Program, information processing method, and determination system

Abstract

The present invention provides, for example, a program that makes it possible to determine an irregular pulse wave within a prescribed time width on the basis of a plurality of target pulse wave intervals.　Provided is a program for acquiring pulse waves and accelerations as time series data for a prescribed time width, identifying, on the basis of the acquired time series data regarding the pulse waves, a plurality of pulse wave intervals within the prescribed time width on a time-series basis, identifying, on the basis of the acquired time series data regarding the accelerations, a plurality of acceleration differences, which each are a difference between the maximum acceleration value and the minimum acceleration value within a time corresponding to a respective identified pulse wave interval, such that the plurality of acceleration differences are associated with the plurality of pulse wave intervals, extracting, on the basis of the plurality of identified acceleration differences, a plurality of target pulse wave intervals from the plurality of identified pulse wave intervals, and determining, on the basis of the plurality of extracted target pulse wave intervals, an irregular pulse wave within the prescribed time width.

Description

Program, information processing method, and determination system

[0001] This disclosure relates to a program, an information processing method, and a decision system.

[0002] Patent Document 1 discloses a technology that can improve the reliability of measurement results by switching between multiple measurement modes depending on whether or not a predetermined set of phenomena, such as arrhythmia, occurs when measuring a user's blood pressure.

[0003] Japanese Patent Publication No. 2024-037519

[0004] However, the invention described in Patent Document 1 had the problem that it could not determine irregular pulse waves within a predetermined time range based on a plurality of target pulse wave intervals.

[0005] The present invention aims to provide a program, etc., that can determine irregular pulse waves within a predetermined time range based on a plurality of target pulse wave intervals.

[0006] The present invention provides the following to the computer: (1) The program acquires pulse waves and acceleration as time-series data of a predetermined time width; based on the acquired time-series data of pulse waves, identifies multiple pulse wave intervals in time within the predetermined time width; based on the acquired time-series data of acceleration, identifies multiple acceleration differences, which are the difference between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified multiple pulse wave intervals, and associates these with each of the multiple pulse wave intervals; based on the identified multiple acceleration differences, extracts target multiple pulse wave intervals from the identified multiple pulse wave intervals; and based on the extracted target multiple pulse wave intervals, causes the computer to perform a process to determine irregular pulse waves within the predetermined time width.

[0007] In this embodiment of the present invention, (2) the program described in (1) above preferably determines the irregular pulse wave based on the target pulse wave intervals when the sum of the target pulse wave intervals is greater than or equal to a predetermined threshold.

[0008] (3) The program described in (1) or (2) above preferably identifies the number of irregular intervals that satisfy predetermined conditions from a plurality of target pulse wave intervals.

[0009] (4) The program described in any of (1) to (3) above preferably determines that an irregular pulse wave is present when the proportion of the number of identified irregular intervals is equal to or greater than a predetermined threshold.

[0010] (5) The program described in any of (1) to (4) above preferably determines intervals that exclude a first pulse wave interval in which the identified acceleration difference is greater than a threshold, a second pulse wave interval that is chronologically immediately preceding the first pulse wave interval, and a third pulse wave interval that is chronologically immediately following the first pulse wave interval.

[0011] (6) The program described in any of (1) to (5) above preferably makes multiple judgments within a specified time and determines that there is a pulse abnormality according to the proportion of irregular pulse waves determined in those multiple judgments.

[0012] (7) The program described in any of (1) to (6) above preferably outputs a determination result that determines that there is an irregular pulse wave or a pulse abnormality.

[0013] The present invention provides (8) an information processing method which involves acquiring pulse waves and acceleration as time-series data of a predetermined time width, identifying multiple pulse wave intervals in time series within the predetermined time width based on the acquired time-series data of pulse waves, identifying multiple acceleration differences which are the difference between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified multiple pulse wave intervals, associating each of the multiple pulse wave intervals with the multiple acceleration differences, extracting target multiple pulse wave intervals from the identified multiple pulse wave intervals based on the identified multiple acceleration differences, and determining irregular pulse waves within the predetermined time width based on the extracted target multiple pulse wave intervals.

[0014] The present invention provides (9) a determination system comprising a sensor and a control unit, the control unit acquires pulse waves and acceleration as time-series data of a predetermined time width using the sensor, identifies a plurality of pulse wave intervals in time series within the predetermined time width based on the acquired time-series data of pulse waves, identifies a plurality of acceleration differences which are the difference between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified plurality of pulse wave intervals, associates these with each of the plurality of pulse wave intervals, extracts a plurality of target pulse wave intervals from the identified plurality of pulse wave intervals based on the identified plurality of acceleration differences, and determines irregular pulse waves within the predetermined time width based on the extracted target plurality of pulse wave intervals.

[0015] According to the present invention, it is possible to determine irregular pulse waves within a predetermined time range based on a plurality of target pulse wave intervals.

[0016] This is a block diagram showing the configuration of a wearable device. This is an explanatory diagram showing an overview of a modified version of the irregular pulse wave detection system. This is an explanatory diagram showing an overview of a modified version of the irregular pulse wave detection system. This is an explanatory diagram showing an overview of a modified version of the irregular pulse wave detection system. This is an explanatory diagram showing an overview of a modified version of the irregular pulse wave detection system. This is an explanatory diagram showing the hardware configuration of the irregular pulse wave detection system. This is an explanatory diagram showing an example of a normal pulse wave and an irregular pulse wave. This is an explanatory diagram showing an example of time-series data with a predetermined time width. This is an explanatory diagram showing an example of a detection result in which an irregular pulse wave was detected. This is an explanatory diagram showing an example of a detection result in which a pulse abnormality was detected. This is a flowchart showing an example of the processing procedure of the irregular pulse wave detection system. This is a flowchart showing an example of the processing procedure of the irregular pulse wave detection system.

[0017] (Embodiment 1) This embodiment describes an irregular pulse wave detection system that uses pulse waves and acceleration acquired as time-series data of a predetermined time width to determine irregular pulse waves within a predetermined time width. The irregular pulse wave detection system includes an information processing terminal 1. The information processing terminal 1 is worn on the wrist or other part of the subject and performs measurements of pulse waves and acceleration, which are time-series data of a predetermined time width, and processing to determine irregular pulse waves. The information processing terminal 1 is, for example, a wearable device such as a smartwatch or a wristband-type measuring device. In this embodiment, the information processing terminal 1 is described as a wearable device 1.

