HEARING SYSTEM FOR MONITORING A HEALTH RELATED PARAMETER

Abstract

A binaural hearing system comprises a) left and right hearing devices, e.g. hearing aids, adapted for being worn at or in left and right ears, respectively, of a user, or for being fully or partially implanted in the head at the left and right ears, respectively, of the user, each of the left and right hearing devices comprising a1) a number N.sub.S of different sensors Si (i=1, . . . , N.sub.S), each sensor being configured to monitor a physiological function of the user and providing respective left and right sensor signals ST.sub.i,left, ST.sub.i,right (i=1, . . . , N.sub.S), indicative of the state of the physiological function in question; a2) electric circuitry to provide that information signals, including said sensor signals can be exchanged between the left and right hearing devices and/or forwarded to an auxiliary device, b) a comparison unit for comparing said left and right sensor signals, and providing respective comparison signals CSl.sub.i (i=1, . . . , N.sub.S) for each of said physiological functions; and c) an analysis unit for analyzing said comparison signals and providing a concluding stroke indicator CSI regarding a risk of stroke of the user depending on said comparison signal(s). Thereby an improved functionality of a hearing system may be provided allowing an early warning of a stroke of a wearer of the hearing system.

Claims

1. A binaural hearing system comprising left and right hearing devices, e.g. hearing aids, adapted for being worn at or in left and right ears, respectively, of a user, or for being fully or partially implanted in the head at the left and right ears, respectively, of the user, each of the left and right hearing devices comprising A number N.sub.S of different sensors S.sub.i (i=1, . . . , N.sub.S), each sensor being configured to monitor a physiological function of the user and providing respective left and right sensor signals ST.sub.i,left, ST.sub.i,right (i=1, . . . , N.sub.S), indicative of the state of the physiological function in question; Electric circuitry to provide that information signals, including said sensor signals ST.sub.i,left, ST.sub.i,right, or parts thereof or data originating therefrom, can be exchanged between the left and right hearing devices and/or forwarded to an auxiliary device; wherein the binaural hearing system further comprises A comparison unit for comparing said left and right sensor signals ST.sub.i,left, ST.sub.i,right (i=1, . . . , N.sub.S), or parts thereof, or data originating therefrom, and providing respective comparison signals CSI.sub.i (i=1, . . . , N.sub.S) for each of said physiological functions; and An analysis unit for analyzing said comparison signals CSI (i=1, . . . , N.sub.S) and providing a concluding stroke indicator CSI regarding a risk of stroke of the user depending on said comparison signal(s).

2. A binaural hearing system according to claim 1 wherein at least one of said number of sensors comprises an electrode for picking up electric signals of the body.

3. A binaural hearing system according to claim 1 wherein at least one of said sensors is configured to measure brain activity, e.g. to pick up signals from the user's brain, e.g. EEG-potentials.

4. A binaural hearing system according to claim 1 wherein at least one of said sensors is configured to measure ocular muscle activity, e.g. using electrooculography (EOG).

5. A binaural hearing system according to claim 1 wherein at least one of said number of sensors is configured to measure oxygen saturation of the user's blood, e.g. using pulse oxiometry.

6. A binaural hearing system according to claim 1 wherein at least one of said number of sensors is configured to monitor jaw activity or neck muscle activity.

7. A binaural hearing system according to claim 6 wherein the sensor configured to monitor temporomandibular joint activity or neck muscle activity comprises a radar sensor.

8. A binaural hearing system according to claim 1 wherein said number N.sub.S of different sensors S.sub.i (i=1, . . . , N.sub.S) comprises a first sensor comprising an electrode for picking up electric signals of the body, e.g. EEG signals and/or EOG signals, and at least one additional sensor.

9. A binaural hearing system according to claim 8 wherein said concluding stroke indicator CSI is based on a predefined conditional criterion regarding said comparison signals CSI.sub.i or sensor stroke indicators SSI.sub.i (i=1, . . . , N.sub.S) of said first sensor and said at least one additional sensor in such a way that said comparison signal or said sensor stroke indicator of the at least one additional sensor is only considered in case a first comparison signal CSI.sub.EEG or a first sensor stroke indicator SSI.sub.EEG is indicative of a stroke, wherein said sensor stroke indicator SSI.sub.i for a given sensor is determined based on the left and right sensor signals ST.sub.i,left, ST.sub.i,right for the sensor in question.

