Using Speech Data From Interactions With a Voice Assistant to Predict the Risk of Future Accidents for Older Drivers: Prospective Cohort Study

Abstract

Background With the rapid growth of the older adult population worldwide, car accidents involving this population group have become an increasingly serious problem. Cognitive impairment, which is assessed using neuropsychological tests, has been reported as a risk factor for being involved in car accidents; however, it remains unclear whether this risk can be predicted using daily behavior data. Objective The objective of this study was to investigate whether speech data that can be collected in everyday life can be used to predict the risk of an older driver being involved in a car accident. Methods At baseline, we collected (1) speech data during interactions with a voice assistant and (2) cognitive assessment data—neuropsychological tests (Mini-Mental State Examination, revised Wechsler immediate and delayed logical memory, Frontal Assessment Battery, trail making test-parts A and B, and Clock Drawing Test), Geriatric Depression Scale, magnetic resonance imaging, and demographics (age, sex, education)—from older adults. Approximately one-and-a-half years later, we followed up to collect information about their driving experiences (with respect to car accidents) using a questionnaire. We investigated the association between speech data and future accident risk using statistical analysis and machine learning models. Results We found that older drivers (n=60) with accident or near-accident experiences had statistically discernible differences in speech features that suggest cognitive impairment such as reduced speech rate (P=.048) and increased response time (P=.040). Moreover, the model that used speech features could predict future accident or near-accident experiences with 81.7% accuracy, which was 6.7% higher than that using cognitive assessment data, and could achieve up to 88.3% accuracy when the model used both types of data. Conclusions Our study provides the first empirical results that suggest analysis of speech data recorded during interactions with voice assistants could help predict future accident risk for older drivers by capturing subtle impairments in cognitive function.

Automatic Assessment of Loneliness in Older Adults Using Speech Analysis on Responses to Daily Life Questions

“…One of our contributions lies in providing the first empirical evidence showing the feasibility of using the automatic analysis of speech for detecting changes due to loneliness in older adults. In addition, many recent studies have explored the use of speech data for healthcare applications for monitoring various types of health statuses in older adults, for example, for detecting cognitive impairments ( 31 , 82 – 84 ) and Alzheimer's disease ( 26 , 28 , 29 , 32 , 85 – 90 ), for detecting depression ( 38 , 91 , 92 ), and for predicting driving risks ( 30 ). Together with these previous studies, our results may help future efforts toward developing applications using speech data for automatically and simultaneously monitoring various types of health statuses including loneliness.…”

“…There is growing interest in using speech data for healthcare applications (24,25), due to the improvement in audio quality recorded by portable devices and the popularity of voice-based interaction systems such as voice assistants in smart speakers and smartphones. For example, a number of studies used phone conversations passively recorded (26,27) and others used speech responses to tasks with mobile devices (28)(29)(30)(31)(32). If automatic assessment of loneliness is possible using speech responses collected in either way (i.e., conversations with other people or speech responses collected through voice interfaces), it would greatly increase the opportunity and accessibility of assessment for early detection of loneliness.…”

Synergistic Effect of Motivation for the Elderly and Support for Going Out II: Measures to Induce Elderly Men to Go Out

“…Owing to a decline in local transportation because of population decline, the social infrastructure still relies on private cars [ 6 ]. Although the overall number of traffic accidents is declining, the number of car accidents involving elderly drivers is becoming more noticeable [ 7 , 8 ]. For this reason, people in suburban and rural areas who are too old to drive experience difficulties maintaining a full social life [ 9 ].…”