[0018] Wearable device 1 comprises an LED (Light Emitting Diode) light source and a light receiving element for the LED light. Wearable device 1 emits infrared or green LED light onto the skin of the person being measured and receives the reflected light from the LED light to acquire the pulse wave of the person being measured as time-series data of a predetermined time width. Wearable device 1 also acquires the acceleration caused by the movement of the person being measured as time-series data of a predetermined time width.

[0019] The time series data with a predetermined time width is, for example, time series data over two minutes. The time series data with a predetermined time width can be changed as appropriate to suit the embodiment. In the following description, the time series data with a predetermined time width relating to pulse waves will be described as time series data of pulse waves over two minutes, and the time series data with a predetermined time width relating to acceleration will be described as time series data of acceleration over two minutes.

[0020] Figure 1 is a block diagram showing the configuration of a wearable device. The wearable device 1 includes a control unit 11, a storage unit 12, a display unit 13, a pulse wave sensor 14, an acceleration sensor 15, and a reading unit 16. The above-mentioned units are interconnected via a bus. The control unit 11 is configured using one or more processors such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), or a GPU (Graphics Processing Unit). The control unit 11 performs various information processing and control processing related to the wearable device 1 by appropriately executing a control program 12P (program product) stored in the storage unit 12.

[0021] The storage unit 12 includes RAM (Random Access Memory) or ROM (Read Only Memory), etc. The storage unit 12 stores various data necessary for the control program 12P executed by the control unit 11. The storage unit 12 temporarily stores data generated when the control unit 11 executes the control program 12P. The display unit 13 is, for example, a liquid crystal panel or an organic EL (electro-luminescence) panel, etc.

[0022] The pulse wave sensor 14 measures time-series data of a 2-minute pulse wave at predetermined time intervals (hereinafter, a 20-minute interval is used as an example). The pulse wave sensor 14 comprises a light-emitting unit 14a and a light-receiving unit 14b. The light-emitting unit 14a is equipped with an LED light source having a wavelength range such as red light or green light. The light-emitting unit 14a may also be equipped with an LED light source having a different wavelength range. The light-emitting unit 14a emits red or green LED light onto the skin of the person being measured at predetermined time intervals. The light-receiving unit 14b receives the reflected light from the LED light emitted by the light-emitting unit 14a, thereby measuring time-series data of a 2-minute pulse wave at predetermined time intervals. The wearable device 1 removes unwanted frequency band components included in the 2-minute time-series data of the pulse wave using a low-pass filter, a high-pass filter, a band-pass filter, etc.

[0023] The acceleration sensor 15 measures time-series data of acceleration over a two-minute period at 20-minute intervals. The wearable device 1 may be equipped with a gyroscope or the like instead of the acceleration sensor 15. The reading unit 16 reads information stored in the portable storage medium 1a. The portable storage medium 1a is, for example, a CD (Compact Disc), DVD (Digital Versatile Disc), USB (Universal Serial Bus) memory, or SD (Secure Digital). The reading unit 16 reads the control program 12P from the portable storage medium 1a. The control unit 11 stores the read control program 12P in the storage unit 12. The control unit 11 may be equipped with a communication unit that sends and receives information with external equipment (not shown). The control program 12P may also be downloaded by the communication unit 17 (see Figure 6) from a program provided via a network and stored in the storage unit 12.

[0024] In the present embodiment, the irregular pulse wave determination system may be configured by a wearable device 1 and a server. FIG. 2 is an explanatory diagram illustrating an outline of a modified example of the irregular pulse wave determination system. An irregular pulse wave determination system 100 includes a wearable device 1 and a server 2. The wearable device 1 is worn on the wrist or the like of a subject 3. The server 2 is, for example, a server device, a personal computer, a general-purpose tablet PC, or a cloud server communicatively connected via a network N. In the irregular pulse wave determination system of FIG. 2, the control unit of the wearable device 1 performs processing of acquiring and transmitting time-series data of two-minute pulse waves and the like, and displaying the determination result of irregular pulse waves, and the control unit of the server 2 performs processing of processing the time-series data of pulse waves and the like, determining whether the pulse wave is irregular or not, and transmitting the determination result of irregular pulse wave. The control program is stored in a storage unit on the server 2. In addition, the control unit of the wearable device 1 performs processing for displaying the determination result transmitted from the server 2 on a display unit. The control unit of the wearable device 1 and the control unit of the server 2 are configured using one or more processors. Note that the control unit of the wearable device 1 may perform processing of collectively transmitting the acquired time-series data of pulse waves to the server 2 at predetermined intervals (for example, one-day intervals) via a smartphone, tablet, router, or the like owned by the subject 3 communicatively connected to the network N, and collectively receiving the determination result transmitted from the server 2 at predetermined intervals (for example, one-day intervals).

[0025] In the present embodiment, the irregular pulse wave determination system 100 may be configured of the wearable device 1 and a display terminal. Figure 3 is an explanatory diagram showing an outline of a modified example of the irregular pulse wave determination system. The irregular pulse wave determination system 100 includes the wearable device 1 and the display terminal 4. The display terminal 4 is, for example, a computer, a smartphone, a tablet, or the like. In the irregular pulse wave determination system 100 of Figure 3, a control unit of the wearable device 1 performs processing including acquiring time-series data of pulse waves for two minutes, processing the time-series data of pulse waves, determining whether the pulse wave is irregular, and transmitting the determination result of the irregular pulse wave, and a control unit of the display terminal 4 such as a smartphone or a tablet performs processing of displaying the determination result transmitted from the wearable device 1 on a display unit of the display terminal 4.