10. A binaural hearing system according to claim 1 wherein said predefined conditional criterion regarding said resulting comparison signals CSI.sub.i or sensor stroke indicators SSI.sub.i comprises a degree of asymmetry of the left and right sensor signals ST.sub.i,left, ST.sub.i,right (i=1, . . . , N.sub.S) as reflected in the corresponding comparison signals CSI.sub.i (i=1, . . . , N.sub.S).

11. A binaural hearing system according to claim 1 comprising a wireless interface allowing said concluding stroke indicator and/or an alarm to be forwarded to another device, e.g. via a network.

12. A binaural hearing system according to claim 1 wherein the left and right hearing devices consists of or comprises left and right hearing aids, headsets, earphones, or a combination thereof.

13. A binaural hearing system according to claim 1 wherein the left and right hearing devices form part of or are mechanically and/or electrically connected to glasses, a head band, a cap, or any other carrier adapted for being located on the head of the user.

14. A binaural hearing system according to claim 1 configured to provide that said comparison unit and/or said analysis unit is based on artificial intelligence, e.g. using neural networks or machine learning.

15. A method of detecting a risk of stroke of a user wearing a binaural hearing system comprising left and right hearing devices, e.g. hearing aids, adapted for being worn at or in left and right ears, respectively, of a user, or for being fully or partially implanted in the head at the left and right ears, respectively, of the user, the method comprising In each of the left and right hearing devices providing respective left and right sensor signals ST.sub.i,left, ST.sub.i,right (i=1, . . . , N.sub.S) indicative of a state of a physiological function; providing that information signals, including said sensor signals ST.sub.i,left, ST.sub.i,right, or parts thereof or data originating therefrom, can be exchanged between the left and right hearing devices and/or forwarded to an auxiliary device, wherein the method further comprises comparing said left and right sensor signals ST.sub.i,left, ST.sub.i,right (i=1, . . . , N.sub.S), or parts thereof, or data originating therefrom, and providing respective comparison signals CSI.sub.i (i=1, . . . , N.sub.S) for each of said physiological functions; and analyzing said comparison signals CSI.sub.i (i=1, . . . , N.sub.S) and providing a concluding stroke indicator CSI regarding a risk of stroke of the user depending on said comparison signal(s).

16. A data processing system comprising a processor and program code means for causing the processor to perform the steps of the method of claim 15.

17. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 15.

18. A non-transitory application, termed an APP, comprising executable instructions configured to be executed on an auxiliary device to implement a user interface for a binaural hearing system according to claim 1 wherein the APP is configured to run on cellular phone or on another portable device allowing communication with said binaural hearing system.

19. A non-transitory application according to claim 18 configured to allow an exchange of configuration data and recorded physiological measures between the auxiliary device and the left and right hearing devices.

20. A non-transitory application according to claim 18 configured to estimate a risk of stroke based on sensor data from the left and right hearing devices.

21. A non-transitory application according to claim 18 configured to allow a user to select appropriate sensors for contributing to the stroke related health monitoring provided by the hearing system.

22. A non-transitory application according to claim 18 configured to provide feedback to the user or a care assistant wearing the auxiliary device about the risk of feedback.

Description

BRIEF DESCRIPTION OF DRAWINGS

[0093] The aspects of the disclosure may be best understood from the following detailed description taken in conjunction with the accompanying figures. The figures are schematic and simplified for clarity, and they just show details to improve the understanding of the claims, while other details are left out. Throughout, the same reference numerals are used for identical or corresponding parts. The individual features of each aspect may each be combined with any or all features of the other aspects. These and other aspects, features and/or technical effect will be apparent from and elucidated with reference to the illustrations described hereinafter in which:

[0094] FIG. 1 shows a scheme for monitoring a risk of stroke of a user according to an embodiment of the present disclosure,

[0095] FIG. 2A shows a first embodiment of a hearing system comprising left and right hearing devices, each comprising a number of electrodes for picking up electric signals from a user's body, and

[0096] FIG. 2B a second embodiment of a hearing system comprising left and right hearing devices, each comprising a number of electrodes for picking up electric signals from a user's body and exchanging data with an auxiliary device,

[0097] FIG. 3 shows an embodiment of a hearing system according to the present disclosure comprising left and right hearing devices and a number of sensors mounted on a spectacle frame,

[0098] FIG. 4 shows an embodiment of a binaural hearing system comprising left and right hearing devices and an auxiliary device in communication with each other according to the present disclosure, and

[0099] FIG. 5 shows an embodiment of a binaural hearing system comprising left and right hearing devices, using an artificial intelligence engine to analyze sensor data, and an auxiliary device according to the present disclosure.

