Abstract: Machine learning (ML) techniques can help harness insights from data that complement and extend those that can be attained by traditional statistical methods. The current article introduces clinicians to concepts underlying ML and explores how it can be applied within the domain of neuropsychology. Specifically, we illustrate an application of ML to a dataset that includes a battery of standardized measures designed to provide diagnostic support for concussions, including standardized neurocognitive (CPT 3) and neurobehavioral (BESS, NIH 4 meter gait) measures, gait sensor data, and a CDC concussion symptom checklist. These variables were used to predict the decision-making of a pediatric neurologist evaluating a group of child/adolescent patients. With a sample of 111 cases, ML (using a general linear model and deep learning as illustrations) achieved accuracies of 91% and 84.8% and AUCs of 1.0 and .947, respectively, when predicting the neurologist’s binomial decision-making (safe/remove). In presenting the data and various considerations for interpretation, we attempt to balance both the promise and perils of ML.
Abstract: Effective screening for concussion is increasingly important, and medical professionals play a critical role in diagnostic and return-to-play decisions. However, few well-validated measures are available to assist in those decisions. This study aims to determine whether previously validated measures assessing neurocognitive and neurobehavioral abilities can predict Centers for Disease Control (CDC) concussion symptom endorsement in a sample of child or youth athletes.
Abstract: Sports-related concussions are particularly dangerous injuries due to their complex nature and difficulties associated with diagnostic and return-to-play decisions. Some of the most commonly employed assessment tools have been shown to be unreliable, leading to misdiagnoses. Guidelines for selecting more effective concussion assessment instruments and the use of such tests in urgent care settings are here suggested as an optimal framework for improved care.