[0026] The control unit of the wearable device 1 and the control unit of the display terminal 4 are configured using one or more processors. Data transmission from the wearable device 1 to the display terminal 4 may be performed directly by short-range wireless communication, or may be performed via a network. Furthermore, the wearable device 1 may not include a display unit. Note that in the irregular pulse wave determination system 100 of Figure 3, the control unit of the wearable device 1 may perform processing of acquiring and transmitting two minutes of time-series pulse wave data, and the control unit of the display terminal 4 may perform processing including processing the time-series pulse wave data, determining whether the pulse wave is irregular, and displaying the irregular pulse wave determination result on a display unit. In this case, the control program is stored in a storage unit on the display terminal 4.

[0027] In the present embodiment, the irregular pulse wave determination system 100 may be configured of the wearable device 1, a server 2, and a display terminal 4 owned by a subject 3 wearing the wearable device 1. Figure 4 is an explanatory diagram showing an outline of a modified example of the irregular pulse wave determination system. The irregular pulse wave determination system 100 includes the wearable device 1, the server 2, and the display terminal 4. The display terminal 4 owned by the subject 3 is, for example, a computer, a smartphone, a tablet, or the like.

[0028] In the irregular pulse wave detection system 100 shown in Figure 4, the control unit of the wearable device 1 performs the process of acquiring and transmitting time-series data of the pulse wave over a two-minute period. The control unit of the server 2 performs the processing of the time-series data of the pulse wave, determines whether or not it is an irregular pulse wave, and transmits the result of the irregular pulse wave detection. The control unit of the display terminal 4 displays the detection result transmitted from the server 2 on the display unit of the display terminal 4. The control program is stored in the memory unit of the server 2. The control unit of the server 2 transmits the detection result of the subject to the display terminal 4 once the display terminal 4 is linked to the wearable device 1 via the server 2. The detection result displayed on the display terminal 4 includes icons indicating pulse abnormalities, as well as numerical values ​​and time-series graphs calculated based on the time-series data of the pulse wave, as shown in Figures 9 and 10. Furthermore, the control unit of the wearable device 1 may perform a procedure to send the acquired time-series data of pulse waves to the server 2 in batches at predetermined intervals (for example, every day) via a display terminal 4, such as a smartphone or tablet, or a router, owned by the subject 3, which is connected to the network N. In addition, the control unit of the server 2 may perform a process to send the irregular pulse wave determination result to the display terminal 4 in response to a request from the display terminal 4.

[0029] Furthermore, if the control unit of the display terminal 4 determines that there is an abnormality such as a pulse abnormality, it displays an alert message on the display unit, as shown in Figure 10, to notify the user of the abnormality. The control unit of the wearable device 1, the control unit of the server 2, and the control unit of the display terminal 4 are all configured using one or more processors. Also, the wearable device 1 does not necessarily have a display unit.

[0030] In this embodiment, the irregular pulse wave detection system 100 may consist of a plurality of wearable devices 1, a server 2, a management terminal for medical professionals, and a plurality of display terminals 4 held by a plurality of subjects 3. Figure 5 is an explanatory diagram showing an overview of a modified example of the irregular pulse wave detection system. The irregular pulse wave detection system 100 comprises a wearable device 1, a server 2, a plurality of display terminals 4 held by a plurality of subjects 3, and a management terminal 5 for a medical professional 6. Figure 6 is an explanatory diagram showing the hardware configuration of the irregular pulse wave detection system. The irregular pulse wave detection system 100 comprises a plurality of wearable devices 1, a server 2, a management terminal 5, and a plurality of display terminals 4. The management terminal 5 for the medical professional 6 is, for example, a smartphone, tablet, or computer.

[0031] Wearable device 1 comprises a control unit 11, a display unit 13, a pulse wave sensor 14, an acceleration sensor 15, and a communication unit 17. Server 2 comprises a control unit 21, a storage unit 22, a reading unit 23, and a communication unit 24. Display terminal 4 comprises a control unit 41, a communication unit 42, and a display unit 43. Management terminal 5 comprises a control unit 51, a communication unit 52, a display unit 53, and an input unit 54. The communication unit 17 of wearable device 1, the communication unit 24 of server 2, the communication unit 42 of display terminal 4, and the communication unit 52 of management terminal 5 are communication modules that transmit and receive information via short-range wireless communication or a network N, etc. Note that the display unit 13 may be omitted from wearable device 1.

[0032] The control unit 21 of server 2, the control unit 41 of display terminal 4, and the control unit 51 of management terminal 5 are each configured using one or more processors such as a CPU, MPU, or GPU. The storage unit 22 of server 2 includes RAM or ROM. The reading unit 23 of server 2 reads the control program 22P from the portable storage medium 1a. The control unit 21 of server 2 stores the read control program 22P in the storage unit 12. The display unit 43 of display terminal 4 and the display unit 53 of management terminal 5 are, for example, liquid crystal panels or organic EL panels. The input unit 54 is, for example, an input interface such as a mouse and keyboard. Server 2 may also download the control program 22P provided from an external source via the network N using the communication unit 24 and store the downloaded control program 22P in the storage unit 12. In this case, the reading unit 23 of server 2 may be omitted.

[0033] In the irregular pulse wave detection system 100 shown in Figures 5 and 6, each control unit 11 of a plurality of wearable devices 1 processes the acquisition and transmission of time-series data of the pulse wave of a subject 3 wearing the wearable device 1 for two minutes. The server 2 processes the time-series data of the pulse wave of each of the plurality of subjects 3, determines whether or not it is an irregular pulse wave, and transmits the result of the irregular pulse wave determination. The control unit 51 of the management terminal 5 processes the determination results for each of the plurality of subjects 3 transmitted from the server 2 and displays them on the display unit 53 of the management terminal 5. The control unit 41 of each of the plurality of display terminals 4 processes the determination results transmitted from the server 2 and displays them on the display unit 43 of the display terminal 4. The control unit 11 of each wearable device 1 may also process the acquisition of time-series pulse wave data to be transmitted to the server 2 in batches at predetermined intervals (for example, every day) via a display terminal 4 or router owned by each subject 3 that is connected to the network N.

