Associating transportation planning-related measures with Mild Cognitive Impairment

2025-04-12

AI Summary

This study investigates the association between mild cognitive impairment (MCI) and older adults’ driving-related mobility behavior to enhance road safety. Methodologically, it innovatively quantifies the transportation-planning concept of “life-space”—capturing daily travel patterns (e.g., frequency of home-based, medical, and social trips)—using Geohash encoding, and integrates these features into interpretable machine learning models (C5.0 decision tree, random forest, and SVM). A key contribution is the first systematic incorporation of life-space variables for early MCI detection, prioritizing clinical interpretability, reduced false-negative rates, and public safety applications. Experimental results demonstrate that the C5.0 model achieves a median recall of 74%, significantly outperforming baseline methods, thereby validating the robust predictive power of mobility-derived behavioral features for MCI. This work establishes a novel, non-invasive, behavior-driven paradigm for cognitive risk screening in aging populations.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Understanding the relationship between mild cognitive impairment and driving behavior is essential to improve road safety, especially among older adults. In this study, we computed certain variables that reflect daily driving habits, such as trips to specific locations (e.g., home, work, medical, social, and errands) of older drivers in Nebraska using geohashing. The computed variables were then analyzed using a two-fold approach involving data visualization and machine learning models (C5.0, Random Forest, Support Vector Machines) to investigate the efficiency of the computed variables in predicting whether a driver is cognitively impaired or unimpaired. The C5.0 model demonstrated robust and stable performance with a median recall of 74%, indicating that our methodology was able to identify cognitive impairment in drivers 74% of the time correctly. This highlights our model's effectiveness in minimizing false negatives which is an important consideration given the cost of missing impaired drivers could be potentially high. Our findings highlight the potential of life space variables in understanding and predicting cognitive decline, offering avenues for early intervention and tailored support for affected individuals.

Problem

• Investigates link between driving habits and cognitive impairment in elderly
• Develops model to predict cognitive impairment using driving behavior data
• Aims to enhance road safety by reducing false negative diagnoses

Innovation

• Geohashing to track daily driving habits
• Machine learning models for cognitive impairment prediction
• C5.0 model achieves 74% recall rate