Novel ML-Based Algorithm for Detecting Seizures from Single-Channel EEG.

There is a need for seizure classification based on EEG signals that can be implemented with a portable device for in-home continuous minoring of epilepsy. In this study, we developed a novel machine learning algorithm for seizure detection suitable for wearable systems. Extreme gradient boosting (XGBoost) was implemented to classify seizures from single-channel EEG obtained from an open-source CHB-MIT database.

Model-based analysis of implanted hypoglossal nerve stimulation for the treatment of obstructive sleep apnea.

Study Objectives: Individuals with obstructive sleep apnea (OSA), characterized by frequent sleep disruptions from tongue muscle relaxation and airway blockage, are known to benefit from on-demand electrical stimulation of the hypoglossal nerve. Hypoglossal nerve stimulation (HNS) therapy, which activates the protrusor muscles of the tongue during inspiration, has been established in multiple clinical studies as safe and effective, but the mechanistic understanding for why some stimulation parameters work better than others has not been thoroughly investigated.

Methods: In this study, we developed a detailed biophysical model that can predict the spatial recruitment of hypoglossal nerve fascicles and axons within these fascicles during stimulation through nerve cuff electrodes.

Recovering Motor Activation with Chronic Peripheral Nerve Computer Interface.

Interfaces with the peripheral nerve provide the ability to extract motor activation and restore sensation to amputee patients. The ability to chronically extract motor activations from the peripheral nervous system remains an unsolved problem. In this study, chronic recordings with the Flat Interface Nerve Electrode (FINE) are employed to recover the activation levels of innervated muscles.

Model-based Bayesian signal extraction algorithm for peripheral nerves.

Objective: Multi-channel cuff electrodes have recently been investigated for extracting fascicular-level motor commands from mixed neural recordings. Such signals could provide volitional, intuitive control over a robotic prosthesis for amputee patients. Recent work has demonstrated success in extracting these signals in acute and chronic preparations using spatial filtering techniques.

Fabrication of High Contact-Density, Flat-Interface Nerve Electrodes for Recording and Stimulation Applications.

Many attempts have been made to manufacture multi-contact nerve cuff electrodes that are safe, robust and reliable for long term neuroprosthetic applications. This protocol describes a fabrication technique of a modified cylindrical nerve cuff electrode to meet these criteria. Minimum computer-aided design and manufacturing (CAD and CAM) skills are necessary to consistently produce cuffs with high precision (contact placement 0.

Ultra-low noise miniaturized neural amplifier with hardware averaging.

Objective: Peripheral nerves carry neural signals that could be used to control hybrid bionic systems. Cuff electrodes provide a robust and stable interface but the recorded signal amplitude is small (<3 μVrms 700 Hz-7 kHz), thereby requiring a baseline noise of less than 1 μVrms for a useful signal-to-noise ratio (SNR). Flat interface nerve electrode (FINE) contacts alone generate thermal noise of at least 0.

A biomechanical assessment of isometric handgrip force and fatigue at different anatomical positions.

The present work examined the handgrip force at different anatomical positions for both hands. Anthropometrics, handgrip force, and fatigue were obtained from a representative sample of 20 males randomly selected from the German Jordanian University students. The hand dynamometer first was calibrated with respect to the volunteer's maximal grip strength, and he was then asked to squeeze maximally until the grip force decreased to 50% of its maximal due to fatigue; this test was performed for both hands at different anatomical positions with 2 min of rest for recovery of muscle function.