Device and method for detecting stroke in a patient

Through multiple wearable sensors, measuring body movement data, determining movement asymmetry and generating stroke detection signals, solving the false alarm problem in the existing system, improving the reliability and accuracy of stroke detection, especially when the patient is awake Effectively detect stroke.

CN113226175BActive Publication Date: 2024-11-05UMAN SENSE AB
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201980084985.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-11-12
Filing Date
2019-12-19
Publication Date
2024-11-05
Estimated Expiration
2039-12-19

AI Technical Summary

Technical Problem

Existing stroke detection systems are prone to false alarms, and it is difficult to generate reliable stroke detection signals without triggering false alarms, especially when a patient suffers a stroke while he is awake.

Method used

A plurality of wearable sensors are used to measure motion data on the symmetry plane of the body, and the asymmetry of the motion is determined by the data processing device, and a stroke detection signal is generated based on the asymmetry. When the asymmetry of the motion exceeds a predetermined threshold, a stroke detection signal is generated and an emergency service request can be automatically reported.

Benefits of technology

It reduces the occurrence of false alarms and improves the reliability and accuracy of stroke detection, especially when the patient is awake, and avoids unnecessary interference.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113226175B_ABST
    Figure CN113226175B_ABST
Patent Text Reader

Abstract

A stroke detection device, comprising: a data processing device, the data processing device comprising a processor; and at least one wearable sensor, the at least one wearable sensor being configured to generate motion data of at least a portion of a user's body. The data processing device is configured to process first motion data for a first motion and second motion data for a second motion received from the at least one wearable sensor; wherein the data processing device is configured to determine an asymmetry of the user's motion based on the first motion data and the second motion data, and generate a stroke detection signal according to the determined asymmetry.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to apparatus and methods for detecting a stroke in a patient. Background Art

[0002] A stroke is a medical condition in which poor blood flow to the brain causes cell death. There are two main causes of stroke. An ischemic stroke is usually caused by a blockage in an artery that supplies blood to the brain, resulting in insufficient blood flow to multiple parts of the brain. Blood normally carries oxygen and nutrients to the brain. Once oxygen and nutrients are cut off by the blockage, brain cells cannot make enough energy and eventually stop working. If the blockage is not cleared, brain cells eventually die. A hemorrhagic stroke is caused by bleeding in the brain. The bleeding is usually caused by damaged blood vessels leaking blood. A hemorrhagic stroke can also be caused by a ruptured cerebral aneurysm. In both cases, blood spreads into the surrounding brain tissue to cause increased pressure, which restricts the functioning of brain cells and eventually damages brain tissue.

[0003] In both types of stroke, because brain cells stop functioning normally, the result is a change in brain function. This change can be observed through physical symptoms, such as the inability to move or feel one side of the body, communication problems, and vision loss. These physical symptoms often appear more or less immediately after the stroke begins.

[0004] Historically, strokes have been difficult to treat. Although a patient's symptoms may be recognized and diagnosed as a stroke, available treatments are limited. When a stroke is identified as an ischemic stroke, the patient is given a clot-dissolving medication (such as tissue plasminogen activator) intravenously in the hope that the medication will reach the clot and dissolve it sufficiently to allow blood flow to resume through the affected artery. This treatment needs to be successfully administered within several hours of the onset of the stroke to ensure that damage to brain tissue is limited. Some studies suggest that the window of time to get the best effect from clot-dissolving medications is three hours from the first signs of a stroke.

[0005] If a stroke is not successfully treated, damage to brain tissue is inevitable and the only recourse is to provide care and rehabilitation training to the patient.

[0006] Recently, ischemic strokes have been successfully treated by an endovascular procedure known as "mechanical thrombectomy," in which a blood clot is removed by delivering a clot retrieval device to the site of the blocked blood vessel in the brain. The device secures the clot and pulls the clot out of the vessel when the device is removed. Similarly, hemorrhagic strokes can also be treated via an endovascular procedure by delivering a metal clip to the damaged blood vessel or ruptured aneurysm. The clip is secured to restrict blood flow and further prevent blood from seeping into surrounding tissue. As with clot-dissolving medications, significant damage reduction can be achieved if the procedure is performed within a few hours of the first signs of a stroke.

[0007] Therefore, as treatment options for ischemic stroke improve, the importance of identifying and characterizing stroke symptoms has increased. For patients at increased risk for stroke, a method is needed to provide continuous monitoring to rapidly diagnose and report stroke to a healthcare provider.

[0008] Known techniques utilize sensors worn on the patient's body to detect stroke in patients at an early stage. Villar.JR.'s "A Hybrid Intelligent Identification System for Early Detection of Stroke" describes the use of a wearable device that generates an alert and automatically connects to an electronic health service when a stroke is detected. The above method utilizes two wearable devices to monitor motion data and utilizes a genetic fuzzy finite state machine and time series (TS) analysis to determine stroke.

[0009] US patent application 2018153477 discloses a device for monitoring a stroke patient via a plurality of sensors for determining "physiological signals". Physiological signals may include heart rate signals, atrial rate signals, heart rate variability signals, blood pressure signals, blood pressure variability signals, heart sound signals, etc.

[0010] U.S. Patent 7,981,058 discloses an apparatus for monitoring a patient using a low-cost dual-axis motion sensor. A first sensor captures objective acceleration data, and a second dual-axis sensor captures subjective acceleration data at least relative to the first accelerometer. The acceleration data is then used to determine nonlinear parameters and generate at least two levels of motor function information.

[0011] US application US2017281054 discloses a device for monitoring a stroke patient via a plurality of motion sensors positioned at one or more anatomical locations on the patient's body and configured to detect a plurality of motion parameters corresponding to the motion of a portion of the patient's body. The motion of the portion of the patient's body is then determined based on a plurality of predetermined motion features.

[0012] US application US2015157252 discloses a device for monitoring a patient via multiple sensors. A technique for switching between sensors to determine which sensor provides the best indication of the patient's physiological signal state is described.

[0013] US application US20160213318 discloses a system and method for detecting stroke in a sleeping individual. The system includes a sensor worn on the hand to detect the absence of electrical or muscle activity in the hand.

