Driving under the influence remains a pressing issue in the United States, contributing to approximately one-third of all fatal car crashes and claiming 11,000 lives annually. This research project aims to progress public safety by developing a technological solution aligned with the Department of Transportation's specifications. Our system administers an automated Horizontal Gaze Nystagmus (HGN) test that exposes and detects a driver's physiological impairment in order to prevent them from driving while intoxicated. The novelty in our system lies in the personalized machine-learning algorithm that ensures a precise and confidential assessment of a user's sobriety. Our algorithm is backed by significant amounts of data collected from controlled IRB testing that establishes a statistical baseline and is personalized through the performance of each user during their one-time calibration phase. Once calibrated, our system can determine if a user is unfit to operate their vehicle and will consequently immobilize their automobile's transmission. Throughout the entire process the user's data such as their identity, scores, or personalized scoring model, remains confidential through advanced encryption techniques. In all, these technological advancements within our system address the needs determined by the Department of Transportation in a personalized, robust, and confidential manner.
No takes yet. Share an insight, caveat, or question.
Coleman et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: