An apparatus for detecting sleep disorders, such as obstructive sleep apnea, includes a housing insertable into an ear canal of a subject. A sensor disposed within the housing measures a position of the subject's head relative to an axis of gravity. A transducer is responsive to the sensor and is capable of creating a stimulus detectable by the subject under certain conditions. In various embodiments, a controller receives signals corresponding to a pitch angle and a roll angle of the subject's head measured by the sensor, determines if the pitch and roll angles correspond to a sleep apnea inducing position, and causes the transducer to generate a stimulus upon determining that the subject's head is in the sleep apnea inducing position more than a predetermined threshold number of times. Various parameters of the stimulus may be modified with successive stimulus generation until a non-sleep apnea inducing position is detected.

A smart multi-modal telehealth IoT system for respiratory analysis. Such a system includes a body area sensor network comprised of meshed wireless sensor nodes and advanced machine learning techniques. The system may be used to remotely diagnose a user's respiratory illness and monitor their health.

A method and system are disclosed for use in monitoring/screening/diagnosing sleep or wake state of a subject or patient. The method generally includes monitoring the patient's activity during one or more sleep sessions comprising a plurality of intervals known as epochs. The sleep/wake state of the subject is determined during each epoch of the session using actigraphy data obtained during the monitoring session. The actigraphy data provides information about the activity of a patient during an epoch. The sleep or wake state is determined based on a ratio of the activity count during an epoch to the activity count during a preceding epoch. If the ratio is greater than a first activity threshold, then a “wake” indication may be provided by, for example, the system. Alternatively, or additionally, a “wake” indication may be determined if the activity count during the epoch is greater than a threshold.

A non-invasive method and system is provided for determining an internal component of respiratory effort of a subject in a respiratory study. Both a thoracic signal (T) and an abdomen signal (A) are obtained, which are indicators of a thoracic component and an abdominal component of the respiratory effort, respectively. A first parameter of a respiratory model is determined from the obtained thoracic signal (T) and the abdomen signal (A). The first parameter is an estimated parameter of the respiratory model that is not directly measured during the study. The internal component of the respiratory effort is determined based at least on the determined first parameter of the respiratory model. The first model parameter is determined based on the thorax signal (T) and the obtained abdomen signal (A) without an invasive measurement.

A system and method for identifying sleep states of a subject are provided. In some aspects, the method includes acquiring physiological data from a subject over a sleep period using sensors positioned about the subject, and assembling the physiological data into time-series datasets. The method also includes selecting a temporal window in which signals associated with the time-series datasets are substantially stationary, computing a time bandwidth product based on a selected spectral resolution and the selected temporal window, and determining a number of tapers using the computed time bandwidth product. The method further includes computing a spectrogram using the determined number of tapers and the time-series datasets, analyzing the spectrogram to identify signatures of sleep in the subject, and generating, using the identified signatures, a report indicative of sleep states of the subject.

Systems and Methods for determining a physiological parameter are disclosed. The physiological sensing device can measure a physiological parameter, determine a mood based on the physiological parameter, and render one or more songs associated with the mood.

A biological information detection device includes: a video capture unit, a blood flow analysis unit, a local pulse wave detection unit, a pulse wave propagation velocity calculation unit, and a blood pressure estimation unit. The video capture unit obtains video information on a face of a living body. The blood flow analysis unit analyzes video data of at least three skin areas in the video information, as blood flow information. The local pulse wave detection unit is provided for each skin area to calculate pulse information based on the blood flow information sequenced chronologically. The pulse wave propagation velocity calculation unit calculates a pulse wave propagation velocity based on a phase difference between pieces of the pulse information at each skin area calculated by the local pulse wave detection unit. The blood pressure estimation unit estimates blood pressure based on the pulse wave propagation velocity.

A method for estimating a metabolic rate of a user includes obtaining pulse oximetry data for the user for a period of time. The method includes determining a rate of decline in oxygen saturation of blood of the user that is associated with a breathing rate of the user for the period of time based, at least in part, on the pulse oximetry data. The method includes estimating the metabolic rate of the user for the period of time based, at least in part, on the rate of decline in the oxygen saturation of the blood that is associated with the breathing rate of the user. The method includes providing a notification indicative of the metabolic rate for the period of time.

The present disclosure relates to an apparatus for predicting a hemodynamics parameter being conventionally obtained from an implanted sensor or catheter (invasive sensor), e.g., pulmonary artery pressure, based on noninvasive biosignals, such as electrocardiographic (ECG), impedance cardio graphic (ICG), phonocardiogram (PCG), pulse oximetry plethysmograph (PPG). The present disclosure also relates to a method of feeding multiple noninvasive biosignals and/or general inputs into an AI model or AI models to predict a hemodynamics parameter, such as pulmonary artery pressure, which is conventionally obtained from an implanted sensor or catheter.

A healthcare apparatus includes a BCG sensor; a camera; and a processor configured: to detect a ROI) corresponding to the face from the color facial image; to convert the detected first color image into a black and white image to acquire a first black and white image; to convert the detected second color image into a black and white image to acquire a second black and white image; to apply the acquired first black and white image and the acquired second black and white image to a predetermined trained algorithm model to output a remote photoplethysmography (rPPG) signal waveform of the subject; to calculate a first stress index based on the first heart rate variability; to calculate a second stress index based on the second heart rate variability; and to output a stress index of the subject based on the first stress index and the second stress index.