LiveDrive AI: A Pilot Study of a Machine Learning-Powered Diagnostic System for Real-Time, Non-Invasive Detection of...

Area of Science:

• Neurology
• Artificial Intelligence
• Biomedical Engineering

Background:

• Alzheimer's disease (AD) affects over 55 million globally, necessitating early detection.
• Mild cognitive impairment (MCI) is an early indicator of AD, but current diagnostic biomarkers are limited.
• Non-invasive and accessible tools are needed for early MCI detection.

Purpose of the Study:

• To explore driving performance as a novel, non-invasive biomarker for MCI detection.
• To analyze the predictive capacity of driving patterns in indicating cognitive decline.
• To develop scalable, real-world solutions for early AD diagnosis.

Main Methods:

• Utilized the LiveDrive AI system with multimodal sensing (MMS).
• Analyzed driving performance assessment strategies and patterns.
• Employed machine learning models trained on an expert-annotated dataset to detect MCI status.

Main Results:

• Demonstrated the feasibility of using driving features (velocity, acceleration during turning) as indicators of cognitive decline.
• Showcased the potential for integration into smartphone or car applications for real-time monitoring.
• Validated the use of driving performance for MCI detection.

Conclusions:

• Driving performance offers a promising, non-invasive approach for early AD and MCI detection.
• This method enables continuous cognitive health monitoring in real-world settings.
• The findings represent a significant step towards improved patient outcomes and AD disease management.