# US 2019/0167130 A1 · Apparatus, Methods And Computer Programs For Analyzing Heartbeat Signals > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0167130 A1 - Document ID: US20190167130A1 - Status: Published application - Kind: A1 - Application number: 16/212,303 - Filed: 2018-12-06 - Published: 2019-06-06 - Earliest claimed: 2017-12-06 - Assignees: Withings - Applicants: Withings - Inventors: Ugo Marchand; David Campo - Web page: https://patentgrep.com/patent/US20190167130A1 ## CPC - A61B 5/02438: {with portable devices, e.g. worn by the patient} - A61B 5/0006: {ECG or EEG signals} - A61B 5/0255: Recording instruments specially adapted therefor - A61B 5/352: Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval - A61B 5/6824: {Arm or wrist} - A61B 5/7203: {for noise prevention, reduction or removal} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - A61B 7/04: Electric stethoscopes - G16H 40/63: for local operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/30: for calculating health indices; for individual health risk assessment - A61B 7/02: Stethoscopes - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract An apparatus, method and computer program, the apparatus comprising: processing circuitry and memory circuitry including computer program code, the memory circuitry and the computer program code arranged to, with the processing circuitry, cause the apparatus to: obtain an audio signal from an audio sensing means wherein the audio signal comprises a subject's heartbeat; obtain a further signal from a further sensing means wherein the further signal also comprises the subject's heartbeat; use the further signal to identify individual heart beats in the audio signal; and analyse the individual heartbeats of the audio signal to enable the audio signal to be classified. ## Claims ### Claim 1 An apparatus comprising an audio sensing means, a further sensing means, attachment means for attaching the apparatus to a subject, wherein the audio sensing means is positioned within the apparatus so that when the apparatus is attached to the subject the audio sensing means is positioned adjacent to the subject's torso, the apparatus further comprising a processing circuitry and a memory circuitry including a computer program code, the memory circuitry and the computer program code arranged to, with the processing circuitry, cause the apparatus to: obtain an audio signal from the audio sensing means wherein the audio signal comprises a heartbeat of the subject; obtain a further signal from the further sensing means wherein the further signal also comprises the heartbeat of the subject; use the further signal to identify individual heart beats in the audio signal; and analyse the individual heartbeats of the audio signal to enable the audio signal to be classified. ### Claim 2 (depends on 1) The apparatus as claimed in claim 1 wherein the audio sensing means is positioned within the apparatus so that when the apparatus is attached to a subject the audio sensing means is positioned underneath the subject's arm. ### Claim 3 (depends on 1) The apparatus as claimed in claim 1 wherein the attachment means comprises a cuff which is arranged to fit around the subject's arm. ### Claim 4 (depends on 1) The apparatus as claimed in claim 1 wherein the further sensing means comprises means for sensing a bioelectric signal. ### Claim 5 (depends on 4) The apparatus as claimed in claim 4 wherein the bioelectric signal comprises an electrocardiogram signal. ### Claim 6 (depends on 1) The apparatus as claimed in claim 1 wherein the memory circuitry and the computer program code are configured to, with the processing circuitry, cause the apparatus to identify R peaks in the further signal to enable individual heartbeats in the audio signal to be identified. ### Claim 7 (depends on 1) The apparatus as claimed in claim 1 wherein the memory circuitry and the computer program code are configured to, with the processing circuitry, cause the apparatus to divide the individual heartbeats of the audio signal into segments corresponding to different portions of the heartbeat. ### Claim 8 (depends on 1) The apparatus as claimed in claim 1 wherein the memory circuitry and the computer program code are configured to, with the processing circuitry, cause the apparatus to use wavelets to remove noise from the audio signal. ### Claim 9 (depends on 1) The apparatus as claimed in claim 1 wherein the memory circuitry and the computer program code are configured to, with the processing circuitry, cause the apparatus to extract features from within an individual heartbeat of the audio signal and use the extracted features to classify the audio signal. ### Claim 10 (depends on 1) The apparatus as claimed in claim 1, further comprising a user interface enabling a user to interact with the apparatus, and enabling the apparatus to provide a feedback to the user. ### Claim 11 (depends on 10) The apparatus as claimed in claim 10, wherein the user interface comprises a display arranged to output information for the user. ### Claim 12 (depends on 10) The apparatus as claimed in claim 10, wherein the user interface comprises a loudspeaker arranged to output information for the user. ### Claim 13 (depends on 1) A wearable device comprising the apparatus as claimed in claim 1. ### Claim 14 A method to be carried out with an apparatus by a user, the method comprising: S1—obtaining an audio signal from an audio sensing means wherein the audio signal comprises a subject's heartbeat; S2—giving a feedback to the user upon determination that the obtained audio signal has a quality level below a given threshold, and in which case causing step S1 to be repeated S3—obtaining a further signal from a further sensing means wherein the further signal also comprises the subject's heartbeat; S4—giving a feedback to the user upon determination that the obtained further signal has a quality level below a given threshold, and in which case causing step S3 to be repeated, S5—using the further signal to identity individual heart beats in the audio signal; and S6—analysing the individual heartbeats of the audio signal, S7—classifying the individual heartbeats, S8—providing a result to the user as to whether the heartbeat of the subject is normal or abnormal. ### Claim 15 (depends on 14) The method as claimed in claim 14, further comprising after step S1 a noise removing process using a wavelet signal transform to retain significant signal portions and to remove noise from the audio signal. ### Claim 16 (depends on 14) The method as claimed in claim 14, further comprising after step S3 a noise removing process using a wavelet signal transform to retain significant signal portions and to remove noise from the further signal. ### Claim 17 (depends on 14) The method as claimed in claim 14, wherein during step S2 when a quality level of the audio signal is determined, the method includes the determination of a speech occurrence, either a subject speech of other people talk around. ### Claim 18 (depends on 17) The method as claimed in claim 17, wherein the determination of a speech occurrence is made via assessment of zero-crossing rate and spectral flatness on one or more portions of the audio signal. ### Claim 19 (depends on 14) The method as claimed in claim 14, further comprising: S9—forwarding the recorded audio signal, named a phonocardiogram, from the apparatus to a remote device having a loudspeaker therein, S10—replaying on demand, at the remote device, the phonocardiogram via the loudspeaker. ### Claim 20 A computer program comprising computer program instructions that, when executed by processing circuitry, cause: obtaining an audio signal from an audio sensing means wherein the audio signal comprises a subject's heartbeat; obtaining a further signal from a further sensing means wherein the further signal also comprises the subject's heartbeat; using the further signal to identify individual heartbeats in the audio signal; and analysing the individual heartbeats of the audio signal to enable the audio signal to be classified.