An attention mechanism-based 12-lead electrocardiogram (ECG) classification method is described, the method including acquiring an original image of a 12-lead ECG, segmenting waveform data recorded in the original image to obtain segmented waveform data for each lead in the 12-lead ECG, performing depth feature extraction on the segmented waveform data of said each lead to obtain a first feature map of said each lead, performing feature transformation on the first feature map of said each lead based on an attention mechanism to obtain a depth feature of said each lead, and classifying the depth feature of said each lead to obtain a classification result for the original image. The classification method can make full use of the 12-lead ECG for overall classification and improve the accuracy of image classification.

A wearable medical device is provided for monitoring a cardiac condition of a patient, where the device is releasably mounted to the patient's chest and includes at least two skin-facing electrodes forming a first one or more ECG leads for ongoing monitoring of heart functioning and at least one touch electrode for intermittently obtaining additional circuit vectors for deriving additional metrics regarding the functioning of the patient's heart. Each touch electrode is configured to form an additional lead/vector that is a larger vector and/or separated by at least 15 from a corresponding first lead/vector formed from the first one or more ECG leads in a vector cardiogram representation of the first one or more ECG leads and the additional lead/vector.

A portable medical device having an intravenous line flow sensor integrated into a cable. The portable medical device may be a defibrillator having an ECG or electrode cable couple to ECG or electrode leads. The flow sensor may be integrated into the ECG or electrode cable. The portable medical device uses the flow sensor to capture and store information about fluids delivered to a patient being treated with the portable medical device. The information may include total volume provided, flow rate, and the like. The information may then be used to evaluate the treatment provided to the patient.

An electrocardiography (ECG) scanner module, a multi-contact connector thereof, an ECG scanner thereof and smart clothes using the same are provided. The multi-contact connector includes a base, a fitting portion and several first conductive portions. The base is disposed on a wearable carrier having several conductive wires. The fitting portion is disposed on the base and surrounds a receiving portion. The first conductive portions are annularly disposed on an inner periphery surface of the receiving portion, and each first conductive portion connects to the corresponding conductive wire. The ECG scanner includes several second conductive portions, and an end of each second conductive portion is projected from an outer periphery surface of the ECG scanner. When the multi-contact connector connects to the ECG scanner, each second conductive portion provides a radial force for connecting to the corresponding first conductive portion.

A Wearable Medical System includes a support structure that is configured to be worn by a person. The WMS also includes an electronics module, a cable assembly, and at least one electrode that can be configured to be coupled to the support structure. The cable assembly includes a base member and a cable coupled to the base member. The support structure can be dimensioned relative to the person's body to be worn with tension, and be resiliently stretched under the tension. The stretching of the support structure can stretch the base member of the cable assembly, thus increasing the effective length of the cable, while reducing or even eliminating slack in the cable.

Classification of heartbeats based on intracardiac and body surface electrocardiogram (ECG) signals are provided. Intracardiac ECG (IC-ECG) signals and body surface ECG (BS-ECG) signals are processed to perform heartbeat classifications. A BS annotation of BS-ECG signals reflective of a sensed heartbeat is defined, the BS annotation including a BS annotation time value. IC annotations of IC-ECG signals which reflect atrial-activity or ventricular activity of the sensed heartbeat are also defined, each IC annotation including an IC annotation time value. The IC-ECG signals are discriminated as A-activity or V-activity and IC annotations are designated as IC-A annotations or IC-V annotations, respectively. A respective A/V time sequence comparison of IC annotations reflective of the sensed heartbeat is made with one or more time sequence templates for heartbeat classification. Morphology comparisons of the BS-ECG oscillating signal segments reflective of the sensed heartbeat morphology templates for classification may also be made.

A wearable medical device is provided for monitoring a cardiac condition of a patient, where the device is releasably mounted to the patient's chest and includes at least two skin-facing electrodes forming a first one or more ECG leads for ongoing monitoring of heart functioning and at least one touch electrode for intermittently obtaining additional circuit vectors for deriving additional metrics regarding the functioning of the patient's heart. Each touch electrode is configured to form an additional lead/vector that is a larger vector and/or separated by at least 15 from a corresponding first lead/vector formed from the first one or more ECG leads in a vector cardiogram representation of the first one or more ECG leads and the additional lead/vector.

A method of providing a graphical representation of sleep quality includes obtaining ECG data for a patient, obtaining a plurality of N-N intervals from the ECG data, calculating a plurality of spectral densities based on the plurality of N-N intervals, wherein each spectral density is associated with one of a plurality of successive time windows and is calculated based on certain ones of the N-N intervals associated with the one of the plurality of successive time windows, and generating the graphical representation of sleep quality using the plurality of spectral densities.

A cardiac function measurement and evaluation device is provided to measure and evaluate cardiac function in patients with atrial fibrillation, sinus arrhythmia, and the like, using thoracic impedance data and electrocardiogram data. By creating a two-dimensional scatter plot in which (dZ/dt)min values and preceding RR intervals (RR1) corresponding thereto, and the like obtained by thoracic impedance measurement, are plotted, it is possible to visually and easily evaluate the state of cardiac function in patients with atrial fibrillation and sinus arrhythmia. Using the measurement and evaluation device of the present invention makes it possible to perform examinations easily and repeatedly with less burden on patients. Therefore, it is possible to provide very useful information for diagnosing heart disease, selecting drugs, and the like.

A method for acquiring electrical signals from a living subject, including injecting, via an injection electrode attached to the subject, a known calibration signal to the subject and measuring respective levels of output signals generated at input electrodes attached to the subject in response to the calibration signal. The method further includes deriving respective weighting factors for the input electrodes in response to the respective levels, and applying the respective weighting factors to physiological signals acquired by the input electrodes, so as to generate respective corrected physiological signals.