An apparatus for determining balance compensation includes a platform, sensors and a processor. The platform is configured for a person to stand on the platform. The sensors are coupled to the platform and measure at least one of a weight and a pressure. The processor determines a balance of the person based on the measurements of the sensors.

A computer-implemented method includes obtaining a video of a subject, the video including a plurality of frames; generating, based on the plurality of frames, a plurality of optical flows; and encoding the plurality of optical flows using an autoencoder to obtain a movement-based biomarker value of the subject.

A shivering detection apparatus (100) for detecting shivering of a patient (150) is provided. The apparatus (100) comprises a control unit (110) operatively connected to a transmit unit (120), for transmitting a transmit signal (170) based on a reference signal (140) of a transmit frequency towards the patient (150). The control unit is further operatively connected to a receive unit (130), for receiving a receive signal (190) as a portion of a reflected signal (180) comprising a portion of the transmit signal (170) reflected by the patient (150). The control unit (110) is configured to compare the receive signal (190) to the reference signal (140) and to detect shivering of the patient (150) as differences between the receive signal (190) and the reference signal (140). An associated method and sensor head is also provided.

A system and method for determining a measurement of anxiety in a vehicle that include receiving sensor data from a plurality of sensors disposed within a plurality of areas of the vehicle. The system and method also include processing the sensor data into metrics associated with a type of measurement. Processing of the sensor data is completed by a neural network. The system and method also include analyzing the processed metrics and determining an anxiety level associated with an occupant of the vehicle. The system and method further include training the neural network based on the anxiety level and at least one driving event that is correlated with the anxiety level.

A method includes: obtaining an electrocardiosignal of a target user; importing the electrocardiosignal into a preset atrial fibrillation signal classification model, to obtain a signal type, of the electrocardiosignal, output by the atrial fibrillation signal classification model, where the atrial fibrillation signal classification model is obtained through training with an atrial fibrillation patient being a model training sample; and calculating, based on the signal type of the electrocardiosignal, a risk level of an atrial fibrillation occurrence, to predict whether the target user is to have an atrial fibrillation attack.

A system for monitoring the respiratory activity of a subject, which comprises one or more movement sensors, applied to the thorax of a subject, for generating first signals that are indicative of movement of the thorax of the subject; a receiver for receiving the first generated signals during breathing motion of the subject; and one or more computing devices in data communication with the receiver, for analyzing the breathing motion. The computing device is operable to generate a first breathing pattern from the first signals; divide each respiratory cycle experienced by the subject and defined by the first pattern into a plurality of portions, each of the portions delimited by two different time points and calculate, for each of the plurality of portions of a given respiratory cycle of the first pattern, a slope representing a thorax velocity; derive, from the given respiratory cycle of the first pattern, a pulmonary air flow rate of the subject during predetermined portions of the respiratory cycle; compare between corresponding portions of the first pattern and average flow rates during different phases of the breathing cycle, to calibrate a thorax velocities of the subject with pulmonary air flow rates; and determine respiratory characteristics of the subject for subsequent respiratory cycles experienced by the subject, based on a calculated thorax velocity and the calibration.

Medical device systems and methods are disclosed herein for assessing motor symptoms in Parkinson's disease patients through passively and/or actively acquired sensor data of motor behaviors and generating motor system assessments. Passive movement data and/or active motor performance data collected from Parkinson's disease patients is representative of EQ-5D-5L, PDQ-39, and/or MDS-UPDRS health status measurement data to more accurately predict quality of life, health status, and disease severity of Parkinson's disease patients. The generated motor system assessment may be used to provide neurologists and other health professionals with more accurate treatment recommendations and disease management protocols rather than using patient surveys alone.

A method and user device for providing a unified Parkinson's disease rating scale (UPDRS) value by a user device includes generating, by a sensor of the user device, sensor data based on a user of the user device manipulating the user device. The UPDRS value is determined based on the sensor data and a deep neural network (DNN) model. The UPDRS value is provided to permit an evaluation of the user based on the UPDRS value.

A writing instrument that includes a writing element for depositing a writing material on a support and a plurality of sensors including at least a force sensor and a movement sensor, a communication unit that exchanges data with a remote device a control unit connected to the sensors and to the communication unit in order to transmit to the remote device the measurements provided by the sensors, a memory unit connected to the control unit that stores one or more measurements from the sensors; and a hollow casing that contains at least part of the writing element so that the writing end is exposed, and also houses the sensors, the control unit, the memory unit and the communication unit.

This disclosure relates to a system and method to implement a performance test to help evaluate a patient's neurological and cognitive function. The performance test can be executed by the patient autonomously using a portable computing device, such as a tablet computer or smart phone. The portable computing device can be programmed to execute a set of modules configured to assess motor and cognitive performance, such as a manual function test module, a cognitive processing speed test module, and a movement assessment test module. The set of modules can also include a collection module to aggregate test data from the manual function test module, the cognitive processing speed test module, and the movement assessment test module.