[0034] The control program 22P is stored in the storage unit 22 on the server 2. The control unit 21 of the server 2 processes the transmission of the judgment results for each of the multiple subjects 3 to the management terminal 5, as the management terminal 5 is linked to multiple wearable devices 1 via the server 2. The control unit 21 of the server 2 also processes the transmission of the judgment results for each of the multiple subjects 3 to the linked display terminal 4, as each of the multiple display terminals 4 is linked to each of the multiple wearable devices 1 via the server 2, so that a wearable device 1 worn by a specific subject 3 is paired with a display terminal 4 owned by that subject 3. The control unit 21 of the server 2 may also process the transmission of the irregular pulse wave judgment result for the subject 3 to which the display terminal 4 is linked to the display terminal 4, in response to a request from each display terminal 4.

[0035] The control unit 51 of the management terminal 5 processes the operation of a medical professional 6 via the input unit 54 to select a subject 3 to be displayed from among multiple subjects 3, and displays the judgment result for the selected subject 3 on the display unit 53. The judgment result for the subject 3 displayed on the management terminal 5 includes icons indicating pulse abnormalities, numerical values ​​calculated based on pulse wave time series data, etc., as shown in Figures 9 and 10. Furthermore, if the control unit 51 of the management terminal 5 determines that the subject 3 has an abnormality such as a pulse abnormality, it displays an alert on the display unit 53 to notify the user of the abnormality in the subject 3.

[0036] The judgment result displayed on each of the multiple display terminals 4 is the judgment result for a specific subject 3 transmitted from the server 2, and includes icons indicating pulse abnormalities, numerical values ​​and time-series graphs calculated based on time-series data of pulse waves, etc., as shown in Figures 9 and 10, as well as a message for the subject 3. The message displayed on each of the multiple display terminals 4 includes an alert for the subject 3 that is displayed when it is determined that the subject 3 has an abnormality such as a pulse abnormality.

[0037] As described above, the irregular pulse wave detection system 100 can be implemented in multiple forms. In the following description, an example of implementation in the form shown in Figure 1 will be explained.

[0038] Figure 7 is an explanatory diagram showing examples of normal and irregular pulse waves. The upper part of Figure 7 shows an example of a normal pulse wave, and the lower part shows an example of an irregular pulse wave. In Figure 7, the vertical axis represents voltage, and the horizontal axis represents time. In a normal pulse wave, the interval between pulse waves (hereinafter referred to as pulse wave interval) is kept relatively constant. However, in an irregular pulse wave, many irregular pulses occur. Compared to the average of normal pulse wave intervals, the pulse wave interval in the parts where irregular pulses occur is greatly irregular.

[0039] Irregular pulse waves are an important indicator for detecting signs of arrhythmias, including atrial fibrillation. However, irregular pulse waves detected by wearable devices such as device 1 contain a mixture of irregular pulse waves originating from diseases such as arrhythmias and irregular pulse waves originating from body movements such as acceleration. Therefore, accurate detection of signs of arrhythmias has been difficult. This embodiment describes a method in which an irregular pulse wave determination system simultaneously acquires time-series data of pulse waves and time-series data of acceleration, excludes unnecessary irregular pulses originating from acceleration included in the time-series data of pulse waves, and then determines whether or not the time-series data of pulse waves is an irregular pulse wave.

[0040] The control unit 11 uses the pulse wave sensor 14 and the acceleration sensor 15 to acquire time-series data of pulse waves and acceleration over a 2-minute period at 20-minute intervals. Figure 8 is an explanatory diagram showing an example of time-series data with a predetermined time width. Figure 8A is an explanatory diagram showing an example of time-series data of pulse waves over a 2-minute period. In the graph of Figure 8A, the vertical axis represents voltage (mV), and the horizontal axis represents time. Figure 8B is an explanatory diagram showing multiple pulse wave intervals included in the time-series data of pulse waves over a 2-minute period. In the graph of Figure 8B, the vertical axis represents the width of the pulse wave interval (ms), and the horizontal axis represents time. Figure 8C is an explanatory diagram showing an example of time-series data of acceleration over a 2-minute period. In the graph of Figure 8C, the vertical axis represents acceleration (mm / s²). ２ The horizontal axis shows the pulse wave time series and the acceleration time series data for the 2-minute interval.

[0041] The control unit 11 identifies a plurality of regions sandwiched between two adjacent troughs in two-minute time-series pulse wave data (FIG. 8A) as pulses (pulses) in time series. Specifically, the control unit 11 identifies, in the time-series pulse wave data shown in FIG. 8A, pulse P ｔ－１ , pulse P ｔ , pulse P ｔ＋１ , and pulse P ｔ＋２ in time series. The control unit 11 identifies a plurality of maximum values of each pulse as peaks. In FIG. 8A, the peak of each pulse is indicated by a cross (x).

[0042] The control unit 11 identifies a plurality of intervals between peaks of adjacent pulses as pulse wave intervals in time series. Specifically, the control unit 11, in the time-series pulse wave data shown in FIG. 8A, pulse P t―１ and pulse P ｔ pulse wave interval RR ｔ―１ , pulse P ｔ and pulse P ｔ＋１ pulse wave interval RR ｔ , and pulse P ｔ＋１ and pulse P ｔ＋２ pulse wave interval RR ｔ＋１ in time series. When identifying a plurality of pulse wave intervals, if the distance between the peaks of adjacent pulses is equal to or less than a specified value, the control unit 11 may exclude the corresponding pulse wave interval or pulse.

[0043] The graph of FIG. 8B shows a plurality of pulse wave intervals identified from the time-series pulse wave data of FIG. 8A (for example, pulse wave interval RR ｔ―１ , pulse wave interval RR ｔ and pulse wave interval RR ｔ＋１(etc.) are illustrated. Specifically, the graph in Figure 8B is a scatter plot of multiple pulse wave intervals identified from the pulse wave time-series data in Figure 8A, with the width of the pulse wave interval (ms) on the vertical axis and the time of the earlier peak among the peaks of adjacent pulses used to identify the pulse wave interval on the horizontal axis. Multiple pulse wave intervals are represented by white circles, black circles, and triangles, etc. White circles indicate the target pulse wave intervals, black circles indicate intervals that are excluded, and triangles indicate irregular intervals that are part of the target pulse wave intervals. White circles, black circles, and triangles will be described later. The method of displaying multiple pulse wave intervals is not limited to the display format in Figure 8B. Multiple pulse wave intervals may be represented by different colors (e.g., red, green, and black) or different shapes (e.g., squares and stars), etc. The larger the width of the pulse wave interval, the higher each pulse wave interval is shown in the illustration, and the smaller the width of the pulse wave interval, the lower each pulse wave interval is shown in the illustration. Furthermore, the graph in Figure 8B shows a horizontal line (in bold) indicating the median value of the multiple pulse wave intervals being studied.

