "no disease." "No disease" has a considerably small sum. "Pre-disease" categorizes data within the numerical range between "no disease" and "disordered." Categorization is possible not only by the numerical range of cluster density, but also by the number of clusters. For example, the appearance of three clusters may indicate a certain cardiovascular disease. In this way, by learning from ground truth data, it is possible to predict diseases based on the number of cluster occurrences.

[0103] In at least one embodiment, categorized evaluations based on cluster analysis are transmitted to the terminal of the person whose vital data is being measured or the healthcare professional. The descriptions relating to some or all of the embodiments of this specification are incorporated herein by reference. As already described, numerical ranges for LSA and LSA density and / or number can be defined by statistical or information processing classification of ground truth data. A corresponding categorization is made for each numerical range. For example, if the LSA is between 0 and 10, the categorization data would be "A," meaning "no signs of premature contractions were found." If the LSA is between 10 and 50, the categorization data would be "B," meaning "significant signs of premature contractions were found." If the LSA is 50 or greater, the categorization data would be "C," meaning "significant signs of premature contractions were found." This categorization data is merely an example; any letters or numbers that indicate or serve as a reference for some kind of medical judgment, regardless of their form, are sufficient. When a numerical value such as LSA is calculated, the device determines which numerical range it belongs to and identifies the corresponding categorization data. The device can store this categorization data linked to vital data. Alternatively, it may be unnecessary to store the data linked together, and an application or program may be created that simply makes the categorization data and numerical range searchable and retrievalable. The device transmits the categorization data to the terminal of the person whose vital data is being measured or the healthcare professional. The terminal displays the categorization data. During this transmission and display, in addition to the categorization data, vital data, the distribution in question, a Lorenz plot, and processed versions of this data may also be transmitted and displayed.

[0104] In at least one embodiment, vital data includes pulse rate. In this case, one pulse beat is considered a “period,” and the description relating to some or all of the embodiments herein is incorporated accordingly.

[0105] In at least one embodiment, the description of "vital data related to cardiovascular rhythms" does not need to be limited to the cardiovascular system, but can be simply replaced with the description of "vital data of the body." In this case, "the nth cycle and the (n+1)th cycle" can also be replaced with the description of "the nth value and the (n+1)th value." For example, in sleep phase measurement, if the time taken to fall asleep is measured over multiple days, it corresponds to "the nth value and the (n+1)th value." In this case, for example, by measuring that time over 50 days and calculating the distribution, the distribution of the time required to fall asleep can be determined. As explained earlier, CPL and LSA are calculated for this distribution. A questionnaire is then administered to the people who actually underwent the measurements, asking them about their usual sleep patterns, etc., and those with sleep disorders are identified by a psychiatrist or other medical professional, and these are categorized as ground truth data. This allows for evaluation of whether there is variability in the distribution of sleep onset times based on the measured data, and enables the determination of whether or not a sleep disorder exists. In addition, the respiratory rate per minute is also included in "vital data of the body." For example, by measuring the respiratory rate over a 50-day period and determining the distribution, the variability in respiratory rate can be determined. This method allows for the diagnosis of chronic obstructive pulmonary disease (COPD) and its precursors. In this way, while the body generally maintains homeostasis, when the biological system breaks down, it becomes difficult to maintain a constant rhythm and activity level. According to the embodiment diligently considered by the inventor, it is possible to automatically predict such breakdowns and their precursors.

[0106] In at least one embodiment, autonomic nervous system disorders can be diagnosed. As already described, by training with data from these patients as ground truth data, highly accurate diagnoses based on the present distribution can be achieved. For example, diseases such as autonomic dysfunction, orthostatic dysregulation, diabetic autonomic neuropathy, Lewy body dementia, multiple system atrophy, Addison's disease, Parkinson's disease, and functional dyspepsia can be predicted.

[0107] The following is an overview of the embodiments described above.

[0108] A method, and the apparatus, Calculate the cycle time of vital data related to the cardiovascular system, We calculate a distribution with the nth period and the (n+1)th period as attributes. Based on the distribution, the presence or possibility of autonomic nervous system disorders or cardiovascular diseases is determined. method.

[0109] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is based on information about the minimum distance between adjacent plots in the Lorentz plot, with at least one such piece of information. method.

[0110] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is made by calculating the minimum distance between adjacent plots in the Lorenz plot and then determining the result based on the sum of the minimum distances between at least two adjacent plots. method.

[0111] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is made by calculating the minimum distance between adjacent plots in the Lorenz plot and then determining the result based on the sum of the minimum distances between at least two adjacent plots. The minimum distance between plots where the nth period and the (n+1)th period are approximately identical is excluded from the calculation of the sum. method.

[0112] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is made based on information about the minimum distance between adjacent plots in the Lorentz plot, with at least one such piece of information. Furthermore, the categorized evaluation based on minimum distance information is transmitted to the terminal of the person whose vital data is being measured or the healthcare professional. method.

[0113] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is made by analyzing the clusters of each plot in the Lorenz plot. method.

[0114] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is made by analyzing the clusters in each plot of the Lorenz plot. If no clusters are found or the cluster density is low, it is determined that there is or is likely to be an autonomic nervous system disorder or a cardiovascular disease. method.

