Methods, systems, and devices are disclosed for an efficient hardware architecture to implement gradient boosted trees for detecting biological conditions. For example, a method of detecting a biological condition includes receiving, by a device, a plurality of physiological signals from a plurality of input channels of the device, selecting, based on a trained prediction model, one or more input channels from the plurality of input channels, converting the one or more physiological signals received from the one or more input channels to one or more digital physiological signals, identifying, by using the plurality of gradient boosted decision trees, the selected characteristic in the one or more digital physiological signals, and determining a presence of a physiological condition based on an addition of the output values obtained from the plurality of gradient boosted decision trees.

Abnormalities in electromagnetic fields in the heart, brain, and stomach, among other organs and tissues of the human body, can be indicative of serious health conditions. Described herein are methods, software, systems and devices for detecting the presence of an abnormality in an organ or tissue of a subject by analysis of the electromagnetic fields generated by the organ or tissue.

Systems and methods for data compression which facilitate the diagnosis and treatment of neurodevelopmental and neurodegenerative disorders. The methods comprise performing the following operations by a computing device: generating Normalized Data (“ND”) from Original Data (“OD”) that defines a Normalized Waveform (“NW”) that is unitless and scaled from zero to one; processing ND to extract Micro-Movement Data (“MMD”) defining a Micro-Movement Waveform (“MMW”) comprising a plurality of MMD points; and generating compressed data comprising a stochastic signature of MMW. Each MMD point determined based on a value of a peak of NW and a value representing an average of all data point values between a first valley of NW immediately preceding the peak and a second valley of NW immediately following the peak. The stochastic signature is defined by empirically estimated values of at least one parameter representing a Probability Distribution Function (“PDF”) of a continuous family of PDFs.

A method of distinguishing a non-epileptic seizure from an epileptic seizure in a patient, comprising: detecting a seizure in a patient based on at least one first body signal of the patient selected from an autonomic signal, a neurologic signal, a metabolic signal, an endocrine signal, and a tissue stress marker signal; analyzing at least one second body signal of the patient selected from an autonomic signal, a neurologic signal, a metabolic signal, an endocrine signal, and a tissue stress marker signal; determining, based on the analyzing, at least a first classification index comprising at least one of an epileptic seizure index and a non-epileptic seizure index; and classifying the seizure as one of a non-epileptic seizure or an epileptic seizure based on the at least a first classification index. A medical device system capable of implementing the method. A computer-readable device for storing data that, when executed, perform the method.

A method, comprising receiving a time series of patient body signal, determining first and second sliding time windows for the time series; applying an autoregression algorithm, comprising: applying an autoregression analysis to each of the first and second windows, yielding autoregression coefficients and a residual variance for each window; estimating a parameter vector for each window based on the autoregression coefficients and residual variances; and determining a difference between the parameter vectors; and determining seizure onset and seizure termination based on the difference between the parameter vectors. A non-transitory computer readable program storage unit encoded with instructions that, when executed by a computer, perform the method.

A system and method is provided for modeling brain dynamics in normal and diseased states.

An implantable device for implantation in a human body or animal body. The device includes an energy source, an energy storage device, and an electronics unit. Further, an actuator is coupled with the energy storage device and it is configured to emit electromagnetic waves by discharging the energy storage device.

Systems, apparatus, and methods for treating medication refractory epilepsy are disclosed. In one embodiment, a method of treating epilepsy is disclosed comprising detecting, using a first electrode array coupled to a first endovascular carrier, an electrophysiological signal of a subject. The method further comprises analyzing the electrophysiological signal using a neuromodulation unit electrically coupled to the first electrode array and stimulating an intracorporeal target of the subject using a second electrode array coupled to a second endovascular carrier implanted within a part of a bodily vessel superior to a base of the skull of the subject.

A method and apparatus to detect environmental triggers of stress and antecedent physiological stress symptoms of a patient, followed up with delivery of stress relieving therapeutic response to the patient and a chronological report of events. An embodiment comprises a first device worn by the patient that contains sensors and can transmit and receive signals and a second device used by the caregiver that can transmit and receive signals. This integrated system continuously monitors environmental triggers and physiological stress indicative parameters of a patient diagnosed with autistic spectrum disorder, or other emotional or physical disorders, and compares these parameters against thresholds for the parameters. These thresholds can be configured automatically by the system—based on past episodes—or manually by the caregiver, or using automatically configured thresholds that are fine-tuned by the caregiver. When the parameters exceed the configured thresholds, several responses can be automatically generated by the system including: 1) generating therapeutic calming responses and cues to the patient to alleviate the episode, 2) sending notifications to the caregiver's device for intervention, and 3) creating a chronological assessment report of environmental stress triggers, antecedent physiological stress symptoms, and the resultant behavior of the patient.

Non-invasive intracranial pressure detection and/or monitoring and use of data with respect thereto. Illustratively, with respect to a method, there can be a method to digitally produce and communicate intracranial pressure data from skull deformation electric signals, the method including: receiving, from at least one sensor, detected skull deformation electric signals at electrical equipment configured to transform and process the skull deformation signals that are received; transforming and processing, by the electrical equipment, the received skull deformation electric signals to produce digital intracranial pressure data; and outputting, by the electrical equipment, the digital intracranial pressure data via an output device operably associated with the electrical equipment to render the digital intracranial pressure data.