[0014] WO2018110925 is an international application that discloses a device having sensors on the left and right hands to measure left and right side movements to detect stroke during deep sleep.

[0015] However, problems associated with the above-described systems include problems with generating a reliable signal indicating that a patient has had a stroke without triggering too many false positives. What is needed is a system that can generate a stroke detection signal with minimal false positives, and in the event that false positives do occur, the system can handle them gracefully without causing too much inconvenience to the user. Furthermore, a stroke condition may occur when the patient is awake rather than asleep. Summary of the invention

[0016] Examples of the present invention are directed to solving the above-mentioned problems.

[0017] According to aspects of the present invention, there is a stroke detection device, which includes: a data processing device, which includes a processor; at least one wearable sensor, and the at least one wearable sensor is configured to generate motion data of at least a part of a user's body; the data processing device is configured to process first motion data for a first motion and second motion data for a second motion received from the at least one wearable sensor; wherein the data processing device is configured to determine the asymmetry of the user's motion based on the first motion data and the second motion data, and generate a stroke detection signal according to the determined asymmetry.

[0018] Optionally, the data processing device is configured to determine an asymmetry of the user's movement based on the user performing at least one predetermined body gesture, based on the first movement data and the second movement data.

[0019] Optionally, the data processing means is configured to prompt the user to perform at least one predetermined body gesture.

[0020] Optionally, the data processing device generates a stroke detection signal when the data processing device determines that the asymmetry of the user's movement exceeds a predetermined threshold.

[0021] Optionally, the data processing device is configured to determine the predetermined threshold based on the user's historical movement data of the user's body.

[0022] Optionally, the predetermined threshold is based on one or more presets related to user characteristics.

[0023] Optionally, an automatic emergency service request is generated based on the stroke reporting signal.

[0024] Optionally, the at least one wearable sensor is a wearable sensor on an arm and / or leg.

[0025] Optionally, the first wearable sensor is worn on one of the user's wrists and the second wearable sensor is worn on the other of the user's wrists.

[0026] Optionally, at least one wearable sensor includes a first sensor configured to measure movement on a first side of a plane of symmetry of the user's body and a second wearable sensor configured to measure movement on a second side of the plane of symmetry of the user's body.

[0027] Optionally, the plane of symmetry of the user's body is one or more of an anterior-posterior plane, a frontal plane and / or a transverse plane.

[0028] Optionally, at least one wearable sensor is configured to measure the first motion data, and the second motion data is measured simultaneously.

[0029] Optionally, the at least one wearable sensor is configured to measure the first motion data and the second motion data at different times.

[0030] Optionally, the at least one wearable sensor is configured to transmit the generated motion data to a data processing device.

[0031] Optionally, when the data processing device determines the asymmetry of the user's movement based on the first movement data and the second movement data, the data processing device is configured to prompt the user to perform an additional predetermined body gesture.

[0032] According to aspects of the present invention, there is a method for generating a stroke detection signal, the method comprising: generating motion data of at least a portion of a user's body using at least one wearable sensor; processing first motion data for a first motion and second motion data for a second motion received from the at least one wearable sensor; determining an asymmetry of the user's motion based on the first motion data and the second motion data; and generating a stroke detection signal based on the determined asymmetry.

[0033] Various other aspects and further examples are also described in the following detailed description and appended claims with reference to the accompanying drawings, in which: BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a schematic diagram showing a patient wearing a multi-sensor stroke detection device;

[0035] Figure 2 shows a perspective view of a stroke detection device according to an example of the present application;

[0036] Figure 3 is a schematic illustration of a stroke detection device according to an example of the present application;

[0037] Figure 4a and Figure 4b is a process flow diagram showing execution flows of a wearable sensor and a control device, respectively;

[0038] Figure 5a and Figure 5b is a sequence diagram showing a data transmission sequence between a first wearable sensor device and a second wearable sensor device and a control device;

[0039] Figure 6 is a process flow diagram showing the execution flow of the control device 300;

[0040] Figure 7 is an alternative process flow diagram showing the execution flow of the control device 300;

[0041] Figure 8 A schematic view of a patient's body is shown;

[0042] Figure 9a to Figure 9h shows a series of postures performed by a patient according to an example of the present application;

[0043] Figures 10a to 10e shows a series of postures performed by a patient according to an example of the present application;

[0044] Figures 11a to 11e shows a series of postures performed by a patient according to an example of the present application;

[0045] Figures 12a to 12i shows a series of postures performed by a patient according to an example of the present application;

[0046] Figures 13a to 13c shows a series of postures performed by a patient according to an example of the present application;

[0047] Figures 14a to 14f shows a series of postures performed by a patient according to an example of the present application; and

[0048] Figure 15a to Figure 15b A series of gestures performed by a patient according to an example of the present application are shown. DETAILED DESCRIPTION

[0049] Figure 1 1 is a schematic diagram showing a user 100 equipped with a stroke detection device 102, which includes multiple wearable sensors 200a, 200b. In some examples, the user 100 is a patient 100. In some examples, the patient 100 may be at a particular risk of a transient ischemic attack (TIA) or other types of stroke, such as ischemic stroke, hemorrhagic stroke, aneurysm, arteriovenous malformations (AVM), cryptogenic stroke and / or brainstem stroke. In the following, the term "stroke" will be used. In other examples, the user is not a patient, but uses the stroke detection device 102 as a preventive measure. The terms "user" and "patient" can be used interchangeably, however, for clarity, the term "patient" will be used in the following.

[0050] exist Figure 1 , wearable sensors 200a, 200b are attached to the right wrist 104a and the left wrist 104b of the patient 100, respectively. Reference numeral 200 generally refers to a wearable sensor, but for clarity, reference numerals 200a, 200b refer to the wearable sensors 200a, 200b on the right wrist 104a and the left wrist 104b of the patient 100.

[0051] In other examples, the wearable sensors can be worn on the right ankle 106b and the left ankle 106a, as an alternative to or in conjunction with the wrists. Other locations where the wearable sensors can be worn include footwear, headwear, and clothing attached to, for example, pants and upper body clothing. In other examples, one or more sensors 200a, 200b can be mounted on any suitable portion of the patient's body 110.