[0115] The above method, The distribution is calculated using a Lorentz plot with the nth period and the (n+1)th period as attributes. The determination is made by analyzing the clusters of each plot in the Lorenz plot. Furthermore, the categorized evaluations based on the cluster analysis are transmitted to the terminal of the person whose vital data is being measured or the healthcare worker. method.

[0116] In this disclosure, “cardiovascular vital data” includes data showing the periodic waveform of cardiovascular vital data, and regardless of the form, includes numerical values, sensor measurements, or raw data (data in its raw, unprocessed, or unanalyzed state as measured). “Pulse wave data” similarly includes data showing the periodic waveform of pulse waves, and regardless of the form, includes numerical values, sensor measurements, or raw data (data in its raw, unprocessed, or unanalyzed state as measured).

[0117] After careful consideration by the inventor, it was found that the CPL does not necessarily have to be the "minimum distance," and the same effect can be achieved by analyzing it as the distance to the second closest plot. In other words, the CPL can be defined as the distance to a nearby plot (a plot that is relatively close) in relation to the other plots for the nth period and the (n+1)th period. The same effect is achieved in this case as well. This effect was not known in the prior art and therefore possesses novelty and remarkable effectiveness.

[0118] A method, and the apparatus, Calculate the cycle time of vital data related to the cardiovascular system, We calculate a distribution with the nth period and the (n+1)th period as attributes. Based on the distribution, the presence or possibility of autonomic nervous system disorders or cardiovascular diseases is determined. method.

[0119] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made based on information about the distance of each plot to neighboring plots in the distribution, with at least one such distance. method.

[0120] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made by calculating the distance of each plot in the distribution to its neighboring plots and then making a decision based on the sum of at least two of these calculated distances. method.

[0121] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made by calculating the distance of each plot in the distribution to its neighboring plots, and then making a decision based on the sum of at least two of these calculated distances. The distance between the nth period and the plot where the (n+1)th period is approximately identical is excluded from the calculation of the sum. method.

[0122] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made based on information about the distance of each plot to neighboring plots in the distribution, with at least one such distance. Furthermore, the categorized evaluation based on distance information is transmitted to the terminal of the person whose vital data is being measured or the healthcare professional. method.

[0123] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made by analyzing the clusters in each plot within the distribution. method.

[0124] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made by analyzing the clusters in each plot of the distribution. If no clusters are found or the cluster density is low, it is determined that there is or is a possibility of autonomic nervous system disorder or cardiovascular disease. method.

[0125] The above method, The distribution is calculated using a distribution with the nth period and the (n+1)th period as attributes. The determination is made by analyzing the clusters of each plot in the distribution. Furthermore, the categorized evaluations based on the cluster analysis are transmitted to the terminal of the person whose vital data is being measured or the healthcare worker. method.

[0126] A method, and the apparatus, Calculate the cycle time of vital data related to the cardiovascular system, We calculate a distribution with the nth period and the (n+1)th period as attributes. Based on the distribution, determine the presence or possibility of autonomic nervous system disorders or cardiovascular diseases, or perform an assessment related to the autonomic nervous system or cardiovascular system. method.

[0127] The descriptions relating to some or all of the embodiments of this specification are incorporated herein by reference. The embodiments in this disclosure are not necessarily limited to disease diagnosis. They can also perform autonomic nervous system or cardiovascular assessments. "Performing an assessment" also includes performing any of the methods in this disclosure. For example, any processed vital data, CPL, or LSA, regardless of the manner in which it is processed, constitutes an "assessment," and calculating or transmitting or displaying CPL or LSA to a user terminal or healthcare provider's terminal is included in "performing an assessment." The resulting data, etc., since their numerical values ​​are processed from vital data, constitute an assessment of the autonomic nervous system or cardiovascular system. The inventors have considered that even if a disease is not diagnosed, simply presenting the resulting data, etc., to users or healthcare professionals can be helpful in distinguishing between a healthy state and a healthier state. As a result, there is a great effect of motivating users to live healthier lives and undergo regular checkups.

[0128] The invention disclosed herein only needs to achieve at least one of the effects described above. [Explanation of Symbols]

[0129] 1, 2… Heart sound analysis system 5… Communication lines 10... Heart sound measuring section 20… Heart sound data storage unit 30… Heart sound spectrum calculation unit 40… Abnormal State Detection Unit 50… Presentation part 51... Presentation operation section 60, 61... Transmitter / Receiver Unit 100... Control Processing Unit 110… Terminal 120… Server

Claims

1. A method, and the apparatus, Calculate the cycle time of vital data related to the cardiovascular system, We calculate a distribution with the nth period and the (n+1)th period as attributes. The distance of each plot in the distribution to its neighboring plots is calculated, and the distance between the plots where the nth period and the (n+1)th period are approximately the same is excluded from the calculation of the sum, and the sum of at least two or more calculated distances is calculated. Based on the aforementioned sum, the presence or absence or possibility of cardiovascular disease is determined or evaluated. method.

2. A device, Calculate the cycle time of vital data related to the cardiovascular system, We calculate a distribution with the nth period and the (n+1)th period as attributes. The distance of each plot in the distribution to its neighboring plots is calculated, and the distance between the plots where the nth period and the (n+1)th period are approximately the same is excluded from the calculation of the sum, and the sum of at least two or more calculated distances is calculated. Based on the aforementioned sum, the presence or absence or possibility of cardiovascular disease is determined or evaluated. Device.

Images