Computer implemented biometric methods and systems incorporate sensing biophysical phenomena, translating the phenomena into digital data and transmitting the data to a series of servers operating in an open feedback loop to generate a module. A biometric networking system can include a biometric monitoring cloud computing platform with AI/machine learning augmented models are generated to make user assessments, programs and confidence scores to the healthcare provider systems. The AI/machine learning models can be used by the biometric monitoring network to generate health-related AI processes that analyze relationships treatment techniques and outcomes. AI techniques can be used to calculate movement modeling and confidence scoring including support vector machines, neural networks, and decision trees. The biophysical phenomena may include biometric parameters based on data, such as medical history, exertion, sleep, temperature, cardiovascular events, respiratory events, and muscle and blood pH.

Systems and methods for assessing compliance with position therapy. In an embodiment, position therapy is provided to a user while the user is wearing a position therapy device. The position therapy comprises, by the device, collecting positional data, determining positions of the user over a time period based on the positional data, and, when it is determined that the user is in a target position, providing feedback to the user to influence the user to change to a non-target position. In addition, the device stores a duration of use in its memory. The duration of use indicates a duration that the user has used the wearable position therapy device in each of one or more positions. An assessment of the user's compliance with the position therapy is then provided based, at least in part, on the duration of use.

An apparatus including circuitry configured to determine a probability by combining at least: a probability that an event is present within a current feature of interest given a first set of previous features of interest, and a probability that the event is present within the current feature of interest given a second set of previous features of interest, different to the first set of previous features of interest; circuitry configured to detect the event based on the determined probability; and circuitry configured to control, in dependence on the detection of the event, performance of an action.

The present invention relates to methods for modulating bursts of oscillatory brain activity, such as sleep spindles, in a subject. The invention further relates to methods of improving memory or cognitive function in a subject and method of modulating or enhancing the frequency of occurrence, structure, amplitude, and/or synchronization of sleep spindles in a subject by detecting a burst of oscillatory brain activity in the subject and passing an oscillating current through the skull of the subject.

In a respiratory apparatus for treatment of sleep apnea and other disorders associated with an obstruction of a patient's airway and which uses an airflow signal, an obstruction index is generated which detects the flattening of the inspiratory portion of the airflow. The obstruction index is used to differentiate normal and obstructed breathing. The obstruction index is based upon different weighting factors applied to sections of the airflow signal thereby improving sensitivity to various types of respiration obstructions.

The present invention relates to methods for assessing swallowing motor function in a subject. The methods rely on obtaining intraluminal impedance and pressure measurements from the pharynx and/or esophagus of the subject during clearance of a bolus from the mouth and/or throat of the subject. The intraluminal impedance and pressure measurements are combined to derive a value for one or more pressure-flow variables in the pharynx and/or the esophagus of the subject. The value of the one or more pressure-flow variables is compared to a predetermined pharyngeal and/or esophageal reference value for the one or more pressure-flow variables in order to provide an assessment of swallowing motor function in the subject. The intraluminal impedance and pressure measurements can also be combined to generate a swallow risk index for the subject or to generate an obstructive risk index for the subject based on a combination of a value of more than one pressure-flow variable in the pharynx and/or esophagus of the subject. In this way, swallowing motor function in the subject can be assessed by comparing the swallow risk index or obstructive risk index for the subject to a predetermined reference swallow index or predetermined reference obstructive index, respectively. Products which make use of these methods are also encompassed by the present invention.

In a method and apparatus for swallowing impairment detection, a candidate executes one or more swallowing events, and dual axis accelerometry data is acquired representative thereof. Upon feature extraction and classification, vibrational data acquired in respect of each swallowing event is classified as indicative of one of normal or possibly impaired swallowing.

Remote monitoring of a subject wearing a sports helmet is enabled. In one aspect, an example system includes a safety helmet and a sensor integrated with the helmet for continuously gathering head acceleration force data, the head acceleration force data associated with the head movements of a subject. The system can also include a wireless transceiver coupled to the sensor for transmitting the head acceleration force data and a mobile device for receiving the head acceleration force data from the wireless transceiver. The system can further include a database engine for displaying the head acceleration force data to a user.

A system uses a wearable electronic device to monitoring behavior of an operator of a vehicle. The wearable device is worn on the head of the operator of the vehicle and includes one or more motion sensors. A processor of the wearable device or of a proximate portable electronic device receives data from the one or more motion sensors and detects a pattern of motion based on the data. The system then may determine a physiological state or physical behavior of the driver based on the detected patterns or motion. Detected physiological states may include head bobs associated with sleepiness. Detected physical behaviors may include dangerous behaviors such as phone usage, prolonged gazes, sudden lane changes, or hard braking or steering.

Systems and methods for predicting exposure to an agent. One or more features are extracted from physiological data. For each respective classifier, (i) the respective classifier is identified, wherein the respective classifier is trained using training data for a respective physiological state, (ii) the respective classifier is applied to the one or more features to obtain a classifier output that represents a likelihood of exposure, (iii) a respective first threshold is applied to the classifier output to determine a patient state classification, and (iv) the patient state classifications are aggregated across a number of time intervals to obtain an aggregate patient state classification for each classifier. The aggregate patient state classifications are combined across the plurality of classifiers to obtain a combined classification, and an indication that the patient has been exposed to the agent is provided when the combined classification exceeds a second threshold.