[0044] The control unit 11 refers to the 2-minute acceleration time series data shown in Figure 8C and identifies each acceleration difference, which is the difference between the maximum and minimum acceleration values ​​within the time corresponding to each identified pulse wave interval, in association with each pulse wave interval. Specifically, the control unit 11 identifies the pulse wave interval RR ｔ Within the corresponding time (RR in Figure 8A) ｔ In Figure 8C, corresponding to AA ｔ In this case, the acceleration difference (max(t) - min(t)), which is the difference between the maximum acceleration (max(t)) and the minimum acceleration (min(t)), is calculated as the pulse wave interval RR. ｔ It is identified in correspondence with a plurality of pulse wave intervals (for example, pulse wave interval RR ｔ―１ and pulse wave interval RR ｔ＋１ By performing the same process on (etc.), multiple acceleration differences, which are the difference between the maximum and minimum acceleration values ​​within a time period corresponding to multiple pulse wave intervals, are identified in association with multiple pulse wave intervals.

[0045] The control unit 11 determines which of the multiple sets of pulse wave intervals and the acceleration difference corresponding to said pulse wave intervals is below a threshold (40 mm / s²). ２A pulse wave interval greater than (as shown in the example) is identified as the first pulse wave interval. Specifically, the control unit 11, AA in Figure 8C t In this case, the difference in acceleration between the maximum acceleration (max(t)) and the minimum acceleration (min(t)) (max(t) - min(t)) is 40 (mm / s²). ２ ) is greater than the corresponding pulse wave interval RR in Figures 8A and 8B t This is identified as the first pulse wave interval.

[0046] The control unit 11 identifies the second pulse wave interval that is chronologically immediately preceding the first pulse wave interval, and the third pulse wave interval that is chronologically immediately following the first pulse wave interval. Specifically, the control unit 11 identifies the pulse wave interval RR that is identified as the first pulse wave interval. ｔ and the pulse wave interval RR immediately preceding it in chronological order ｔ－１ Identify the second pulse wave interval as RR t And the pulse wave interval RR that follows immediately in chronological order ｔ＋１ This is identified as the third pulse wave interval. When the control unit 11 has identified a plurality of first pulse wave intervals, it identifies a plurality of sets of second and third pulse wave intervals.

[0047] The control unit 11 determines the intervals that exclude the identified first pulse wave interval, second pulse wave interval, and third pulse wave interval. Specifically, the control unit 11 refers to multiple pulse wave intervals (Figure 8B) included in the pulse wave time series data and determines the pulse wave interval RR ｔ (First pulse wave interval) and pulse wave interval RR ｔ－１ (Second pulse wave interval) and pulse wave interval RR ｔ＋１ The interval is determined to exclude (the third pulse wave interval). In Figure 8B, the pulse wave interval RR ｔ and pulse wave interval RR ｔ－１ and pulse wave interval RR ｔ＋１ The intervals that are excluded, including the one indicated by the black circle, are shown.

[0048] The control unit 11 extracts the target pulse wave intervals by excluding intervals to be excluded from the multiple pulse wave intervals. Specifically, the control unit 11 extracts the pulse wave interval RR shown by the black circle from among the multiple pulse wave intervals. ｔ and pulse wave interval RR ｔ－１ and pulse wave interval RR ｔ＋１The control unit 11 extracts multiple target pulse wave intervals (white circles and triangles in Figure 8B), excluding the ones shown above. The control unit 11 determines whether the total value (cumulative time) of the extracted target pulse wave intervals is equal to or greater than a predetermined threshold (hereinafter, 25 seconds is used as an example). Specifically, the control unit 11 determines whether the total value on the vertical axis of the target pulse wave intervals shown as white circles and triangles in Figure 8B is 25 seconds or more.

[0049] The control unit 11 calculates the median of the multiple target pulse wave intervals if the sum of the target pulse wave intervals is 25 seconds or more. The control unit 11 may also calculate the average value or mode of the target pulse wave intervals instead of the median. An example of calculating the median of the target pulse wave intervals will be described below. In Figure 8B, the median of the target pulse wave intervals is shown in bold horizontal lines.

[0050] The control unit 11 uses the calculated median value to identify the number of irregular intervals that satisfy a predetermined condition from the target multiple pulse wave intervals. The number of irregular intervals that satisfy the predetermined condition is, for example, the number of irregular intervals that are more than ±25% away from the median value of the target multiple pulse wave intervals. In Figure 8B, irregular intervals that are more than ±25% away from the median value of the target multiple pulse wave intervals are shown as triangles, and there are 2 such irregular intervals.

[0051] In this embodiment, regardless of whether the target pulse wave intervals are consecutive or not, if the total value of the pulse wave intervals is 25 seconds or more, the control unit 11 identifies the number of irregular intervals that satisfy a predetermined condition (the number of irregular intervals that are ±25% or more away from the median of the target pulse wave intervals) from the target pulse wave intervals. However, the embodiment is not limited to this. If the total value of the consecutive pulse wave intervals is 25 seconds or more, the control unit 11 may identify the number of irregular intervals that satisfy a predetermined condition from the target pulse wave intervals.

[0052] The control unit 11 calculates the ratio of irregular intervals. The ratio of irregular intervals is, for example, the ratio of the number of target pulse wave intervals to the number of irregular intervals that are more than ±25% from the median of the target pulse wave intervals. In Figure 8B, the number of target pulse wave intervals is 21, which is the sum of the number of pulse wave intervals indicated by white circles (19) and the number of pulse wave intervals (irregular intervals) indicated by triangles (2). Therefore, the ratio of irregular intervals is 2 / 21 * 100 = 9.5%.