[0100] The figures are schematic and simplified for clarity, and they just show details which are essential to the understanding of the disclosure, while other details are left out. Throughout, the same reference signs are used for identical or corresponding parts.

[0101] Further scope of applicability of the present disclosure will become apparent from the detailed description given hereinafter. However, it should be understood that the detailed description and specific examples, while indicating preferred embodiments of the disclosure, are given by way of illustration only. Other embodiments may become apparent to those skilled in the art from the following detailed description.

DETAILED DESCRIPTION OF EMBODIMENTS

[0102] The detailed description set forth below in connection with the appended drawings is intended as a description of various configurations. The detailed description includes specific details for the purpose of providing a thorough understanding of various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. Several aspects of the apparatus and methods are described by various blocks, functional units, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as elements). Depending upon particular application, design constraints or other reasons, these elements may be implemented using electronic hardware, computer program, or any combination thereof.

[0103] The electronic hardware may include microprocessors, microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), gated logic, discrete hardware circuits, and other suitable hardware configured to perform the various functionality described throughout this disclosure. Computer program shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0104] The present application relates to the field of hearing devices, e.g. hearing aids.

[0105] Strokes result from poor blood flow to the brain that creates brain cell death. Strokes are either ischemic or haemorrhagic. Over 85% of strokes are ischemic. Ischemic strokes are caused by poor blood supply to the brain (often due to a blood clot), while haemorrhagic strokes result from the rupture of a blood vessel, creating bleeding.

[0106] Every year over 3 million people worldwide suffer a stroke. Many of the risk factors for a stroke are lifestyle related and include high blood pressure, tobacco smoking, obesity, high blood cholesterol, and diabetes. As the incidence of lifestyle related health problems continue to raise around the world, so does the incidence of strokes.

[0107] The location (also known as site of lesion) of a stroke varies. A stroke can occur in the brain cortex, in the cerebellum, in the brainstem, or in the area between the brain and the skull.

[0108] Symptoms include reduced muscle function, which can be seen with muscle weakness in the arm and face and slurred speech. Most often, the site of lesion is on one side of the head and therefore the symptoms affect only one side of the body (unilateral).

[0109] Early detection of stroke is essential to reduce the chances of death and of permanent disability.

[0110] The present disclosure proposes to use bilateral ear-level devices (e.g. hearing devices) to monitor physiological function(s) and to detect any unilateral changes in physiological function. A hearing system according to the present disclosure may comprise the following components (cf. e.g. FIG. 1): [0111] 1. An ear-level device: This is a hearing device, such as a hearing aid, e.g. an air conduction based hearing instrument, a cochlear implant type hearing instrument, or a bone-conducting hearing system, a hearable/personal sound amplifying product intended for people without hearing loss, or any other ear-level device (cf. e.g. FIG. 2A, 2B). The device could also include exogenous sensors, for example located on smart glasses (e.g. pupillometry, cf. e.g. FIG. 3) or headbands (e.g. electroencephalography with better precision), to take the physiological measures. [0112] 2. A physiological change monitor: We propose to monitor physiological functions with ear-level measures, with focus on the detection of any unilateral changes that would warn about a possible stroke (e.g. including EEG and/or EOG measurements monitoring brain and/or eye movement activity of the user, cf. e.g. FIG. 2A, 2B). A unique physiological measure may be used, or the system may combine several physiological measures for best accuracy (high sensitivity and specificity; few false positives and false negatives). [0113] 3. A data analyzer: The physiological measures are compared between the sides (difference right-left) for the identification of any unilateral changes. Artificial intelligence, big data, and deep neural networks allow for data analysis and for thresholds in differences allowed that are informed by normative data that is individualised for each user for best accuracy during a calibration period. Thereby initial threshold values can be conservative but adjusted over time based on the values collected for a specific user over the calibration period. In an embodiment, the hearing system is configured to provide that the calibration period occurs automatically when using the devices for the first timeand to allow for manual initiation later on, as needed. If unilateral physiological changes are identified, a risk of eminent stroke is estimated, and an alarm or an optional alert, feedback, and advice system may be triggered. In an embodiment, the hearing system is configured to differentiate an eminent risk of stroke from a general risk factor for stroke, e.g. due to a low level of physical activity or poor diet, etc.

