Patient sleep is staged using personalized circadian models built with data collected by wearable devices over daytime and nighttime hours, thus capturing a patient's personal circadian rhythms. The circadian model is used to identify sleep intervals in incoming nightly data for the patient. The identified sleep intervals are analyzed by the machine learning system which stages epochs of sleep. Methods include receiving patient heart rate data from over a plurality of circadian cycles; creating a circadian model for the patient with a defined operation for applying sleep labels to new data from the wearable device; applying the circadian model to nightly test data from the device to identify a sleep interval; and assigning, with a classifier, sleep stages to epochs of the sleep interval.

Generally, methods, devices, and systems related to analyte monitoring and data logging are provided—e.g., as related to in vivo analyte monitoring devices and systems. In some aspects, methods, devices, and systems are provided that relate to enable related settings based on an expected use of an in vivo positioned sensor; logging or otherwise recording analyte levels acquired or derived—e.g., sample analyte levels more frequently than they are logged or otherwise recorded in memory; dynamically adjust the data logging frequency; randomly determine times of acquiring or storing analyte levels from the in-vivo positioned analyte sensors; and enable recording related settings when the system is operable.

An electrocardiogram analysis apparatus includes: an electrocardiogram signal inputting section to which electrocardiogram signals of measurement electrodes attached to a subject are input; a mistaken attachment determining section which, by using the input electrocardiogram signals, determines whether the measurement electrodes are mistakenly attached or not; an outputting section which, if it is determined that the measurement electrodes are mistakenly attached, notifies of mistaken attachment of the measurement electrodes; and an electrocardiogram data storing section which, in a case where there is an input indicative of confirmation of the notification, stores information indicating that the measurement electrodes have been checked, together with the input electrocardiogram signals, and, in a case where there is not an input indicative of confirmation of the notification, stores information indicating that the measurement electrodes have not been checked, together with the input electrocardiogram signals.

A system for telemedicine diagnostics through remote sensing includes a computing device configured to initiate a communication interface between the computing device and a client device operated by a human subject, wherein the secure communication interface includes an audiovisual streaming protocol, receive, from at least a remote sensor at the human subject, a plurality of current physiological data, generate a clinical measurement approximation as a function of the change of a first discrete and a second discrete set of current physiological data, wherein generating further comprises receiving approximation training data correlating physiological data with clinical measurement data, training a measurement approximation model as a function of the training data and a machine-learning process, and generating the clinical measurement approximation as a function of the current physiological data and the measurement approximation model, and presenting the clinical measurement approximation to a user of the computing device using the secure communication interface.

A method for estimating blood pressure using a blood flow occlusion system applied to an artery includes receiving from a first sensor a sensed signal; processing at a processor the sensed signal to detect beats in a pulsatile signal; determining validity of the detected beats; storing the detected beats and data associated with the detected beats in the sensed signal as the pressure applied to the artery by the blood flow occlusion system deflates towards a level below a nominal level; determining baseline beat characteristics; evaluating the stored beats and associated data to detect change in beat characteristics as compared to the baseline beat characteristics; selecting a beat before the detected change in the beat characteristic as the last beat indicating the onset of the diastolic blood pressure for the artery; determining a value of the applied pressure at the last beat as the diastolic blood pressure for the artery.

A PPG PRV device for generating a PRV parameter of a PPG signal (20) as an estimation of a HRV parameter of an ECG signal. The PPG PRV device employs a PPG probe (700) and a PPG PRV controller (710). In operation, the PPG probe (700) generate a PPG signal (20). In response thereto, the PPG PRV controller (710) generates a normalized PPG signal (20′) including a plurality of pulses of the PPG signal (20) designated as normal pulses by the PPG PRV controller (710) and excluding at least one pulse of the PPG signal (20) designated at least one abnormal pulse by the PPG PRV controller (710), wherein the normalized PPG signal (20′) is HRV comparable to the ECG signal. The PPG PRV controller (710) derives the PRV parameter from a HRV measurement of the normalized PPG signal (20′).

Methods, systems, and computer programs encoded on a computer storage medium, for improving EEG measurements by identifying artifacts present in EEG measurements and providing a real-time indication to a user of likely artifacts in EEG measurements are described. EEG measurements of a patient can be obtained by placing a wearable device or EEG cap on a patient's head. Sensors in the cap provide EEG data to a computing device that processes the data to identify one or more artifacts in the EEG data. The artifacts can be identified by conducting one or more operations of determining the signal to noise ratio of the line noise, calculating mutual information between sensor pairs, and applying the p-welch method. Based on the types of artifacts identified, the computing device can output an indicator that provides feedback to the technician performing an EEG test to make adjustments to the test setup.

An implantable medical device (IMD) and method are provided. The IMD includes a sensing channel configured to obtain biological signals indicative of biological behavior of an anatomy of interest over a period of time. The biological behavior has a feature of interest that repeats over time. The biological signals have clinically relevant (CR) segments that include information related to the feature of interest. The biological signals have non-clinically relevant (NCR) segments that do not include information related to the feature of interest. At least one of circuitry or a processor are configured to compare the biological signals to an amplitude window to distinguish the CR segments from the NCR segments, save to memory the CR segments and delete the NCR segments, save to memory time information indicative of a duration of the NCR segments that were deleted and to form a lossy compressed data set for the biological signals.

A data processing method for detecting and classifying a segment of a signal that is obtained from a single-channel EEG-recording as a target signal segment or as a non-target signal segment. The method includes a voting process to determine whether classification of a first detected segment of the signal as a target signal segment or classification of a second detected segment of the signal as a non-target signal segment is correct. A device and a system that are configured and arranged to perform the data processing method.

A device is disclosed comprising: an optical physiological sensor and a further measurement system. The optical physiological sensor comprises a light emitter and a light detector configured to detect the light from the light emitter after it has been attenuated by tissue comprising blood vessels. The optical physiological sensor is configured to determine the value of a physiological parameter from the detected light. The further measurement system is configured to determine when the value of the physiological parameter is likely to be reliable. The further measurement system comprises at least one measurement subsystem, each measurement subsystem employing a different measurement modality that is also different to a measurement modality used to determine the value of the physiological parameter.