The present invention relates to a method of analysing cardiac data relating to a patient, comprising: providing cardiac data relating to the patient—optionally by using a means for providing physiological data (20); determining one or more properties of the data, wherein the or each property is determined over a particular context length, the context length being selected based on the or each property—optionally using an analysis module (24); comparing the or each property against a respective predetermined threshold value, thereby to indicate a probability of the patient experiencing a cardiac event—optionally using a means for providing an output (26); and providing an output based on the comparison. A system and apparatus corresponding to this method is also disclosed.

Systems, apparatuses and methods may provide for technology that converts a plurality of multi-channel time-synchronized signals into a plurality of image patches, combines the plurality of image patches into an image, and generates, by a transformer neural network, a classification result based on the image.

This disclosure is directed to a medical system and technique for a filter-based approach to arrhythmia detection. In one example, the medical system comprises one or more sensors configured to sense physiological parameter(s); sensing circuitry configured to generate patient data based on the sensed physiological parameter(s), the patient data comprising signal data to represent cardiac activity of the patient; and processing circuitry configured to: detect a cardiac arrhythmia for the patient based on a classification of the signal data in accordance with a machine learning model, wherein the machine learning model comprises filter(s) for at least one portion of the signal data, wherein the at least one filter corresponds to a feature set that maps to the cardiac activity represented by the portion(s) of the signal data; and generate for display output data indicative of a positive detection of the cardiac arrhythmia.

A method of obtaining and analyzing ECG data from a patient or group of patients is disclosed. The ECG data is obtained from the patient at an acquisition device. Once the ECG data is obtained, the ECG data is transmitted to an analysis server that is operated by an analysis provider and is located remote from the location of the acquisition device. Along with the ECG data, acquisition parameters are transmitted to the analysis server. At the analysis server, one of a plurality of algorithms is selected to analyze the ECG data. If an abnormality is detected, the patient information is directed to a healthcare provider who can then contact the patient to schedule an appointment. Based upon the referral, a referral fee can be transferred from the healthcare provider to the analysis provider. The patient can be prompted to provide additional information and selections that dictate the level of analysis generated.

To provide an electrocardiogram analysis system capable of determining the need for an electric shock to a patient undergoing cardiopulmonary resuscitation (CPR) with a higher accuracy. An electrocardiogram analysis system includes electrocardiogram (ECG) signal acquiring means 11, ECG signal sampling means 12, ECG spectrogram transforming means 13, impedance signal acquiring means 21, impedance signal sampling means 22, impedance spectrogram transforming means 23, a convolutional neural network (CNN) 4 including an input layer 4I, an output layer 4O, sample data accumulation means 4L, and sample data input means 4T, and electric shock indication reporting means 5. The CNN is a priori provided with sample data including sample ECG spectrograms and sample impedance spectrograms obtained from a large number of subjects, and sample response data on the need for an electric shock, and is optimized by self-learning the sample data.

To provide an electrocardiogram analysis system capable of determining the need for an electric shock to a patient undergoing cardiopulmonary resuscitation (CPR) with a higher accuracy. An electrocardiogram analysis system includes electrocardiogram (ECG) signal acquiring means 11, ECG signal sampling means 12, ECG spectrogram transforming means 13, impedance signal acquiring means 21, impedance signal sampling means 22, impedance spectrogram transforming means 23, a convolutional neural network (CNN) 4 including an input layer 4I, an output layer 4O, sample data accumulation means 4L, and sample data input means 4T, and electric shock indication reporting means 5. The CNN is a priori provided with sample data including sample ECG spectrograms and sample impedance spectrograms obtained from a large number of subjects, and sample response data on the need for an electric shock, and is optimized by self-learning the sample data.

A portable electrocardiographic device includes: an electrode unit configured to detect an electrocardiographic waveform; and a control unit configured to record, in a storage unit, the electrocardiographic waveform detected by the electrode unit. The electrode unit includes a pair of measurement electrodes for measuring the electrocardiographic waveform, and an earth electrode for detecting a reference potential for a change in a potential of a body, and the earth electrode is disposed in such a manner that a distal end side of a finger of a subject that is a target of the electrocardiographic waveform measurement is brought in contact with the earth electrode, and one of the measurement electrodes is disposed on a proximal end side of the finger of the subject, the distal end side of which is in contact with the earth electrode.

An apparatus yields signals that are equivalent to ECG signals and allow determination of a heartbeat interval or heart rate from bio-vibration signals including vibrations derived from heartbeats. An ECG meter acquires ECG signals of a sample, and a piezoelectric sensor acquires bio-vibration signals of the sample simultaneously. The bio-vibration signals include beating vibration signals derived from heartbeats. A learning unit of a prediction modeling apparatus establishes a prediction model by machine learning in which ECG signals are used as teaching data, and model input signals obtained by performing a specified processing on the bio-vibration signals are input. The learning unit delivers the prediction model to a prediction unit of a signal processing apparatus. The prediction model predicts and outputs pECG signals upon input of model input signals obtained by performing a specified processing on bio-vibration signals acquired from a subject under prediction with a piezoelectric sensor.

A user device containing carbon nanotubes coatings for increasing ECG electrode conductivity while maintaining visually dark electrodes in wearable devices. The carbon nanotubes can also allow for the carbon nanotube coated electrode to increase or cause a capillary action of sweat to increase conductivity of the sweat and signal strength from the skin.

A rapid chest pain risk assessment system includes an assessor, a computed tomography (CT) scanner, an electrocardiogram device for providing electrocardiogram related data, and an enzyme analyzer for analyzing the patient's blood. A computer enabled risk calculator categorizes the patients into low, intermediate, and high risk categories. The computer enabled risk calculator, using data from electrocardiogram, blood analyzer and patient's age, other risk factors and history, automatically generates orders for patients in low and intermediate risk categories to undergo a CT scan. A CAC analyzer using the computer file for analyzing the CT scan results then provides a CAC score based on those CT scan results. A risk score based on electrocardiogram, blood analyzer and patient's age, other risk factors and history of symptoms plus the CAC score is generated. Patients that are automatically assessed as being very low risk based on the risk score are recommended for discharge from the emergency room thereby lowering the unnecessary prolonged ER stay time.