No abstract

Concussions are common cognitive impairments, but their effects on task performance in general, and on driving in particular, are not well understood. To better understand the effects of concussion on driving, we investigated previously gathered data on twenty-two people with a concussion, driving in a virtual-reality driving simulator (VRDS), and twenty-two non-concussed matched drivers. Participants were asked to per-form a behavioral task (either coin sorting or a verbal memory task) while driving. In this study, we chose a few common metrics from the VRDS and tracked their changes through time for each participant. Our pro-posed method—namely, the use of convolutional neural networks for classification and analysis—can accu-rately classify concussed driving and extract local features on driving sequences that translate to behavioral driving signatures. Overall, our method improves identification and understanding of clinically relevant driv-ing behaviors for concussed individuals and should generalize well to other types of impairments.

The Human Phenotype Ontology (HPO) is a dictionary of more than 15,000 clinical phenotypic terms with defined semantic relationships, developed to standardize their representation for phenotypic analysis. Over the last decade, the HPO has been used to accelerate the implementation of precision medicine into clinical practice. In addition, recent research in representation learning, specifically in graph embedding, has led to notable progress in automated prediction via learned features. Here, we present a novel approach to phenotype representation by incorporating phenotypic frequencies based on 53 million full- text health care notes from more than 1.5 million individuals. We demonstrate the efficacy of our proposed phenotype embedding technique by comparing our work to existing phenotypic similarity- measuring methods. Using phenotype frequencies in our embedding technique, we are able to identify phenotypic similarities that surpass the current computational models. In addition, we show that our embedding technique aligns with domain experts' judgment at a level that exceeds their agreement. We show that our proposed technique efficiently represents complex and multidimensional phenotypes in HPO format, which can then be used as input for various downstream tasks that require deep phenotyping, including patient similarity analyses and disease trajectory prediction.