Study protocol for “In-vehicle sensors to detect changes in cognition of older drivers”

Tappen, Ruth M.; Newman, David; Rosselli, Mónica; Jang, Jinwoo; Furht, Borko; Yang, KwangSoo; Ghoreishi, Seyedeh Gol Ara; Zhai, Jiannan; Conniff, Joshua; Jan, Muhammad Tanveer; Moshfeghi, Sonia; Panday, Somi; Jackson, Kelley L.; Adonis-Rizzo, Marie · 2023 · BMC Geriatrics

DOI: 10.1186/s12877-023-04550-5

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This document outlines the study protocol for a naturalistic longitudinal investigation designed to determine if in-vehicle sensors can detect early cognitive decline in older drivers. The research is motivated by the high prevalence of mild cognitive impairment (MCI) and dementia among adults aged 65 and older, many of whom remain unaware of their condition while continuing to drive. Since cognitive deficits often manifest in driving behavior years before clinical diagnosis, the study aims to develop an unobtrusive, low-cost monitoring system that provides early warnings of cognitive change, addressing the limitations of current screening methods that reach only a small fraction of at-risk individuals. The study employs a mixed-methods design involving 460 participants aged 65 and older with valid driver’s licenses and baseline cognitive scores indicating no significant impairment. Over a three-year period, participants will undergo quarterly cognitive assessments and have sensor data downloaded from their vehicles. The sensor system includes a telematics unit collecting GPS, inertial measurement unit (IMU), and On-Board Diagnostic data, as well as a video unit with driver-facing and forward-facing cameras equipped with AI for real-time analysis of behaviors such as distraction, lane departure, and traffic sign detection. Cognitive status is evaluated using a comprehensive battery including the Montreal Cognitive Assessment, Trail Making Test, Stroop-Color Word Test, and various measures of executive function, memory, and visual attention. Clinical diagnoses are determined through a consensus panel combining neuropsychological results and clinical ratings. The analysis plan involves normalizing sensor data and integrating external factors like weather and traffic conditions to identify critical features. The researchers will compare traditional prediction modeling with Recurrent Neural Networks to generate Driver Behavior Indices (DBIs) that are specific to age, gender, and vehicle type. These DBIs will be used to classify drivers and detect transitions from unimpaired status to MCI or dementia. The study also evaluates the acceptability of the sensor system regarding obtrusiveness and driver distraction. The significance of this work lies in its potential to establish a scalable method for monitoring cognitive health in older drivers through existing vehicle technologies. By linking continuous driving data with rigorous cognitive testing, the study seeks to identify specific behavioral anomalies indicative of cognitive decline. Successful validation of this approach could lead to widespread implementation of in-vehicle sensing systems, offering a proactive tool for identifying cognitive impairment earlier than current clinical practices allow, thereby enhancing road safety and facilitating timely medical intervention for millions of older drivers.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via author_sweep_intake on 2026-05-27.

StageOutcomeToolModelPromptAttemptsCompleted
discover success author_sweep 2 2026-05-27
archive success canonical_url 1 2026-06-04
extract success cached 3 2026-06-15
clean success clean 1 2026-06-04
chunk success chunk 1 2026-06-04
embed success embed Qwen/Qwen3-Embedding-8B 1 2026-06-04
enrich success semantic_scholar 2 2026-06-04
promote success 1 2026-06-04
summarize success llm qwen3.6-27b-prismaquant summ-v5 2 2026-06-15
tag success vector_similarity 15 2026-06-11
verify success 1 2026-06-15

Summary generated by qwen3.6-27b-prismaquant on 2026-06-15; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).