[0114] The hearing system may further comprise the following component: [0115] 4. Alert, feedback, and advice system: An alert is e.g. sent to the emergency services (e.g. telephone 112 in Europe or 911 in North America), to the closest nurse ward for hospitalized patients, or to a family member. The alert can include a text message, alerting the recipient that the user is suffering a stroke without relying on the user having to give verbal commands whilst suffering the stroke. Alert settings are selected by the user. When the alert is sent, the device may be configured to provide feedback (e.g. help is on its way) and advice (e.g. Dos and Don'ts while waiting for an ambulance, etc.) to its user and care assistants. This functionality may e.g. be implemented in an auxiliary device, e.g. a remote control, e.g. implemented as an APP of a smartphone or similar device (cf. e.g. FIG. 4). In an embodiment, the hearing system is configured to alert directly a contact defined as In case of emergency in a mobile device.

[0116] FIG. 1 shows a scheme for monitoring a risk of stroke of a user according to an embodiment of the present disclosure. FIG. 1 illustrates basic steps of an embodiment of the present disclosure in the form of a method of estimating a risk of stroke of a user wearing a binaural hearing system comprising left and right hearing devices. The method comprises [0117] S1. Physiological measures are taken at the ear level. In an embodiment. physiological measures (STI.sub.left, STI.sub.right) are recorded (e.g. at regular time intervals or at predetermined points in time, or when predetermined events are occurring, such as abnormal physical activity) at the ear level on left and right sides (e.g. based on one or more of brain activity (EEG), blood oxygen concentration, ocular muscle activity, temporomandibular movement). [0118] S2. The physiological measures (STI.sub.left, STI.sub.right) are compared between the left and right sides (e.g. in that a comparison measure, CSI, between left and right physiological measures is determined). [0119] S3. If unilateral physiological changes are measured, a risk of stroke is detected. Is the comparison measure larger than or equal to a threshold value (i.e. is CSICSI.sub.TH?)? If NO, return to S1. If Yes, go to S4.

[0120] S4. An alarm is triggered (e.g. in that the user and/or a caretaker is informed about a risk of stroke, e.g. via the hearing devices and or via a remote control or display device (e.g. a smartphone), e.g. via a network, e.g. to a predefined receiver (e.g. a family member or caretaker or alarm unit), cf. also point 4) above (Alert, feedback, and advice system).

[0121] FIG. 2A shows a first embodiment of a hearing system comprising left and right hearing devices, each comprising a number of electrodes for picking up electric signals from a user's body. FIG. 2A shows a pair of behind the ear (BTE) hearing devices with EEG electrodes on the surface of an in-the-ear (ITE) part, e.g. an ear mould. The electrodes may form part of respective sensors of the left and right hearing devices for picking up signals from the user's brain (e.g. EEG potentials) and/or for monitoring eye movement (e.g. EOG potentials or eye muscle activity). In an embodiment, the sensors may comprise electric potential sensor(s) (EPS) with integrated circuits (EPIC) in the ear canal. in an embodiment, the electrodes are conventional (e.g. dry or wet) electrodes for establishing a direct electric contact between skin and electrode. The electrodes may e.g. be located on the surface of in-the-ear moulds (as illustrated in FIG. 2A), in domes for positioning an ITE-part in the ear canal, or integrated in a BTE-part.

