An Overview of Machine Learning Applications in Sports Injury Prediction.

Use injuries, i.e., injuries caused by repetitive strain on the body, represent a serious problem in athletics that has traditionally relied on historic datasets and human experience for prevention. Existing methodologies have been frustratingly slow at developing higher precision prevention practices. Technological advancements have permitted the emergence of artificial intelligence and machine learning (ML) as promising toolsets to enhance both injury mitigation and rehabilitation protocols. This article provides a comprehensive overview of recent advances in ML techniques as they have been applied to sports injury prediction and prevention. A comprehensive literature review was conducted searching PubMed/Medline, Institute of Electrical and Electronics Engineers (IEEE)/Institute of Engineering and Technology (IET), and ScienceDirect. Ovid Discovery and Google Scholar were used to provide additional aggregate results and a grey literature search. A focus was placed on papers published from 2017 to 2022. Algorithms of interest were limited to K-Nearest Neighbor (KNN), K-means, decision tree, random forest, gradient boosting and AdaBoost, and neural networks. A total of 42 original research papers were included, and their results were summarized. We conclude that given the current lack of open source, uniform data sets, as well as a reliance on dated regression models, no strong conclusions about the real-world efficacy of ML as it applies to sports injury prediction can be made. However, it is suggested that addressing these two issues will allow powerful, novel ML architectures to be deployed, thus rapidly advancing the state of this field, and providing validated clinical tools.

An intrinsically stretchable and bendable electrochromic device.

Stretchable electrochromic devices (ECDs) were fabricated from electrospun PEDOT:PSS (poly(3, 4-ethylenedioxythiophene):polystyrene sulfonate) fibers. Stretchable and transparent electrodes with a sheet resistance of 1200 Ω sq-1were prepared by depositing the conductive fibers on elastomeric substrates that were prepared from polydimethylsiloxane. The conductive substrates replaced the ITO coated glass electrodes that are typically used in ECDs. The functioning device was prepared from a flexible chitosan electrolytic gel and a 4, 7-bis(4-diphenylaminophenyl)-2, 1, 3-benzothiaziazole (TPA-BZT-TPA) electrochrome that were deposited on the streatchable transparent electrodes. The assembled device could be stretched to 150% its original length and bent to a curvature of 0.1. The device could be operated and switched between its yellow (off) and blue (on) states while being stretched and bent with a maximum contrast ΔT ≈ 30% at 805 nm and a coloration efficiency of 168 cm2C-1. The stretchable device had an electrochromic contrast that was 30% greater than its counterpart that was prepared from conventional ITO-glass electrodes. The critical composition required for making devices truly stretchable was possible by evaluating the performance of five types of devices consisting of different layers.

Investigation of Seizure-Susceptibility in a Drosophila melanogaster Model of Human Epilepsy with Optogenetic Stimulation.

We examined seizure-susceptibility in a Drosophila model of human epilepsy using optogenetic stimulation of ReaChR (red-activatable channelrhodopsin). Photostimulation of the seizure-sensitive mutant parabss1 causes behavioral paralysis that resembles paralysis caused by mechanical stimulation, in many aspects. Electrophysiology shows that photostimulation evokes abnormal seizure-like neuronal firing in parabss1 followed by a quiescent period resembling synaptic failure and apparently responsible for paralysis. The pattern of neuronal activity concludes with seizure-like activity just prior to recovery. We tentatively identify the mushroom body as one apparent locus of optogenetic seizure initiation. The α/ß lobes may be primarily responsible for mushroom body seizure induction.