An ambulatory medical device is provided. The ambulatory medical device includes at least one sensor configured to acquire sensor data descriptive of patient motion and at least one processor coupled to the at least one sensor. The at least one processor is configured to detect the patient motion from the sensor data, and to classify the patient motion.

A treatment system for stimulating the vagus nerves is described, comprising the following elements: —a detection and control unit (20); —at least one detection probe (10d, 10g) connected to the detection and control unit and intended to be applied to at least one of the two vagus nerves of a patient; —means (24) provided in the detection and control unit for detecting a phenomenon of mass discharge of action potentials in at least one vagus nerve using the detection probe or detection probes; —stimulation probes (10d, 10g) for stimulating vagus nerves, and—means (24) provided in the detection and control unit that are capable, in response to the detection of a mass discharge, of applying predefined asymmetric stimulation signals to said stimulation probes capable of causing a depolarization and/or hyperpolarization of the vagus nerves and of blocking the conduction of the action potentials at least in the efferent direction. The system is intended for preventing the risk of sudden death in the event of an epileptic seizure in epilepsy patients.

A method for estimating a physical condition used by a computer includes simultaneously measuring blood flow volumes of at least two body parts of a person and estimating the person's physical condition on the basis of the blood flow volumes of the at least two body parts measured in the simultaneously measuring.

A seizure characterization method includes correlating locations of electrodes placed around a brain and used to produce sequential electroencephalography (EEG) signals with a three-dimensional anatomical brain model derived from magnetic resonance imaging (MRI). The sequential EEG signals are modelled from the electrodes placed around the brain in three dimensions using cortical and sub-cortical brain regions included in the brain model to define constraints for the numerical solution. Amounts of the sequential EEG signals are quantified in three dimensions relative to the brain regions included in the brain model. The method also includes establishing, based on the quantifying, at least one propagation pattern of the sequential EEG signals in time relative to the brain regions in the brain model.

Provided herein are neural interface systems for a patient, the systems comprising an implantable sensor device and an external processing device. The implantable sensor device comprises: an implantable lead assembly for implantation above the skull and below the skin of the patient, and for recording physiologic parameter information of the patient; and an implantable transmitter for receiving the physiologic parameter information from the implantable lead assembly and for transmitting patient data that is based on the physiologic parameter information. The external processing device receives the patient data from the implantable transmitter. Methods of provided a neural interface are also described.

Methods and systems for monitoring use, determining risk, and pricing insurance policies for a vehicle having one or more autonomous or semi-autonomous operation features are provided. According to certain aspects, a computer-implemented method for communicating information regarding a smart infrastructure component to an autonomous or semi-autonomous vehicle may be provided. Sensors may be communicatively connected to an infrastructure communication device, and the infrastructure communication device may generate a message based upon information from the sensors and/or regarding the infrastructure component. The message may be transmitted, and, with the vehicle operator's permission, all or part of the determined message may be presented to the operator of the autonomous or semi-autonomous vehicle. The message may include weather, traffic, ice, or road condition or construction information and facilitate safer vehicle travel. Insurance discounts for customers may be generated based upon their vehicle being equipped with this safety and vehicle damage prevention functionality.

The present disclosure provides for monitoring brain health and predicting and detecting seizures via a wearable head ap paratus. An exemplary system includes a wearable head apparatus with a plurality of sensors. The system includes a memory device with instructions for performing a method. The method provides for first receiving electroencephalography (EEG) data and/or other data types output by the plurality of sensors. The EEG data includes electrical signals representing brain activity of a user. The method provides for processing the EEG data and/or other data types using a machine learning model to identify a time window of a subset of the EEG data and/or other data types, which represents a seizure. The method provides for tagging the time window as seizure data. A representation of the time window of the EEG data and/or other data types is then output.

A region on the head is examined with respect to the different muscles present in the region, and correlation areas are defined, where not two correlation areas relate to the same muscle in the region. The EEG probes are then produced individually for the examined human in order to optimize positioning of the electrodes on the different correlation areas. This way, signals from the muscles can be filtered out relatively easy when combining the signals from the different electrodes because the signals are not correlated between the electrodes, in contrast to the EEG signals.

A method for creating a mother wavelet function. The method includes preparing a plurality of vectors, extracting a kernel from the plurality of vectors, and extracting the mother wavelet function from the kernel. The kernel includes a mode value of a vector of the plurality of vectors.

A method for detecting and predicting an epileptic seizure. The method includes preparing a plurality of electrical signals, extracting a plurality of patterns from the plurality of electrical signals, extracting a plurality of features from the plurality of electrical signals by applying the plurality of patterns on the plurality of electrical signals, optimizing the plurality of patterns and the plurality of features, and classifying each of the plurality of electrical signals in a plurality of classes by applying a plurality of classifiers on the plurality of features. The plurality of electrical signals include a plurality of samples. The plurality of classes include a seizure class and a non-seizure class, and the plurality of classifiers include a plurality of cascaded AdaBoost classifiers.