[0122] FIG. 2B shows an embodiment of a hearing system comprising left and right hearing devices, each comprising a number of EEG and reference electrodes for picking up electric signals from a user's body and exchanging data with an auxiliary device. In the embodiment of FIG. 2B, the first and second (right and left) hearing devices (HD.sub.1, HD.sub.2) comprises BTE parts (BTE1, BTE2), respectively, adapted for being located at or behind an ear of a user (U). Further, the first and second hearing devices (HD.sub.1, HD.sub.2) each comprises EEG-electrodes (EEGe1, EEGe2), and a reference electrode (REFe1, REFe2), respectively, arranged on the outer surface of the ITE parts (ITE1, ITE.sub.2) adapted for being located fully or partially in an ear canal of the user (U). When the first and second hearing devices are operationally mounted on the user, the electrodes of the ear pieces are positioned to have electrical contact with the skin of the user to enable the sensing of body signals (e.g. brainwave signals). In the embodiment of FIG. 2B, three EEG-electrodes (EEGe1, EEGe2) are shown on each ITE-part, but more or less may be present in practice depending on the application. Further a reference electrode (REFe1, REFe2) is shown on each ITE part. Thereby the reference voltage (V.sub.REF2) picked up by the reference electrode (REFe2) of the second ITE part (ITE2) can be used as a reference voltage for the EEG potentials (V.sub.EEG1i, i=1, 2, 3) picked up by the (three) EEG electrodes (EEGe1) of the first ITE part (ITE1), and vice versa. In an embodiment, the first and second hearing devices provides a binaural hearing system. The reference voltages (V.sub.REF1, V.sub.REF2) may be transmitted from one part to the other (HD.sub.1<->HD.sub.2) via electric interface EI (cf. e.g. US20160081623A1, and optionally via an auxiliary device (AD), e.g. a remote control device, e.g. a smartphone). The auxiliary device (AD) may e.g. be configured to process body signals, e.g. EEG-signals, (cf. processing unit (PRO) and optionally performing other processing tasks related to the hearing system) and/or providing a user interface for the hearing system (cf. e.g. FIG. 4, 5). Each of the first and second hearing devices (HD.sub.1, HD.sub.2) and the auxiliary device (PRO) comprises antenna and transceiver circuitry (Rx/Tx) configured to establish a wireless link (WLCon) to each other. The two sets of EEG-signal voltage differences (V.sub.EEG1, V.sub.EEG2) can be used separately in each of the respective first and second hearing devices (HD.sub.1, HD.sub.2) (e.g. to control processing of an input audio signal) or combined in one of the hearing devices and/or in the auxiliary device (PRO, e.g. for display and/or further processing), e.g. to provide comparison signals CSI for one or more physiological functions, e.g. brain activity (e.g. (ear) EEG signals) and/or eye activity (e.g. (ear) EOG signals), as proposed in the present disclosure.

[0123] FIG. 3 shows an embodiment of a (binaural) hearing system according to the present disclosure comprising left and right hearing devices and a number of sensors mounted on a spectacle frame (e.g. hearing glasses). The hearing system (HS) comprises a number of sensors S.sub.1i, S.sub.2i (i=1, . . . , N.sub.S) associated with (e.g. forming part of or connected to) left and right hearing devices (HD.sub.1, HD.sub.2), respectively. The first, second and third sensors S.sub.11, S.sub.12, S.sub.13 and S.sub.21, S.sub.22, S.sub.23 are mounted on a spectacle frame of the glasses (GL). In the embodiment of FIG. 3, sensors S.sub.11, S.sub.12 and S.sub.21, S.sub.22 are mounted on the respective sidebars (SB.sub.1 and SB.sub.2), whereas sensors S.sub.13 and S.sub.23 are mounted on the cross bar (CB) having hinged connections to the right and left side bars (SB.sub.1 and SB.sub.2). Glasses or lenses (LE) of the spectacles are mounted on the cross bar (CB). The left and right hearing devices (HD.sub.1, HD.sub.2) comprises respective BTE-parts (BTE.sub.1, BTE.sub.2), and may e.g. further comprise respective ITE-parts (ITE.sub.1, ITE.sub.2). The ITE-parts may e.g. comprise electrodes for picking up body signals from the user, e.g. forming part of sensors S.sub.1i, S.sub.2i (i=1, . . . , N.sub.S) for monitoring physiological functions of the user, e.g. brain activity or eye movement activity or temperature (cf. e.g. FIG. 2A, 2B). The sensors mounted on the spectacle frame may e.g. comprise one or more of an eye camera (e.g. for monitoring pupillometry), a blood sensor for measuring oxygen in the blood, a sensor for monitoring Temporomandibular joint (TMJ) movement and/or neck muscle (sternocleidomastoid) activity (e.g. a radar sensor).