[0052] Figure 2 Shows Figure 1 A perspective view of an example of a wearable sensor 200 is shown. In one example, the wearable sensor 200 includes a band 202 configured to secure the wearable sensor 200 to the patient 100 and a sensor body 204 housing a processing board 206. The processing board 206 may include a power source 208, a data processing device 210, and a sensor assembly 212.

[0053] The sensor assembly 212 may include any suitable sensor component or multiple sensor components that are configured to measure the inclination, position, orientation and / or acceleration of the portion of the body 110 of the patient 100 to which the wearable sensor 200 is attached. The sensor assembly 212 may include a piezoelectric component, a piezoresistive component and / or a capacitive component to convert mechanical motion into an electrical signal. In other examples, any suitable sensor is used that is configured to detect the movement of one or more parts of the patient's body. A piezoelectric ceramic (e.g., lead zirconate titanate) sensor or a single crystal (e.g., quartz, tourmaline) sensor may be used. In some examples, a capacitive accelerometer is used because it has superior performance in the low frequency range.

[0054] The data processing device 210 may be implemented by dedicated software (or firmware) running on one or more general or dedicated computing devices (e.g., one or more hardware processors). Each "element" or "device" of such a computing device refers to the conceptual equivalent of a method step; there is not always a one-to-one correspondence between an element / device and a specific hardware or software program. A piece of hardware sometimes includes different devices / elements. For example, a processing unit acts as one element / device when executing one instruction, but acts as another element / device when executing another instruction. In addition, an element / device may be implemented by one instruction in some cases, but may be implemented by multiple instructions in some other cases. Such a software-controlled computing device may include one or more processing units, such as a CPU ("central processing unit"), a DSP ("digital signal processor"), an ASIC ("application-specific integrated circuit"), discrete analog and / or digital components, or some other programmable logic devices such as an FPGA ("field programmable gate array"). The data processing device 210 may also include a system memory and a system bus that connects various system components including the system memory to the processing unit. The system bus may be any of a variety of types of bus structures, including a memory bus or a memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The system memory may include computer storage media in the form of volatile and / or nonvolatile memory, such as read only memory (ROM), random access memory (RAM), and flash memory. The application-specific software may be stored in the system memory, or on other removable / non-removable volatile / non-volatile computer storage media included in or accessible to the computing device, such as magnetic media, optical media, flash memory cards, digital tapes, solid-state RAM, solid-state ROM, etc. The application-specific software may be provided to the data processing device 210 on any suitable computer-readable medium, including recording media and read-only memory.

[0055] The data processing device 210 includes one or more communication interfaces and one or more data acquisition devices, the communication interface is, for example, a serial interface, a USB interface, a wireless network interface, etc., and the data acquisition device is, for example, an analog to digital (A / D) converter. In one example, the data processing device 210 may include a transmitter component configured to transmit sensor data received from the sensor component 212 and processed by the data processing device 210 and / or the A / D converter (not shown) via one or more communication interfaces. In one example, via or WiFi transceiver provides a communication interface, and the processed sensor data is sent to the control device 300 (hereinafter referred to as Figure 3 Alternatively, the processed sensor data may be sent to one or more remote devices via GSM, LTE or any other similar licensed or unlicensed mobile communication interface.

[0056] The power source 208 may include a battery, a kinetic energy source, or other power source suitable for the wearable device. The power source 208 is arranged to provide energy for powering the data processing device 210 and the sensor assembly 212 of the processing board 206.

[0057] The wearable sensor 200 may further include a fastening component 214 configured to be fixed together with a corresponding component 216 to enable the wearable sensor 200 to be fixed to a limb of the patient 100 .

[0058] In one example, the fastening component 214 includes a sensor (not shown) configured to determine whether the band 202 of the wearable sensor 200 is in an “open” configuration or in a “secured” configuration. Figure 2 An example of an “open” configuration of the strap 202 is shown in FIG. 2 , wherein the wearable sensor 200 is not secured to any object. Figure 1 An example of a “closed” configuration is shown in FIG, wherein the wearable sensor 200 is secured to the patient 100. Similarly, Figure 3 200 , wherein the fastening component 214 has been fastened to the corresponding component 216 to arrange the band of the wearable sensor 200 into a fixed loop. In one example, the sensor of the fastening component 214 is electrically connected to the processing board 206 so that the data processing device 210 can determine the configuration of the band 202 of the wearable sensor 200. Therefore, the data processing device 210 can determine whether the patient 100 is wearing the wearable sensor 200, and the data processing device 210 can generate the "wearing" or "not wearing" state information of the wearable sensor 200. When determining information related to the patient 100, the data processing device 210 can use the "wearing" or "not wearing" state information of the wearable sensor 200. For example, if the data processing device 210 determines that the patient 100 is not wearing the wearable sensor 200 based on the "not wearing" state information, the data processing device 210 can determine that any alarm related to the patient 100 may be a false alarm.

[0059] Figure 3 An exemplary wireless network 302 is shown according to an example. Figure 3 , two wearable sensors are shown as 200a and 200b (previously referred to as Figure 1and Figure 2 The wearable sensor 200a, 200b is worn by a patient 100 (not shown) and the corresponding band 202 of each wearable sensor is in a "closed" configuration. Each wearable sensor 200a, 200b collects sensor data from the patient, processes the data, and transmits the data to the control device 300 via the wireless network interface 304.

[0060] In some examples, the wearable sensors 200a, 200b collect sensor data from the patient 100 and transmit the data to the control device 300 via the wireless network interface 304 without processing the sensor data. Figure 5b In other examples, one of the wearable sensors 200a communicates wirelessly with another wearable sensor 200b. For example, the wearable sensors 200a and 200b may communicate wirelessly with each other. or low power consumption One of the wearable sensors 200a communicates wirelessly with the control device 300 via the wireless network interface 304. The other wearable sensor 200b does not communicate wirelessly with the control device 300.

[0061] In some examples, one of the wearable sensors 200a processes sensor data collected from some or all of the wearable sensors 200a, 200b. In this way, one of the wearable sensors 200a is the master wearable sensor 200a, and another of the wearable sensors 200b is the slave wearable sensor 200b. This will refer to Figure 5a Further detailed discussion.

