This disclosure is directed to techniques for identifying a medical condition, such as an infection and/or a disease, from sensor data indicative of physiological parameters. In some examples, one example technique for identifying the medical condition includes process sensor data comprising data indicative of a plurality of physiological parameters for a patient comprising an impedance parameter, computing an index based upon values corresponding to at least two of the physiological parameters and based upon a comparison between the index and prediction criterion, generating, for display, output data corresponding to the comparison results, wherein the output data indicates a prediction of the medical condition in the patient if the comparison results indicate satisfaction of the prediction criterion.

Described herein is an apparatus for monitoring various physiological parameters of a user. The apparatus may be in the form of a commode, so as to allow a user to obtain e.g., an ECG measurement while they are using the commode. The apparatus may comprise an electrode assembly comprising a set of electrodes to perform an electrocardiogram (ECG) by sensing an electrical signal corresponding to heart activity of a user when in contact with skin of the user and output the electrical signal. The apparatus may further comprise a converter assembly to convert the electrical signal to a modulated signal, and a transmitter to transmit the modulated signal. The apparatus may transmit the modulated signal to a computing device which may receive the modulated signal and determine whether the electrical signal indicates that the user is experiencing a heart condition.

A physiological information processing instrument according to the presently disclosed subject matter can include a memory that stores instructions, a processor that executes the instructions stored in the memory to judge whether an electrocardiogram waveform of a subject person is of at least one of a ventricular pacing beat and a left bundle branch block beat, to perform an ST measurement by applying myocardial ischemia evaluation criteria to the electrocardiogram waveform that has been judged of at least one of a ventricular pacing beat and a left bundle branch block beat, and to analyze results of the ST measurement and outputs an analysis result and information relating to myocardial ischemia in the form of audible or visible information.

A physiological information processing instrument according to the presently disclosed subject matter can include a memory that stores instructions, a processor that executes the instructions stored in the memory to judge whether an electrocardiogram waveform of a subject person is of at least one of a ventricular pacing beat and a left bundle branch block beat, to perform an ST measurement by applying myocardial ischemia evaluation criteria to the electrocardiogram waveform that has been judged of at least one of a ventricular pacing beat and a left bundle branch block beat, and to analyze results of the ST measurement and outputs an analysis result and information relating to myocardial ischemia in the form of audible or visible information.

Systems and methods are provided for analyzing electrocardiogram (ECG) data of a patient using a substantial amount of ECG data. The systems receive ECG data from a sensing device positioned on a patient such as one or more ECG leads. The system may include an application that communicates with an ECG platform running on a server(s) that processes and analyzes the ECG data, e.g., using neural networks for delineation of the cardiac signal and classification of various abnormalities, conditions and/or descriptors. The processed ECG data is communicated from the server(s) for display in a user-friendly and interactive manner with enhanced accuracy.

A method for measuring an electrocardiogram-based blood glucose using artificial intelligence is provided. The method includes: receiving an electrocardiogram signal of a user; extracting a plurality of unit electrocardiogram signals from the received electrocardiogram signal; extracting a blood glucose spatial feature from each of the plurality of unit electrocardiogram signals using a first artificial neural network model; and extracting a blood glucose feature by analyzing a time series change of the blood glucose spatial feature using a second artificial neural network model, and predicting blood glucose of the user based on the extracted blood glucose feature.

A system for acquiring electrocardiograph (ECG) and bioimpedance (BI) data is disclosed. The system (an ECG/BI measurement system) can use as few as one or two pairs of electrodes, permitting wearable devices employing the ECG/BI measurement system to be made into smaller, more comfortable, and more inconspicuous formats, as well as decreasing potential failure points in the measurement of electrical signals conducted between the system and the user. The system can measure both ECG and BI data using at least one shared pair of electrodes. In some cases, ECG and BI data are separately extracted from a measured signal across a shared pair of electrodes, while another pair of electrodes is being driven with a supply current. In other cases, internal switching can automatically switch a pair of electrodes between ECG-measuring circuitry and BI-measuring circuitry, such as based on a clock signal or other trigger.

A method for non-invasive detection of coronary artery disease (CAD). The method includes acquiring a raw ECG signal from a patient, generating a denoised ECG signal by applying a first wavelet transform on the raw ECG signal, generating an artifact-free ECG signal by applying a second wavelet transform on the denoised ECG signal, generating a filtered ECG signal by applying a band-stop filter on the artifact-free ECG signal, extracting an averaged ECG signal of a plurality of averaged ECG signals from the filtered ECG signal, detecting an ST segment in the averaged ECG signal by applying a delineation algorithm on the averaged ECG signal, detecting an isoelectric line in the averaged ECG signal, determining an existence of CAD in the patient responsive to detecting a CAD detection condition, and determining a non-existence of CAD responsive to not detecting the CAD detection condition.

Electrical impulses are received from a beating heart. The electrical impulses are converted to an ECG waveform. The ECG waveform is converted to a frequency domain waveform, which, in turn, is separated into two or more different frequency domain waveforms, which, in turn, are converted into a plurality of time domain cardiac electrophysiological subwaveforms and discontinuity points between these subwaveforms. The plurality of subwaveforms and discontinuity points are compared to a database of subwaveforms and discontinuity points for normal and abnormal patients or to a set of rules developed from the database. An ST segment and one or more ST subwaveforms within the ST segment are identified from the plurality of subwaveforms and discontinuity points based on the comparison. The ECG waveform with the one or more ST subwaveforms within the ST segment is displayed.

A glucose monitoring system can make use of electrocardiograph (ECG) data and bioimpedance data acquired from a wearable device. The ECG data and bioimpedance data can each be processed to obtain a glucose level. These values can be processed together to obtain an adapted glucose value. In some cases, photoplethysmography data can also be used to assist in processing of the ECG data. The various types of data can be acquired from sensors on a wearable device. The wearable device can be removably coupled to a user's skin, such as via an adhesive substrate. In some cases, the wearable device can include a reusable electronics module that couples to replaceable electrodes on a replaceable adhesive substrate.