[0124] FIG. 4 shows an embodiment of a binaural hearing system comprising left and right hearing devices and an auxiliary device in communication with each other according to the present disclosure. FIG. 4 shows an embodiment of a binaural hearing system comprising left and right hearing devices (HD.sub.left, HD.sub.right) and an auxiliary device (AD) in communication with each other according to the present disclosure. The left and right hearing devices are adapted for being located at or in left and right ears and/or for fully or partially being implanted in the head at left and right ears of a user. The left and right hearing devices and the auxiliary device (e.g. a separate processing or relaying device, e.g. a smartphone or the like) are configured to allow an exchange of data between them (cf. links IA-WL and AD-WL in FIG. 4), including exchanging the (possibly amplified and/or digitized) output from electronic circuitry coupled to the sensor part (DET, e.g. a number of health sensors, e.g. bio sensors, e.g. comprising electrodes or sensors for picking up signals from the body of the user), or signals based thereon, e.g. EarEEG and/or EarEOG signals, which are fully or partially picked up by the respective left and right hearing devices. The binaural hearing system comprises a user interface (UI) fully or partially implemented in the auxiliary device (AD), e.g. as an APP, cf. Health Monitoring APP screen of the auxiliary device (AD) in FIG. 4. In the embodiment, of FIG. 4, at least one of the hearing devices and the auxiliary device comprises an alarm unit (AU) for initiating and/or providing an alarm to the user and/or to other systems or persons of relevance to the user and/or to the handling of a stroke (cf. signal AL). The issue of an alarm may be initiated in the auxiliary device, and e.g. presented on the user interface (UI), e.g. in the status screen (cf. Health Monitoring APP in FIG. 4). The left and right hearing devices each comprise a forward path between M input units IU.sub.i, i=1, . . . , M (each comprising e.g. an input transducer, such as a microphone or a microphone system and/or a direct electric input (e.g. a wireless receiver)) and an output unit (SP), e.g. an output transducer, here a loudspeaker. A beamformer or selector (WGTU) and a signal processor (SPU) is located in the forward path. In an embodiment, the signal processor is adapted to provide a frequency dependent gain according to a user's particular needs. In the embodiment of FIG. 4, the forward path comprises appropriate analogue to digital converters and analysis filter banks (AD/FBA) to provide input signals IN.sub.1, . . . , IN.sub.M (and to allow signal processing to be conducted) in frequency sub-bands (in the (time-) frequency domain). In another embodiment, some or all signal processing of the forward path is conducted in the time domain. The weighting unit (beamformer or mixer or selector) (WGTU) provides beamformed or mixed or selected signal RES based on one or more of the input signals IN.sub.1, . . . , IN.sub.M. The function of the weighting unit (WGTU) is controlled via the signal processor (SPU), cf. signal CTR, e.g. influenced by the user interface (signal X-CNT). The forward path further comprises a synthesis filter bank and appropriate digital to analogue converter (FBS/DA) to prepare the processed frequency sub-band signals OUT from the signal processor (SPU) as an analogue time domain signal for presentation to a user via the output transducer (loudspeaker) (SP).

[0125] The Health Monitoring APP of the auxiliary device (AD) in FIG. 4 is e.g. embodied in an APP of a smartphone. From the screen shown in FIG. 4, a stroke predictor can be configured and the results monitored (and configuration data can be transferred to the hearing device(s) to perform physiological measure recording based thereon and results can be transferred to the auxiliary device and availed to the Health Monitoring APP for possible analysis and display, cf. e.g. FIG. 1). Appropriate sensors for contributing to the (stroke related) health monitoring provided by the hearing system can be selected by ticking selection boxes to the left of the available sensors. In the example of FIG. 4, all three sensors Brainwaves (EEG), Eye movement (EOG) and Bloodoxygen % are selected (as indicated by solid square tick-box .square-solid.).

[0126] A Status box is provided below the Activated sensors box. The Status box is configured to provide feedback to the user (or a care assistant wearing the auxiliary device). In the situation exemplified in FIG. 4, the status of all three sensors is OK (i.e. no sign of stroke or an upcoming stroke based on comparison signals CSI.sub.i for the three selected sensors), and a concluding value of the stroke indicator CSI regarding a risk of stroke of the user is presented as Risk of stroke: LOW.