[0053] The control unit 11 determines whether the percentage of the specified irregular intervals is greater than or equal to a predetermined value (hereinafter, 20% or more is used as an example). If the percentage of irregular intervals is 20% or more, the control unit 11 determines that it is an irregular pulse wave. If the percentage of irregular intervals is not 20% or more, or if the sum of the intervals of the multiple pulse waves being tested is not 25 seconds or more, the control unit 11 determines that it is not an irregular pulse wave. In Figure 8B, the percentage of irregular intervals is 9.5...%, so the control unit 11 determines that it is not an irregular pulse wave. If the control unit 11 determines that it is an irregular pulse wave, it displays the determination result on the display unit 13.

[0054] Figure 9 is an explanatory diagram showing an example of a judgment result in which an irregular pulse wave was determined. The screen d1 shown in Figure 9 displays a numerical field d11 and a graph field d12. The numerical field d11 is displayed at the top of the screen d1, and the graph field d12 is displayed at the bottom of the screen d1. The numerical field d11 displays the date and time when the pulse wave time series data was acquired, as well as numerical values ​​indicating the patient's blood pressure index, pulse rate, and activity level. The blood pressure index is a value that correlates with the systolic blood pressure calculated from the pulse wave time series data. The pulse rate is the number of pulses calculated from the pulse wave time series data. The activity level is the level of the patient's activity level calculated from the acceleration time series data using a known method.

[0055] The activity level is a numerical value calculated based on the time-series data of acquired acceleration, and in this embodiment, it is expressed as the "minutes" of normal walking in one-hour units. Specifically, the control unit 11 calculates the cumulative number of steps in one hour based on the time-series data of acquired acceleration, calculates the walking minutes from the calculated cumulative number of steps, and displays it. The activity level to be displayed may also be the cumulative number of steps in one-hour units. Alternatively, the activity level may be exercise (EX), which is calculated by calculating the intensity of physical activity expressed in units of METs from the time-series data of composite acceleration calculated based on the three-axis acceleration obtained from the three-axis acceleration sensor, and then integrating the obtained intensity of physical activity over a predetermined time unit, for example, one hour.

[0056] The graph column d12 displays a line graph showing the hourly representative values ​​(e.g., median and mean) of blood pressure indicators, a line graph showing the hourly representative values ​​(e.g., median and mean) of pulse rate, and a bar graph showing the hourly activity level, corresponding to the date displayed in the numerical column d11. The line graph showing the hourly representative values ​​of blood pressure indicators is displayed as a solid line. The line graph showing the hourly representative values ​​of pulse rate is displayed as a dotted line.

[0057] In the graph section d12, the portion corresponding to the time period displayed in the numerical section d11 (for example, 8:00 to 8:59) is marked with a dashed line. Furthermore, if an irregular pulse wave or pulse abnormality is detected in each hourly time period, the corresponding time period is highlighted (for example, the hatched portion). In addition, an icon I1 is displayed above the highlighted portion. Icon I1 indicates that an irregular pulse wave or pulse abnormality has been determined. Different icons may be used for irregular pulse wave detection and pulse abnormality detection. Alternatively, instead of icon I1, the message "Irregular pulse wave detected." may be displayed on screen d1 to indicate that an irregular pulse wave has been detected. Note that if the display unit 13 of the wearable device 1 is small, the numerical section d11 and graph section d12 may be displayed by switching between them according to a slide operation or the like. Also, when displaying on a display terminal 4 linked to the wearable device 1, it is preferable to display the numerical section d11 and graph section d12 on a single screen, as shown in Figure 9.

[0058] The control unit 11 stores the determination result, which indicates that the pulse wave is irregular, in the storage unit 12, in parallel with displaying the determination result. If the control unit 11 determines that the pulse wave is not irregular, it stores the determination result in the storage unit 12 without displaying the determination result that it is not an irregular pulse wave. If the processing of time-series data of the pulse wave, determination of whether or not it is an irregular pulse wave, and transmission of the determination result of whether or not it is an irregular pulse wave are performed on an external processing device such as the server 2, the determination result is stored in the storage unit of the external processing device.

[0059] In this embodiment, an example is shown in which the control unit 11 determines that a pulse wave is not irregular if the sum of the multiple target pulse wave intervals is not 25 seconds or more, but the embodiment is not limited to this. The control unit 11 may store the multiple target pulse wave intervals as unusable data if the sum of the multiple target pulse wave intervals is not 25 seconds or more. The processing in that case will be described below. The control unit 11 repeats the process from acquiring the time-series data of the pulse wave over two minutes to extracting the multiple target pulse wave intervals. The control unit 11 determines whether the sum of the multiple target pulse wave intervals extracted again is 25 seconds or more. If the sum of the multiple target pulse wave intervals extracted again is 25 seconds or more, the control unit 11 calculates the median value of the pulse wave intervals. If the sum of the multiple target pulse wave intervals extracted again is not 25 seconds or more, the control unit 11 stores the pulse wave intervals as unusable data and repeats the process from acquiring the time-series data of the pulse wave over two minutes to extracting the multiple target pulse wave intervals.

[0060] The control unit 11 repeatedly acquires time-series data of pulse waves and acceleration over two minutes at 20-minute intervals using the pulse wave sensor 14 and acceleration sensor 15. The control unit 11 repeatedly performs the above process using the time-series data of pulse waves and acceleration over two minutes that have been repeatedly acquired within a specified time, thereby determining multiple times whether the acquired time-series data of pulse waves are irregular pulse waves. Specifically, if the specified time is one hour, the control unit 11 repeatedly performs the above process using the time-series data of pulse waves and acceleration over two minutes that have been repeatedly received, thereby determining three times whether the acquired time-series data of pulse waves are irregular pulse waves.

[0061] The control unit 11 calculates the percentage of irregular pulse waves determined in the multiple judgments. Specifically, if an irregular pulse wave is determined once in three judgments, the control unit 11 calculates "1 / 3" as the percentage of irregular pulse waves. The control unit 11 determines that there is a pulse abnormality according to the calculated percentage of irregular pulse waves. Specifically, the control unit 11 determines that there is a pulse abnormality if the percentage of irregular pulse waves is "2 / 3" or more, and determines that there is no pulse abnormality if the percentage of regular pulse waves is less than "2 / 3". The control unit 11 displays the judgment result of determining a pulse abnormality on the display unit 13.

