A physiological monitoring device is provided and includes a physiological sensing device, a first PPG sensor, a vital signs detector, and a PPG controller. The physiological sensing device senses at least one physiological feature of a subject to generate at least one sensing signal. The first PPG sensor senses pulses of a blood vessel of the subject to generate a first PPG signal when the first PPG sensor is activated. The vital signs detector obtains vital signs data according to the at least one sensing signal. The PPG controller detects whether a specific event is happening to the subject according to the vital signs data. In response to detecting that the specific event is happening to the subject, the PPG controller activates the first PPG sensor. The physiological monitoring apparatus obtains a blood oxygen level of the subject according to the first PPG signal.

A system and methods for a hands-free transmission, reception, and processing of a heartbeat audio is disclosed. In one embodiment, the system includes a heart monitor having a microphone, configured to pick-up a heartbeat sound wave and convert the heartbeat sound wave to a heartbeat audio, and a transmitter, configured to transmit the heartbeat audio; headphones having a receiver, configured to receive the heartbeat audio from the transmitter, and a speaker configured to play the heartbeat audio for a user; and a software application configured to (i) generate an overlaid audio by overlaying a secondary audio file onto the heartbeat audio, (ii) transmit the overlaid audio to the receiver, and (iii) play the overlaid audio using the speaker while the user is meditating, relaxing, or working out.

Exercise-based watch faces and complications for use with a portable multifunction device are disclosed. The methods described herein for exercise-based watch faces and complications provide indications of time and affordances representing applications (e.g., a workout application or a weather application). In response to detecting a user input corresponding to a selection of the affordance (e.g., representing a workout application), a workout routine can optionally be begun. Further disclosed are non-transitory computer-readable storage media, systems, and devices configured to perform the methods described herein, as well as electronic devices related thereto.

A medical device is configured to detect an atrial tachyarrhythmia episode. The device senses a cardiac signal, identifies R-waves in the cardiac signal attendant ventricular depolarizations and determines classification factors from the R-waves identified over a predetermined time period. The device classifies the predetermined time period as one of unclassified, atrial tachyarrhythmia and non-atrial tachyarrhythmia by comparing the determined classification factors to classification criteria. A classification criterion is adjusted from a first classification criterion to a second classification criterion after at least one time period being classified as atrial tachyarrhythmia. An atrial tachyarrhythmia episode is detected by the device in response to at least one subsequent time period being classified as atrial tachyarrhythmia based on the adjusted classification criterion.

A method of generating a model for generating a synthetic electrocardiography (ECG) signal comprises: receiving subject-specific training data for machine learning, said training data comprising a photoplethysmography (PPG) signal acquired from the subject and an ECG signal acquired from the subject, wherein the ECG signal provides a ground truth of the subject for associating the ECG signal with the PPG signal; using associated pairs of a time-series of the PPG signal and a corresponding time-series of the ECG signal as input to a deep neural network, DNN; and determining, through the DNN, a subject-specific model relating the PPG signal of the subject to the ECG signal of the subject for converting the PPG signal to a synthetic ECG signal using the subject-specific model.

Provided are a brain stimulation system, method, apparatus and storage medium based on artificial intelligence. The system includes: a plurality of brain stimulation terminals and a cloud platform. The cloud platform is configured to, with artificial intelligence algorithm especially machine learning and deep learning, generate multi-dimensional psychological big data using physiological data and psychological state evaluation parameters gotten from the plurality of brain stimulation terminals and established models of algorithm for disease diagnosis. The brain stimulation terminal is configured to analyze the physiological data and psychological state evaluation parameters of a target subject, measure a mental state of the target subject, obtain brain stimulation parameters required for the target subject according to the mental state, and generate corresponding non-invasive brain stimulation for the target subject according to the brain stimulation parameters based on the multi-dimensional big data through the artificial intelligence algorithm.

An apparatus and method for detecting a bio-signal feature are provided. The apparatus according to one aspect may include: a bio-signal acquirer configured to acquire a bio-signal; and a processor configured to generate an envelope signal of the bio-signal, and detect at least one feature of the bio-signal based on a difference between the envelope signal and the bio-signal.

Embodiments herein relate to reflective optical medical sensor devices. In an embodiment, a reflective optical medical sensor device including a central optical detector and a plurality of light emitter units disposed around the central optical detector is provided. A plurality of peripheral optical detectors can be disposed to the outside of the plurality of light emitter units. Each of the plurality of peripheral optical detectors can form a channel pair with one of the plurality of light emitter units. The reflective optical medical sensor device can also include a controller in electrical communication with the central optical detector, the light emitter units, and the peripheral optical detectors. The controller can be configured to measure performance of channel pairs; select a particular channel pair; and measure a physiological parameter using the selected channel pair. Other embodiments are also included herein.

The present disclosure relates to noninvasive methods for detecting liver fibrosis. Disclosed herein are noninvasive liver fibrosis detection methods that use Doppler Ultrasound devices and a physics-based machine learning method. Further disclosed herein are methods for detecting liver fibrosis in a subject by detecting and measuring the presence of a shift in the frequency of blood flow in the hepatic vein as compared to the frequency of blood flow in the portal vein.

The present disclosure relates to noninvasive methods for detecting liver fibrosis. Disclosed herein are noninvasive liver fibrosis detection methods that use Doppler Ultrasound devices and a physics-based machine learning method. Further disclosed herein are methods for detecting liver fibrosis in a subject by detecting and measuring the presence of a shift in the frequency of blood flow in the hepatic vein as compared to the frequency of blood flow in the portal vein.