Example 1

[0127] The below table lists some examples of physiological functions and corresponding (possible) physiological measurement techniques for the estimation of stroke.

TABLE-US-00001 Physiological function (focus is on detection of any unilateral changes compared to individual baseline) Physiological measure(s) Brain activity Electroencephalography at ear level Blood oxygen saturation Pulse oximetry at ear level Ocular muscle activity Electrooculography at ear level Pupillometry also possible, but not at ear level: could be combined with smart glasses Video-oculography Temporomandibular joint (TMJ) Acoustics of ear canal based on movement feedback (to monitor changes in ear and neck muscle canal shape because of TMJ (sternocleidomastoid) movement) activity Radar (to monitor TMJ movement and neck muscle activity) Electromyography at ear level

[0128] Video-oculography represents a measure that is showing promise for early detection of stroke, see e.g. the study of [Toker et al.; 2013]. The study used L/R Vestibulo-ocular reflex (VOR) asymmetry to have a 100% accuracy in detecting stroke.

Example 2

[0129] Strokes have a three-hour critical window: Early detection is essential to reduce death and permanent brain damage. Earlier detection and treatment leads to significantly lower healthcare and societal costs.

[0130] It is proposed to use artificial intelligence in combination with one or more ear level sensors (e.g. located in left and right hearing devices of a binaural hearing aid system) to detect a stroke (and issue an alarm by notifying relevant persons/institutions) (cf. FIG. 5):

[0131] FIG. 5 shows an embodiment of a binaural hearing system comprising left and right hearing devices (HD.sub.left, HD.sub.right), using an artificial intelligence engine (AI-Engine) to analyze sensor data (ST.sub.i,left, ST.sub.i,right, i=1, . . . , N.sub.S) and e.g. an auxiliary device (AD) to implement a user interface (UI) according to the present disclosure. [0132] 1. Body parameters may be measured or monitored with ear-level sensors integrated in both left and right hearing devices (HD.sub.left, HD.sub.right), e.g. one or more, such as a majority, or all of: [0133] Brain activity (ear-level EEG) [0134] Blood oxygen saturation (ear-level pulse oximetry) [0135] Eye muscle activity (ear-level electrooculography) [0136] Jaw joint and neck muscle activity (acoustics of ear canal based on hearing device feedback, ear-level electromyography) [0137] 2. An Artificial Intelligence Engine (AI-Engine) drives sensor fusion and calculation of the brain asymmetry index (BAI) (or other stroke indicator). All sensor data are made available to the Artificial Intelligence engine (AI-Engine). It compares the body parameters (ST.sub.i,left, ST.sub.i,right) measured at the left and right ears. The left-right-delta (or difference) values (e.g. providing a brain asymmetry index) must stay below a specific threshold (TH). Because the chance of stroke is low, big data may establish a stable reference threshold for normal vs abnormal brain asymmetry index. This is important to avoid false positives as well as false negatives, so that only stroke sets off the alert, but so that all strokes set off the alert. Several AI techniques may be applied: [0138] Data cleaning and pre-processing: Excludes noise and outliers. [0139] Sensor fusion: Combines the data from all sensors in the training for accurate, complete, and dependable sensor data indicators. The system relies on the combination of all sensor data rather than just on one sensor. Data are preferably intelligently combined by weighting the inputs of the different sensors to provide increased reliability. This way the limitations of each individual type of sensor can be reduced and a more accurate estimation of whether the person is about to experience a stroke or not is provided. (AI technique applied: convolutional neural networks). [0140] Unsupervised learning: Finds hidden patterns or intrinsic structures in sensor data across all users (AI technique applied: clustering of sensor data). [0141] Supervised learning: Healthcare professional/healthcare systems/researchers adds data from confirmed cases of stroke. (AI technique applied: classification and regression). [0142] 3. Stroke alert system (SAS): When the brain symmetry index (BAI) exceeds the safe threshold value (cf. exemplary screen of the Health monitoring APP for User=U illustrated in FIG. 5, Activated sensors: Brainwaves (EEG) and Status: BAI>Safe TH), possibly in combination with criteria regarding other sensor parameters (cf. e.g. Eye movement (EOG), Blood oxygen %, Jaw muscle activity and corresponding Not OK (NOK) status indications in FIG. 5), a warning (WARN) is sent to the user (U) and/or to a general practitioner (GP) for screening of the condition (e.g. via the user interface (UI) of an auxiliary device (AD), e.g. a computer, such as a tablet or smartphone or the like, cf. warning Risk of stroke: HIGH and button Alert specialist in FIG. 5, which (upon activation) initiates an alert to call for immediate expert attention to the user U). An expert response may be fed back into the Artificial Intelligence Engine for supervised learning (cf. dashed line feedback signal signal EXPR in FIG. 5). The alert system is highly customizable based on the user's risk profile: can link directly to emergency service (112), to family members, to nursing home personnel, in accordance with the General Data Protection Regulations (GDPR). [0143] 4. To further strengthen predictions: Feed data from electronic health record/patient journal and health apps in the unsupervised learning and in the supervised learning.