[0062] Figure 10 is an explanatory diagram showing an example of a judgment result in which a pulse abnormality was determined. Screen d2 in Figure 10 has the same configuration as screen d1 (Figure 9), but also displays the message "A pulse abnormality has been detected. There is a risk of atrial fibrillation, etc., so please get examined at a hospital." The message indicating that a pulse abnormality has been determined is displayed between the numerical field d11 and the graph field d12. The message indicating that a pulse abnormality has been determined may be displayed in a different position from Figure 10, such as the top, right, left, or center of screen d2. If the display unit 13 of the wearable device 1 is small, the numerical field d11, the graph field d12, and the message indicating a pulse abnormality may be displayed while switching them according to a slide operation or the like. In this case, it is preferable that the control unit 11 of the wearable device 1 automatically switches the displayed numerical field d11 and graph field d12 to a message indicating a pulse abnormality when a pulse abnormality is detected, or displays a message indicating a pulse abnormality when the wearable device 1 is started, thereby controlling the display unit 13 to prioritize the display of the message over the numerical field d11 and graph field d12.

[0063] The control unit 11 stores the determination result in the storage unit 12 in parallel with displaying the determination result that an abnormal pulse was detected. If the control unit 11 determines that there is no abnormal pulse, it stores the determination result in the storage unit 12 without displaying the determination result that there is no abnormal pulse. When processing time-series data of pulse waves, determining whether or not there is an irregular pulse wave, and transmitting the determination result of an irregular pulse wave are performed on an external processing device such as a server, the determination result is stored in the storage unit of the external processing device.

[0064] Figures 11 and 12 are flowcharts illustrating an example of the processing procedure for an irregular pulse wave detection system. The control unit 11 uses a pulse wave sensor 14 and an acceleration sensor 15 to acquire time-series data of pulse waves and acceleration over two minutes at 20-minute intervals (step S101). The control unit 11 identifies multiple pulses (pulses) in the time-series data of the two-minute pulse wave (Figure 8A) as regions between two adjacent troughs (step S102). The control unit 11 identifies multiple peaks as the maximum values ​​of each pulse (step S103). The control unit 11 identifies multiple pulse wave intervals in the time-series data as the intervals between the peaks of adjacent pulses (step S104). Note that when irregular pulse wave detection is performed on an external processing device such as a server 2, step S101 refers to acquiring time-series data of pulse waves and acceleration over two minutes measured using the pulse wave sensor 14 and acceleration sensor 15 from the wearable device 1.

[0065] The control unit 11 refers to the time-series data of acceleration over two minutes (Figure 8C) and identifies each acceleration difference, which is the difference between the maximum and minimum acceleration values ​​within the time period corresponding to each identified pulse wave interval, in association with each pulse wave interval (step S105). The control unit 11 repeatedly performs the process in step S105 for the multiple pulse wave intervals identified in step S104, thereby identifying multiple acceleration differences, which are the differences between the maximum and minimum acceleration values ​​within the time period corresponding to multiple pulse wave intervals, in association with multiple pulse wave intervals (step S106).

[0066] The control unit 11 determines that among multiple sets of pulse wave intervals and the acceleration differences corresponding to said pulse wave intervals, the acceleration difference is 40 (mm / s²). ２The control unit 11 identifies a pulse wave interval larger than ) as the first pulse wave interval (step S107). The control unit 11 identifies a second pulse wave interval that is chronologically immediately preceding the first pulse wave interval, and a third pulse wave interval that is chronologically immediately following the first pulse wave interval (step S108). The control unit 11 determines that the identified first pulse wave interval, second pulse wave interval, and third pulse wave interval are excluded from the interval (step S109).

[0067] The control unit 11 extracts the target pulse wave intervals by excluding intervals that are not to be targeted from the multiple pulse wave intervals (step S110). The control unit 11 determines whether the sum of the extracted target pulse wave intervals is 25 seconds or more (step S111). If the control unit 11 determines that the sum of the target pulse wave intervals is 25 seconds or more (step S111: YES), it calculates the median of the target pulse wave intervals (step S112). Using the median calculated in step S112, the control unit 11 identifies the number of irregular intervals that satisfy a predetermined condition (for example, the number of irregular intervals that are ±25% or more from the median) from the target pulse wave intervals (step S113). The control unit 11 determines the ratio of the number of irregular intervals by calculating the ratio of the target pulse wave intervals to the number of irregular intervals that satisfy the predetermined condition (step S114).

[0068] The control unit 11 determines whether the proportion of the identified irregular intervals is 20% or more (step S115). If the proportion of irregular intervals is 20% or more (step S115: YES), the control unit 11 determines that it is an irregular pulse wave (step S116). The control unit 11 displays the determination result of determining that it is an irregular pulse wave on the display unit 13 (step S117). If the proportion of irregular intervals is not 20% or more (step S115: NO), or if the control unit 11 determines that the sum of the target pulse wave intervals is not 25 seconds or more (step S111: NO), it determines that it is not an irregular pulse wave (step S118).

[0069] Furthermore, if the control unit 11 determines that the sum of the intervals between the target pulse waves is not 25 seconds or more (step S111: NO), it may return to step S101 and repeat the processes from steps S101 to S110. After step S117 or step S118, the control unit 11 stores the determination result of whether or not it is an irregular pulse wave (determination result that it is an irregular pulse wave, or determination result that it is not an irregular pulse wave) in the storage unit 12 (step S119).

[0070] The control unit 11 determines whether or not one hour (specified time) has elapsed (step S120). If the control unit 11 determines that one hour (specified time) has not elapsed (step S120: NO), it returns to step S101 and repeats the processes from steps S101 to S119. If the control unit 11 determines that one hour (specified time) has elapsed (step S120: YES), it calculates the percentage of irregular pulse waves determined in multiple determinations (step S121).