[0062] Although the illustrated example shows only two wearable sensors 200a, 200b, in alternative examples, the patient 100 may wear additional wearable sensors. For example, the patient 100 may wear a wearable sensor 200a, 200b on each limb. This may be desirable for a patient 100 at particular risk and requiring increased sensor data collection.

[0063] In some examples, multiple wearable sensors 200a, 200b can establish a personal area network (PAN) or a body area network (BAN) for the wearable sensors 200a, 200b to communicate with each other. In some examples, multiple wearable sensors 200a, 200b can establish a mesh network between each other. This will refer to Figure 5aDescribed in further detail.

[0064] In a less preferred example, the wearable sensors 200a, 200b may be connected to the control device 300 via a wired connection. However, the wired connection between the wearable sensors 200a, 200b and the control device 300 may interfere with the body movements of the patient 100.

[0065] As described above, the communication interface between the wearable sensors 200a, 200b and the control device 300 is via transceiver, Wi-Fi transceiver, GSM transceiver, LTE transceiver or any other similar licensed or unlicensed mobile communication interface.

[0066] The following will refer to Figure 4a The process is described in more detail. The control device 300 can be any mobile or remotely-controlled or any other suitable control device 300. In some examples, the control device 300 is a mobile phone device, such as an Apple TM , Apple mobile phone TM , Apple tablet TM , Apple Watch TM , Android TM Devices, wearable operating systems TM The control device 300 receives data from the wearable sensors 200a, 200b, processes the received data, determines the patient's condition, and performs reporting processing when appropriate. Figure 4b Describe the process in more detail.

[0067] In some alternative examples, the control device 300 includes a wearable sensor 200a. In this way, the control device 300 can be a smartphone including one or more accelerometers (e.g., a 6-axis accelerometer). The smartphone is then mounted in a band and worn on the user's arm. According to the present application, the smartphone mounted on one arm will serve as the wearable sensor 200 and the control device 300. In addition, another wearable sensor 200b (e.g., a smart watch) can be worn on the other arm.

[0068] Figure 4a An example of a processing flow for the data processing device 210 is shown. Figure 4a The process flow shown in can be executed in a continuous loop or periodically. In the case of periodically executing the process, a power saving mode can be adopted between executions to minimize battery use.

[0069] In step 400, the sensor output is received by the data processing device 210 from the sensor assembly 212. In the case where the sensor data is generated by, for example, a piezoelectric component, the output from the piezoelectric component may require an optional pre-processing step 410 to ensure that the desired analog signal is generated. An example of a pre-processing step may be to reduce high frequency noise generated by the piezoelectric component from the analog signal. The pre-processing step 410 may occur at the sensor assembly 212 or at the data processing device 210.

[0070] After the pre-processing step 410, conversion of the signal from an analog signal to a digital signal may be performed in step 420. This analog-to-digital conversion may occur at the sensor assembly 212 or at the data processing device 210.

[0071] The digital signal is then processed in step 430 to reduce noise and time stamp the sensor readings.

[0072] Optionally, step 430 may include converting the acceleration vector generated by the accelerometer to the norm of the acceleration vector. That is, the acceleration vector is converted to a strictly positive length in a single direction. This provides a number of advantages, including a reduction in storage space for storing vector data and invariance to accelerometer orientation. Other filters are contemplated in combination with the above steps or independently to ensure that the filtered acceleration vector signal is invariant to gravity or orientation of the sensor assembly 212. In a preferred example, any of the aforementioned filtering steps is performed locally on the wearable sensors 200a, 200b, for example by the data processing device 210.

[0073] Optionally, step 430 may also include applying a high pass filter in combination with the above step or independently to remove the acceleration vector generated by gravity on the accelerometer. This can be achieved by removing slow or constant acceleration vectors from the difference of the acceleration vector. Advantageously, this enables the removal of noise caused by gravity.

[0074] Optionally, step 430 may also include filtering signals generated by body movements that are not a direct result of signals from the brain. In other words, the wearable sensors 200a, 200b do not detect indirect results of electrical signals reaching the muscles. Examples of movements that may be filtered include:

[0075] Movements that are only an indirect result of signals from the nervous system. For example, while walking, electrical signals may stimulate the arms to swing forward and backward to ensure balance. However, while walking, the arms swinging downward may be the result of gravity and body mechanics rather than the stimulation of any muscles. Therefore, these movements should be identified and removed from the acceleration vectors generated by one or more accelerometers, when possible.

[0076] Therefore, in some examples, the data processing device 210 filters the signal in the signal processing step 430 to exclude one or more movements that are not related to muscle movement due to the central nervous system. In some examples, the data processing device 210 filters the signal to exclude one or more of the following: passive limb mechanics, other biosignals (e.g., heart function signals), tremors or other involuntary muscle movements, environmental noise (e.g., bus or vehicle engines). In this way, the data processing device 210 filters the signal and can analyze the movement of the patient 100 when the patient 100 is awake and out of bed.

[0077] Then, optionally, in step 440 , the sensor data is formatted according to the defined data structure for transmission to the control device 300 . Finally, in step 450 , the wearable sensor 200a , 200b transmits the formatted sensor data to the control device 300 using the wireless network interface 304 .

[0078] In some examples, such as Figure 4a The steps shown are performed by the data processing device 210. In some other examples, such as Figure 4a The steps shown are partially or fully executed by a remote processing device, for example, partially or fully executed by the control device 300 .

[0079] Figure 4b An example of a process flow is shown for a control device 300. In some examples, the control device 300 is a mobile phone 300, but may be any suitable mobile device. Figure 4b The process flow shown in can be executed in a continuous loop or periodically. In the case of periodically executing the process, a power saving mode can be adopted between executions to minimize battery use.

[0080] In step 460, the control device 300 receives the formatted sensor data from the wearable sensors 200a, 200b. Then, optionally, in step 470, the received sensor data is merged with the existing data previously received from the wearable sensors 200a, 200b and any other wearable sensors that transmit sensor data to the control device 300. In one example, the data is stored in a local database that is stored on the control device 300. In one example, the system implements "chunking" of the formatted sensor data, which includes dividing the data into blocks, each block including a prefix indicating some parameters (e.g., timestamp, size, etc. for the recorded signal data). This enables each data block to resynchronize the control device 300 with the clock of the wearable sensor.