[0144] In an embodiment, absorption of RF-power by the brain may be monitored (e.g. by measuring the power of the received wireless signal from the other hearing device of a binaural hearing system), cf. e.g. EP3035710A2 (section [0161]-[0168], and FIG. 9A-C). By comparing this radio absorption left-right and right-left, one might detect asymmetries that develop over time. Such asymmetry, e.g. defined by a predefined threshold value, may contribute to the confidence level of the decision of issuing a stroke alarm.

[0145] The present disclosure is exemplified by the estimation of a risk of an upcoming stroke of a user wearing a hearing system comprising health monitoring sensors. Other physiological events than stroke that can be associated with an asymmetric behaviour of physiological parameters detectable at the head (e.g. at the left and right ears) of a user may be correspondingly identified, e.g. epilepsy or other illnesses related to the central nervous system.

[0146] It is intended that the structural features of the devices described above, either in the detailed description and/or in the claims, may be combined with steps of the method, when appropriately substituted by a corresponding process.

[0147] As used, the singular forms a, an, and the are intended to include the plural forms as well (i.e. to have the meaning at least one), unless expressly stated otherwise. It will be further understood that the terms includes, comprises, including, and/or comprising, when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will also be understood that when an element is referred to as being connected or coupled to another element, it can be directly connected or coupled to the other element but an intervening element may also be present, unless expressly stated otherwise.

[0148] Furthermore, connected or coupled as used herein may include wirelessly connected or coupled. As used herein, the term and/or includes any and all combinations of one or more of the associated listed items. The steps of any disclosed method is not limited to the exact order stated herein, unless expressly stated otherwise.

[0149] It should be appreciated that reference throughout this specification to one embodiment or an embodiment or an aspect or features included as may means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the disclosure. Furthermore, the particular features, structures or characteristics may be combined as suitable in one or more embodiments of the disclosure. The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects.

[0150] The claims are not intended to be limited to the aspects shown herein, but is to be accorded the full scope consistent with the language of the claims, wherein reference to an element in the singular is not intended to mean one and only one unless specifically so stated, but rather one or more. Unless specifically stated otherwise, the term some refers to one or more.

[0151] Accordingly, the scope should be judged in terms of the claims that follow.

REFERENCES

[0152] [van Putten & Tavy; 2012] Michel J. A. M. van Putten and Denes L. J. Tavy, Continuous Quantitative EEG Monitoring in Hemispheric Stroke Patients Using the Brain Symmetry Index, Stroke 2004, 35:2489-2492: originally published online Oct. 7, 2004 [0153] EP3035710A2 (OTICON) 22 Jun. 2016 [0154] US20150319542A1 (OTICON) May 11, 2015 [0155] US20160081623A1 (OTICON) 24 Mar. 2016 [0156] [Toker et al.; 2013] Newman-Toker, D. E., Tehrani, A. S. S., Mantokoudis, G., Pula, J. H., Guede, C. I., Kerber, K. A., Ari Blitz, Sarah H. Ying, Yu-Hsiang Hsieh, Richard E. Rothman, Daniel F. Hanley, David S. Zee, Jorge C. Kattah, Quantitative video-oculography to help diagnose stroke in acute vertigo and dizziness, Stroke, 2013, 44(4), 1158-1161. [0157] EP3035710A2 (Oticon) 22 Jun. 2016