Detecting Early-Stage Dementia Using Naturalistic Driving

Wotring, Brian M; Antin, Jonathan F · 2023 · ROSA P / Center for Advanced Transportation Mobility, North Carolina A&T State University

archive: archived pipeline: cataloged verified

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

Summary

This study investigates whether naturalistic driving data can identify older adults with pre-mild cognitive impairment (pre-MCI), a stage of cognitive decline preceding formal diagnosis. Motivated by the growing aging population and the critical role of driving in maintaining independence, the research aims to determine if driving behaviors and safety metrics serve as early indicators of cognitive decline. The study specifically examines how pre-MCI status influences driving patterns and the utilization of Advanced Driver Assistance Systems (ADAS), such as adaptive cruise control (ACC) and lane centering (LC). The researchers conducted two analyses using naturalistic driving data. Analysis 1 utilized data from 15 participants (7 pre-MCI, 8 cognitively normal controls) recruited in Virginia, Texas, and the Washington D.C. area. Participants were screened using subjective memory questions and the Self-Administered Gerocognitive Exam (SAGE). Vehicles were equipped with the Virginia Tech Transportation Institute Data Acquisition System (DAS) to collect kinematic data, video, and ADAS status. Analysis 2 incorporated data from the Strategic Highway Research Program (SHRP 2) to compare mobility and safety outcomes between drivers with and without Level 2 automation features. Safety-critical events, including crashes, near-crashes, and crash-relevant conflicts, were identified via accelerometer thresholds and validated through video review. Analysis 1 revealed low usage rates for ADAS; only three of seven participants with lane centering ever used it, and six of 14 with ACC used it. Lane departure warnings were more common than forward collision warnings, but no significant differences were found between pre-MCI and control groups. Analysis 2 found statistically reliable differences in mobility metrics for pre-MCI drivers using Level 2 vehicles. These individuals made fewer trips per day (3.59) compared to those without Level 2 features (4.66), suggesting self-regulatory behavior. However, they tended to drive for longer durations (13.34 minutes vs. 11.69 minutes) when Level 2 features were available. Safety-critical event rates showed a trend toward significance but did not reach statistical reliability in this dataset. The findings suggest that driving safety performance metrics may eventually serve as an early warning system for pre-MCI. The study indicates that pre-MCI drivers may exhibit modest differences in mobility, particularly when driving vehicles with Level 2 automation, potentially due to self-restriction of driving frequency despite longer trip durations. The authors conclude that while current ADAS utilization is low, these technologies may support independent mobility for those with early cognitive decline. Future research with larger datasets is needed to validate safety-critical events as a reliable diagnostic marker.

Key finding

Older adults with pre-mild cognitive impairment demonstrated modest differences in mobility metrics, specifically fewer daily trips and longer trip durations when driving vehicles equipped with Level 2 automation, compared to cognitively normal individuals.

Methodology

naturalistic

Sample size: 15

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 bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

StageOutcomeToolModelPromptAttemptsCompleted
discover success rosap 2 2026-05-23
archive success 1 2026-05-23
extract success cached 2 2026-06-10
clean success 1 2026-06-01
chunk success 1 2026-06-01
embed success 1 2026-06-02
enrich success 1 2026-05-23
promote success 1 2026-05-23
summarize success llm qwen3.6-27b-prismaquant summ-v5 3 2026-06-10
tag success vector_similarity 19 2026-06-11
verify partial 2 2026-06-10

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.

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).