[0071] The control unit 11 determines whether the proportion of irregular pulse waves determined in multiple judgments is 2 / 3 or more (step S122). If the control unit 11 determines that the proportion of irregular pulse waves determined is 2 / 3 or more (step S122: YES), it determines that there is a pulse abnormality (step S123). The control unit 11 displays the judgment result of determining a pulse abnormality on the display unit 13 (step S124). If the control unit 11 determines that the proportion of irregular pulse waves determined is not 2 / 3 or more (less than 2 / 3) (step S122: NO), it determines that there is no pulse abnormality (step S125). After step S124 or step S125, the control unit 11 stores the judgment result of whether there is a pulse abnormality or not (judgment result of determining a pulse abnormality, or judgment result of determining that there is no pulse abnormality) in the storage unit 12 (step S126).

[0072] According to Embodiment 1, the irregular pulse wave determination system acquires pulse waves and acceleration as time-series data of a predetermined time width, identifies multiple pulse wave intervals in a time series within the predetermined time width based on the acquired time-series data of pulse waves, and identifies multiple acceleration differences, which are the differences between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified multiple pulse wave intervals, in association with each of the multiple pulse wave intervals, based on the acquired time-series data of acceleration.

[0073] According to Embodiment 1, the irregular pulse wave determination system extracts target pulse wave intervals from a plurality of identified pulse wave intervals based on a plurality of identified acceleration differences, and determines irregular pulse waves within a predetermined time width based on the extracted target pulse wave intervals.

[0074] According to Embodiment 1, the irregular pulse wave determination system determines an irregular pulse wave based on the target pulse wave intervals when the sum of the target pulse wave intervals is greater than or equal to a predetermined threshold.

[0075] According to Embodiment 1, the irregular pulse wave determination system can identify the number of irregular intervals that satisfy predetermined conditions from a plurality of target pulse wave intervals.

[0076] According to Embodiment 1, the irregular pulse wave determination system determines an irregular pulse wave to be present when the ratio of the number of identified irregular intervals is equal to or greater than a predetermined threshold.

[0077] According to Embodiment 1, the irregular pulse wave determination system can determine intervals that exclude a first pulse wave interval in which the identified acceleration difference is greater than a threshold, a second pulse wave interval that is chronologically immediately preceding the first pulse wave interval, and a third pulse wave interval that is chronologically immediately following the first pulse wave interval.

[0078] According to Embodiment 1, the irregular pulse wave detection system performs multiple detections within a specified time and determines a pulse abnormality based on the proportion of irregular pulse waves detected in those multiple detections.

[0079] According to Embodiment 1, the irregular pulse wave detection system can output a detection result that indicates an irregular pulse wave or pulse abnormality.

[0080] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the invention is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended.

[0081] The matters described in each embodiment can be combined with each other. Furthermore, the independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. In addition, the claims use a form in which claims referencing two or more other claims (multi-claim form), but are not limited to this. A form in which multi-claims referencing at least one multi-claim (multi-multi-claim) may also be used.

[0082] 1 Information terminal device (wearable device) 11 Control unit 12 Storage unit 12P Control program 13 Display unit 14 Pulse wave sensor 14a Light-emitting unit 14b Light-receiving unit 15 Acceleration sensor 16 Reading unit 17 Communication unit 1a Portable storage medium 2 Server 21 Control unit 22 Storage unit 22P Control program 23 Reading unit 24 Communication unit 3 Subject 4 Display terminal 41 Control unit 42 Communication unit 43 Display unit 5 Management terminal 51 Control unit 52 Communication unit 53 Display unit 54 Input unit 6 Medical professional d1 Screen d11 Numerical field d12 Graph field d2 Screen

Claims

1. A program that causes a computer to perform the following processes: acquire pulse waves and acceleration as time-series data of a predetermined time width; identify multiple pulse wave intervals in time series within the predetermined time width based on the acquired time-series data of pulse waves; identify multiple acceleration differences, which are the differences between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified multiple pulse wave intervals, based on the acquired time-series data of acceleration; extract target multiple pulse wave intervals from the identified multiple pulse wave intervals based on the identified multiple acceleration differences; and determine irregular pulse waves within the predetermined time width based on the extracted target multiple pulse wave intervals.

2. The program according to claim 1, which determines the irregular pulse wave based on the multiple target pulse wave intervals when the sum of the multiple target pulse wave intervals is equal to or greater than a predetermined threshold.

3. The program according to claim 1, which identifies the number of irregular intervals that satisfy predetermined conditions from a plurality of target pulse wave intervals.

4. The program according to claim 3, which determines an irregular pulse wave to be present when the proportion of the number of identified irregular intervals is equal to or greater than a predetermined threshold.

5. The program according to claim 1, which determines intervals that exclude a first pulse wave interval in which the identified acceleration difference is greater than a threshold, a second pulse wave interval that is chronologically immediately preceding the first pulse wave interval, and a third pulse wave interval that is chronologically immediately following the first pulse wave interval.

6. The program according to claim 1, which performs multiple judgments within a specified time and determines a pulse abnormality according to the proportion of irregular pulse waves determined in those multiple judgments.

7. The program according to claim 6, which outputs a determination result that determines an irregular pulse wave or a pulse abnormality.

8. An information processing method that acquires pulse waves and acceleration as time-series data of a predetermined time width; identifies multiple pulse wave intervals in a time series within the predetermined time width based on the acquired time-series data of pulse waves; identifies multiple acceleration differences, which are the differences between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified multiple pulse wave intervals, in association with each of the multiple pulse wave intervals based on the acquired time-series data of acceleration; extracts target multiple pulse wave intervals from the identified multiple pulse wave intervals based on the identified multiple acceleration differences; and determines irregular pulse waves within the predetermined time width based on the extracted target multiple pulse wave intervals.

9. A determination system comprising a sensor and a control unit, wherein the control unit acquires pulse waves and acceleration as time-series data of a predetermined time width using the sensor, identifies multiple pulse wave intervals in time series within the predetermined time width based on the acquired time-series data of pulse waves, identifies multiple acceleration differences, which are the difference between the maximum and minimum acceleration values ​​within the time corresponding to each of the identified multiple pulse wave intervals, in association with each of the multiple pulse wave intervals, extracts target multiple pulse wave intervals from the identified multiple pulse wave intervals based on the identified multiple acceleration differences, and determines irregular pulse waves within the predetermined time width based on the extracted target multiple pulse wave intervals.

Images