[0081] In step 475, data analysis is performed on the sensor data by control device 300. A patient condition, such as an ongoing stroke condition (e.g., transient ischemic attack), is then determined based on data analysis 475. This includes determining that the first movement of the patient's body and the second movement of the patient are asymmetric, as shown in step 480. The determination of the patient condition being present may be based on the sensor data exceeding a predetermined asymmetry threshold.

[0082] Refer to the following Figure 6 , Figure 7 , Figure 9a to Figure 9h , Figures 10a to 10e , Figures 11a to 11e , Figures 12a to 12i , Figures 13a to 13c , Figures 14a to 14f and Figure 15a to Figure 15b The processes of the data analysis step 475, the patient event determination step 480 and the report processing step 490 are described in more detail.

[0083] Once the reporting process 490 is complete and the patient has been unable to cancel the reporting of the patient's condition, the control device 300 proceeds with a transmission to the remote network, as shown in step 495. For example, in step 495, the control device 300 contacts the network point 308 via the network interface 306 to request emergency services for handling the patient's condition. In one example, the mobile device may communicate at least one of the patient's condition, the GPS location of the mobile device, the patient ID, the patient's medical history, a recent sensor data report, etc.

[0084] It should be noted that step 475 and subsequent steps may be performed as direct subsequent steps of step 460. Alternatively, step 475 and subsequent steps may be performed in an independent loop that is independently triggered by, for example, a periodic time interrupt.

[0085] In some examples, such as Figure 4b The steps shown are performed by the control device 300. In some examples, such as Figure 4b The steps shown are partially or completely performed by the data processing device 210. In this way, the data processing device 210 is able to perform Figure 4a and Figure 4b All steps in , and emergency services can be requested to deal with the patient's condition, as shown in step 495.

[0086] In this specification, multiple wearable sensors are used to collect data. Figure 5aA flow is shown for collecting data from more than one wearable sensor 200a, 200b at a control device 300. In steps 510 and 520, sensor data from a first wearable sensor 200a positioned on the left side of the body and a second wearable sensor 200b positioned on the right hand side of the body is collected.

[0087] In step 530, the sensor data from the first wearable sensor 200a is transmitted to the second wearable sensor 200b via the wireless network interface 304. In step 540, once the sensor data from the first wearable sensor 200a is received at the second wearable sensor 200b, the sensor data from the first wearable sensor 200a is combined with the sensor data from the second wearable sensor 200b (previously collected in step 520) and transmitted to the control device 300.

[0088] exist Figure 5a In the alternative example shown in Figure 5b An alternative flow is shown for collecting data from more than one wearable sensor at the control device 300. In steps 510 and 520, sensor data is collected from a first wearable sensor 200a positioned on the left side of the body and from a second wearable sensor 200b positioned on the right hand side of the body.

[0089] In step 550, the control device 300 instructs the first wearable sensor 200a to transmit the sensor data collected by the first wearable sensor 200a to the control device 300 via the wireless network interface 304. In step 560, the first wearable sensor 200a transmits the collected data to the control device 300 via the wireless network interface 304. In step 570, the control device 300 instructs the second wearable sensor 200b to transmit the sensor data collected by the second wearable sensor 200b to the control device 300 via the wireless network interface 304. In step 580, the second wearable sensor 200b transmits the collected data to the control device 300 via the wireless network interface 304.

[0090] Go to Figure 6 , describing in more detail the processes of the data analysis step 475, the patient event determination step 480 and the reporting processing step 490. Figure 6 It shows that Figure 4b Examples of data analysis step 475, patient event determination step 480, and escalation processing step 490 are shown.

[0091] One of the symptoms of a stroke patient is sudden numbness or weakness in the face, arm or leg, especially on one side of the body. This means that the patient is susceptible to asymmetric body movements during a stroke event.

[0092] Now refer to Figure 8 References for discussing the body's axis of symmetry. Figure 8 A perspective view of a patient's body 110 is shown having a first axis 800. The first axis is also referred to as the vertical or longitudinal axis of the body 110. The body also has a second axis 802 and a third axis 804. The second axis 802 is also referred to as the transverse axis of the body 110. The third axis 804 is also referred to as the anterior-posterior axis of the body 110.

[0093] Figure 8 Also shown is a body 110 having a first plane 810, also referred to as an anterior-posterior plane 810, in which the first axis 800 and the third axis 804 lie. The body 110 includes a second plane 808, also referred to as a transverse plane 808, in which the second axis 802 and the third axis 804 lie. The body 110 also includes a third plane 806, also referred to as a frontal plane, in which the first axis 800 and the second axis 802 lie.

[0094] In this manner, symmetry of body motion involves similarity of the first motion and the second motion across one or more planes 806, 808, 810 of the body 110. Thus, asymmetry of body motion involves dissimilarity of the first motion and the second motion across one or more planes 806, 808, 810 of the body 110. In this manner, the planes 806, 808, 810 of the body 110 are also symmetry planes for motion of the body 110.

[0095] For clarity, only the first symmetry plane 810 will be described. Advantageously, the use of the first symmetry plane 810 for stroke detection purposes reflects a basic symmetry plane represented in the hemispheres of the user's brain. However, reference to the symmetry of the movement of the body 110 may be with respect to any one of the first symmetry plane 810, the second symmetry plane 808, and / or the third symmetry plane 806. The first symmetry plane 810 divides the body 110 into a left-hand side 812 and a right-hand side 814. One symptom of a stroke may be sudden numbness or weakness of the face, arm, or leg, particularly on one side of the body with respect to the anterior-posterior symmetry plane 810.

[0096] In an example, the patient 100 is prompted to perform one or more predetermined postures, such as Figure 6As shown in step 600. Once the system condition is met, the control device 300 can prompt the patient 100 to perform a predetermined posture. In one example, the system condition is that a threshold of the probability of the patient condition existing has been exceeded. Determining the probability of the patient condition existing is discussed in GB1820892.6, which is incorporated herein by reference in its entirety.

[0097] In other examples, the system condition is that the control device 300 can prompt the patient 100 based on a timer, an external request, or a request from the patient 100. For example, a remote physician can request the control device 300 to prompt the patient 100 to perform a predetermined posture. Alternatively, the patient 100 may not feel well and may wish to check whether they are suffering from a stroke.

