SCH: INT: Collaborative Research: Diagnostic Driving: Real Time Driver Condition Detection Through Analysis of Driving Behavior

点击翻译按钮获取中文摘要

The automobile presents a great opportunity for healthcare monitoring. For one, most Americans engage in daily driving, and patient's time spent in vehicles is a missed opportunity to monitor their condition and general wellbeing. The goal of this project is to develop and evaluate technology for automatic in-vehicle monitoring of early symptoms of medical conditions and disrupted medications of patients, and to provide preventive care. Specifically, in this project we will focus on Attention-Deficit/Hyperactivity disorder (ADHD) in teenagers and young adults, a prevalent chronic medical condition which when uncontrolled has the potential for known negative health and quality of life consequences. The approach of using driving behavior to monitor ADHD symptoms could be applied to many other medical conditions (such as diabetes, failing eyesight, intoxication, fatigue or heart attacks) thereby transforming medical management into real-time sensing and management. Identification of all these conditions from driving behavior and alerting the proper agent could transform how we think about health monitoring and result in saved lives and reduced injuries.The main goal of this project is to leverage the large amounts of health data that can be collected while driving via machine learning, in order to detect subtle changes in behavior due to out-of-control ADHD symptoms that can, for example, indicate the onset of episodes of inattention before they happen. Via lab-based driving simulator as well as on-road studies, the research team will investigate the individualized behaviors and patterns in vehicle control behaviors that are characteristic of ADHD patients under various states of medication usage. The team will develop a machine learning framework based on case-based and context-based reasoning to match the current driving behavior of the patient with previously recorded driving behavior corresponding to different ADHD symptoms. The key machine learning challenge is to define appropriate similarity measures to compare driving behavior that take into account the key distinctive features of ADHD driving behavior identified during our study. The team will evaluate the accuracy with which the proposed approach can identify and distinguish between different out-of-control ADHD symptoms, which are the implications for long-term handling of ADHD patients, via driving simulator experiments as well as using instrumented cars with real patients.