[0098] Then, the control device 300 commands the patient 100 to perform one or more gestures. The patient 100 performs a first gesture as shown in step 602. Then, the patient 100 performs a second gesture as shown in step 604. In some examples, the first gesture and the second gesture are performed simultaneously. In this way, the first gesture can be made by a first part of the patient's body 110, and the second gesture can be made by a second part of the patient's body 110. For example, the patient's right wrist 104a can make a first gesture, and the patient's left wrist 104b can make a second gesture.

[0099] exist Figures 14a to 14e One such example of a first motion and a second motion performed at different times is shown in FIG, whereby the patient is moving his leg. Figures 14a to 14f A series of leg postures performed by a patient 100 according to an example of the present application are shown. Figures 14a to 14e In the embodiment, the first leg 1400 is moved, and then the same movement is repeated with the other leg 1402. The movement of the legs 1400 can be performed backward and forward at the hip joint, such as Fig.14a , Fig.14b , Fig.14c Additionally or alternatively, the leg movement may be as shown. Fig.14e The knee joint is shown, or Fig.14f Performed at the ankle joint as shown.

[0100] In some examples, the control device 300 displays on the screen the first and second postures for the patient 100 to perform in steps 602, 604. The control device 300 displays an animation of the predetermined posture so that the patient 100 can follow and repeat the same movement. Alternatively, the control device 300 prompts the patient 100 to perform symmetrical movements with two arms or two legs, and lets the patient 100 decide which symmetrical movements the two arms or two legs should perform.

[0101] Alternatively, in another example, the control device 300 does not prompt the patient 100 to perform the first posture and the second posture. In this case, the patient 100 performs the first posture and the second posture without prompting from the control device 300. For example, the patient 100 may have been instructed by a physician to periodically perform the first posture and the second posture, and then the control device 300 analyzes the motion data in step 475, as previously discussed.

[0102] In one example, the first wearable sensor 200a is mounted on the patient's right wrist 104a and the second wearable sensor 200b is mounted on the patient's left wrist 104b. This means that the first posture and the second posture are made on opposite sides of the symmetry plane (e.g., the front-to-back plane) 810 of the patient's body 110.

[0103] The first wearable sensor 200a and the second wearable sensor 200b measure a motion made by a first portion of the patient's body 110 and a motion made by a second portion of the patient's body 110 while performing the gesture. The first wearable sensor 200a and the second wearable sensor 200b measure one or more of acceleration, velocity, timing, distance, range of motion of the right wrist 104a and the left wrist 104b relative to the symmetry plane 810. The first wearable sensor 200a and the second wearable sensor 200b may also measure whether the first motion and the second motion are jerky or smooth in nature.

[0104] In this manner, in step 475, the control device 300 analyzes the motion data from the first wearable sensor 200a and the second wearable sensor 200b, and determines whether there is a significant difference between the motions of the first posture and the second posture.

[0105] For example, the control device 300 may determine that the rate, speed, or acceleration of the first posture and the second posture may be different. For example, the control device 300 may determine that the range of motion of the first posture and the second posture may be different. For example, the control device 300 may determine that the direction of motion of the first posture and the second posture may be different. For example, the control device 300 may determine that the range of rotation of the first posture and the second posture may be different. For example, the control device 300 may determine that the timing of the first posture and the second posture may be different.

[0106] Then, the control device 300 determines whether the first posture and the second posture are symmetrical, as shown in step 606 .

[0107] In some examples, the first and second gestures require the patient 100 to move their right wrist 104a and left wrist 104b together to perform a simple clap. Additionally or alternatively, various other gestures may be performed. Figure 9a to Figure 9h, Figures 10a to 10e , Figures 11a to 11e , Figures 12a to 12i , Figures 13a to 13c , Figures 14a to 14f and Figure 15a to Figure 15b Other possible postures for patient 100 to perform during steps 602, 604, and / or 612 are shown and are discussed in further detail below.

[0108] The control device 300 determines a difference in motion data for the first posture and the second posture. In some examples, when the difference is above a predetermined threshold, the control device 300 determines that the first posture and the second posture are asymmetric. In some examples, when the difference in motion data between the first posture and the second posture is greater than a difference of 5%, 10%, 20%, 30%, 40%, or 50%, the control device 300 determines that there is asymmetric motion. For example, the control device 300 determines that the patient's right wrist 104a moves 10% faster and has a 10% greater range of motion than the patient's left wrist 104b. In some other examples, the control device 300 determines an activity measure and / or energy expenditure associated with the motion data of the first posture and the second posture. Therefore, when the difference in activity measure and / or energy expenditure is above a predetermined threshold, the control device 300 determines that the first posture and the second posture are asymmetric. In some examples, control device 300 determines that asymmetric movement exists when the difference in activity measures and / or energy expenditure associated with motion data between the first posture and the second posture is greater than a 5%, 10%, 20%, 30%, 40%, or 50% difference.

[0109] In some examples, the threshold for the difference in determining asymmetric movement of the patient's body 110 can be dynamic. In some examples, the threshold for the difference can be modified based on the patient's characteristics (e.g., health, age, gender, or any other suitable parameter that may affect the movement of the patient's body 110).

[0110] In some examples, the control device 300 is configured to determine the predetermined threshold based on the patient's historical motion data of the patient's body 110. This means that the control device 300 can determine whether the first posture and the second posture are significantly asymmetric relative to the patient's historical motion data. For example, the patient 100 may have limited motion in a part of the body due to an old injury that may cause the patient 100 to have asymmetric motion. In this way, the control device 300 can ignore asymmetric behavior due to non-stroke conditions.

[0111] In some examples, the control device 300 is configured to determine the predetermined threshold based on one or more presets related to the characteristics of the patient 100. For example, the motion associated with a young patient or an elderly patient can now be described. In addition, the preset is also related to other characteristics of the patient 100 (e.g., inactivity characteristics, activity characteristics, etc.).

[0112] When the control device 300 determines that the first posture and the second posture are not symmetrical, as shown in step 606, the control device 300 can perform the reporting process step 490. In some examples, the control device 300 can report and contact medical services, as shown in step 608.

[0113] If the control device 300 determines that the first posture and the second posture are symmetrical, the control device 300 may cancel the alarm, as shown in step 610. After the alarm is canceled, the control device 300 continues to receive and analyze data received from the wearable sensors 200a, 200b, as shown in reference to Figure 4a , Figure 4b discussed.

[0114] Optionally, steps 602, 604 of the patient 100 performing the first and second postures are performed simultaneously. For example, if the patient 100 is prompted to clap their hands together, the first and second postures of the right wrist 104a and the left wrist 104b moving toward each other will be measured by the wearable sensors 200a, 200b simultaneously.

[0115] Additionally or alternatively, steps 602, 604 may be performed at different times. For example, the first posture and the second posture may be performed by the patient 100 at different times. For example, the patient 100 may perform the first posture using the wearable sensor 200a mounted on the right wrist 104a, and then subsequently perform the second posture using the wearable sensor 200b mounted on the left wrist 104b. Alternatively, the determination of the patient event in step 480 may be performed using a single wearable sensor 200a, whereby the patient swaps the wearable sensor 200a from the right wrist 104a to the left wrist 104a after performing the first posture but before performing the second posture.

[0116] Optionally, upon determining that there is asymmetric movement between the first posture and the second posture 606, the control device 300 may prompt the patient 100 to perform additional movements, as shown in step 612. The control device 300 may prompt the patient 100 to perform similar or more complex predetermined postures. The control device 300 may use additional postures to determine the presence of asymmetric body movement for borderline cases. Alternatively, the patient 100 or the remote physician may request additional movements to be performed by the patient 100 as a double check.

[0117] The control device 300 then determines in step 614 whether the additional gesture performed in step 612 is asymmetrical. Determination step 614 is similar to step 606. If the control device 300 determines that the additional gesture is asymmetrical, the control device 300 reports to medical services in step 608, as before. Similarly, if the control device 300 determines that the additional gesture is in fact symmetrical, the control device cancels the alarm in step 610, as previously described.

[0118] Optionally, in one example, step 612 or step 606 may additionally include further testing of patient 100 to determine whether medical services should be alerted. In some examples, further testing may need to be performed before the patient performs the gesture in step 606 or step 612. Alternatively, further testing may need to be performed after the patient performs the gesture in step 606 or step 612.

[0119] For example, the control device 300 may display a countdown alarm 700 presented to the patient 100 on the display of the control device 300. The countdown alarm 700 may include a simple countdown alarm showing a countdown in a short time, before which the control device 300 will move to step 608 to alert medical services. The patient 100 has the option to cancel the countdown at any time. If the patient 100 fails to respond to the countdown alarm, the control device 300 will move directly to step 608 to alert medical services. In the case where the patient 100 cancels the countdown by performing the required cancellation task (e.g., pressing a cancel button), the patient 100 is presented with an option to reset the reporting process. Alternatively, the patient 100 may be presented with an option to move directly to step 608 to alert medical services when the patient 100 feels that there is still a problem.

[0120] In an optional example, the patient 100 cannot cancel the countdown alarm until all user tests are successfully completed. In one example, a two-part countdown is used. Countdown 1 is a short countdown (e.g., less than 60 seconds) and can be canceled by the patient 100. Countdown 2 is a long countdown (e.g., greater than 60 seconds) that can only be canceled by successfully completing all patient 100 tests.

[0121] In another optional example, the patient 100 is additionally required to perform a simple cognitive test, such as performing simple mental arithmetic, as shown at 710. If the control device 300 determines that the patient 100 fails the further test 700, 710, the control device 300 may report and alert medical services at step 608.

[0122] Now refer to Figure 9a to Figure 9h , Figures 10a to 10e , Figures 11a to 11e , Figures 12a to 12i , Figures 13a to 13c , Figures 14a to 14f and Figure 15a to Figure 15b Other postures for determining asymmetry of a patient's movement are described.

[0123] Figure 9a to Figure 9h , Figures 10a to 10e , Figures 11a to 11e , Figures 12a to 12i , Figures 13a to 13c , Figures 14a to 14f and Figure 15a to Figure 15b A series of gestures performed by a patient 100 according to an example of the present application is shown.

[0124] Figures 9a to 9d The patient 100 is shown moving their right arm 900 from a downward pointing orientation to an upward pointing orientation above the head. Figure 9e to Figure 9h The patient is shown moving their left arm 902 from a downward pointing direction to an upward pointing direction above the head. Figures 9a to 9d The posture and Figure 9e to Figure 9h The posture in is mirrored. The posture is mirrored about the anterior-posterior symmetry plane 810. In this way, the stroke detection device 102 can determine whether there is asymmetry between the movements, as previously described with reference to Figure 4a , Figure 4b As stated. Figure 9a to Figure 9h The postures shown may be performed simultaneously or at different times. The patient 100 moves the arms 900 , 902 in a plane parallel to the frontal plane 806 .

[0125] Figures 10a to 10e A series of arm postures are shown whereby the patient 100 moves their arms 900, 902 from Fig.10a Move to the first position on their hips Fig.10e 900, 902 are in a position pointing upward above their head. Figures 10a to 10e The posture in is similar to Figure 9a to Figure 9h The posture shown, except that both arms 900, 902 move simultaneously. Figures 10a to 10e The posture shown can be used to determine asymmetry of the patient's movement about the anterior-posterior symmetry plane 810. The patient 100 moves the arms 900, 902 in a plane parallel to the frontal plane 806.

[0126] Figures 11a to 11e Again, a similar Figures 10a to 10e However, in Figures 11a to 11e In the embodiment, the patient's right arm 900 rests on the hips and the patient's left arm 902 is raised above their head. The patient then continues to raise the right arm 900 and lower the left arm 902 until Fig.11eThe patient 100 can then repeat the process to return to the Fig.11a in the original position. Figures 11a to 11e The posture in may be useful for the patient 100 to perform because it requires an element of cognitive ability to coordinate the arms 900, 902. The patient's inability to coordinate their arms 900, 902 may be another indication of a stroke condition.

[0127] Figures 12a to 12i Again, a similar Figures 10a to 10e However, the patient 100 swings both of their arms 900, 902 in a counter-clockwise direction until Fig.12c The left arm 902 is above the shoulder. The patient 100 then swings their two arms 900, 902 up and down in a clockwise direction until the right arm 900 is above the shoulder, as shown in FIG. Fig.12i As shown. Similarly, Figures 12a to 12i The posture in may be useful for patient 100 to perform because it requires an element of cognitive ability to coordinate arms 900 , 902 .

[0128] Figures 13a to 13c A series of arm postures for the patient 100 are shown. The patient 100 moves the arms 900, 902 in a plane parallel to the anterior-posterior plane 810. The patient 100 moves their arms through the transverse plane 808 and moves their arms from Fig.13a The first position shown above their heads is rotated downward to Fig.13c Shown in a second position through their sides.

[0129] Figures 14a to 14f is a series of leg positions and has been discussed above.

[0130] Fig.15a and Fig.15b Another series of arm postures is shown. The patient 100 moves their arms 900, 902 from a first position, in which the patient 100 extends their arms 900, 902 out from their sides at shoulder height, to a second position. Fig.15a As shown, in this second position, the patient 100 points their arms 900, 902 together in front of the patient. The patient 100 moves their arms 900, 902 in a plane parallel to the transverse plane 808.

[0131] In other examples, the control device 300 may prompt the patient 100 to make other movements. For example, the patient 100 may be prompted to move their hands in a circle in front of them in a plane parallel to the frontal plane 806, with each hand moving in the same or opposite directions. Additionally or alternatively, the patient 100 may be prompted to move their hands up and down in a linear motion in front of them in a plane parallel to the frontal plane 810, with each hand moving in the same or opposite directions.

[0132] In other examples, the patient 100 may be prompted to perform alternating movements, i.e., small, rapid movements, such as moving a finger to the nose, alternating hand clapping, or toe tapping movements.

[0133] In this way, the gestures are complex enough that the control device 300 can separate the gestures from involuntary movements such as tremors, twitches, and jerks that may be seen in an epileptic seizure. The gestures can be performed anywhere and at any time of the day. This means that even when traveling or away from home, the patient 100 can perform the gestures when prompted by the control device 300.

[0134] Advantageously, the control device 300 can determine the movement of the gestures using only the wearable sensors 200a, 200b. This means that no further equipment is required to determine the movement of the patient 100. In this way, gestures can be used to demonstrate symmetrical movement of one or more specific muscle groups or multiple muscle groups in a clear and simple manner. This means that these gestures are easy for the patient 100 to perform while being complex enough to determine asymmetrical movement indicative of a stroke condition.

[0135] In another example, two or more examples are combined. Features of one example can be combined with features of other examples.

[0136] Examples of the invention have been discussed with particular reference to the examples shown. However, it will be appreciated that variations and modifications may be made to the described examples within the scope of the invention.

Claims

1. A stroke detection device, comprising: A data processing device, the data processing device comprising a processor; at least two wearable sensors configured to generate motion data of at least a portion of a user's body; The data processing device is configured to process first motion data for a first motion and second motion data for a second motion received from the at least two wearable sensors; wherein the data processing device is configured to determine an asymmetry of the user's movement based on the first movement data and the second movement data, and to generate a stroke detection signal according to the determined asymmetry, wherein the data processing device is in communication with a control device (300), the control device being configured to prompt a user to perform a first predetermined body posture, wherein the data processing device is configured to determine the asymmetry of the user's movement based on the user performing the first predetermined body posture, based on the first movement data and the second movement data, Wherein, the control device is configured to prompt the user to perform a cognitive test when the data processing device determines the asymmetry of the user's movement based on the first movement data and the second movement data.

2. The stroke detection device according to claim 1, wherein: When the data processing device determines that the asymmetry of the user's movement exceeds a predetermined threshold, the data processing device generates a stroke detection signal.

3. The stroke detection device according to claim 2, wherein: The data processing device is configured to determine the predetermined threshold based on user historical movement data of the user's body.

4. The stroke detection device according to claim 2 or 3, wherein: The predetermined threshold is based on one or more presets related to user characteristics.

5. The stroke detection device according to any one of claims 1 to 3, wherein: Generates automatic emergency service request based on stroke escalation signal.

6. The stroke detection device according to any one of claims 1 to 3, wherein: The at least two wearable sensors are wearable sensors on arms and / or legs.

7. The stroke detection device according to claim 6, wherein: The first wearable sensor is worn on one of the user's wrists, and the second wearable sensor is worn on the other of the user's wrists.

8. The stroke detection device according to any one of claims 1 to 3, wherein: The at least two wearable sensors include a first wearable sensor configured to measure movement on a first side of a symmetry plane of the user's body and a second wearable sensor configured to measure movement on a second side of the symmetry plane of the user's body.

9. The stroke detection device according to claim 8, wherein: The plane of symmetry of the user's body is one or more of an anterior-posterior plane, a frontal plane and / or a transverse plane.

10. The stroke detection device according to any one of claims 1 to 3, wherein: The at least two wearable sensors are configured to measure the first motion data, and the second motion data is measured simultaneously.

11. The stroke detection device according to any one of claims 1 to 3, wherein: The at least two wearable sensors are configured to measure the first motion data and the second motion data at different times.

12. The stroke detection device according to any one of claims 1 to 3, wherein: The at least two wearable sensors are configured to transmit the generated motion data to the data processing device.

13. The stroke detection device according to any one of claims 1 to 3, wherein: When the data processing device determines the asymmetry of the user's movement based on the first movement data and the second movement data, the data processing device is configured to prompt the user to perform a second predetermined body posture, which is different from the first predetermined body posture.

14. The stroke detection device according to claim 13, wherein: The second predetermined body posture is more complex than the first predetermined body posture.

15. A method for generating a stroke detection signal, the method comprising: prompting the user to perform a first predetermined body posture, generating motion data of at least a portion of a user's body using at least two wearable sensors; processing first motion data for a first motion and second motion data for a second motion received from the at least two wearable sensors; determining an asymmetry of the user's movement based on the user performing the first predetermined body gesture, based on the first movement data and the second movement data; generating a stroke detection signal based on the determined asymmetry; as well as Upon determining an asymmetry of the user's movement based on the first movement data and the second movement data, the user is prompted to perform a cognitive test.