WATCH-SS: Developing a Trustworthy and Explainable Modular Framework for Detecting Cognitive Impairment from...

Area of Science:

• Neurology
• Computational Linguistics
• Artificial Intelligence in Medicine

Background:

• Early detection of cognitive impairment (CI) is vital for managing Alzheimer's disease and related dementias.
• Current screening methods may lack accessibility or efficiency for widespread primary care use.

Purpose of the Study:

• To introduce the Warning Assessment and Alerting Tool for Cognitive Health from Spontaneous Speech (WATCH-SS).
• To develop a modular, explainable framework for detecting CI using speech analysis.

Main Methods:

• WATCH-SS employs a three-stage framework analyzing linguistic and acoustic speech features.
• It incorporates multiple detector approaches, from real-time efficient to high-accuracy offline methods.
• A predictive model classifies CI based on aggregated, clinically interpretable summary features.

Main Results:

• The WATCH-SS framework demonstrated strong predictive performance on the DementiaBank ADReSS dataset.
• Achieved an Area Under the Curve (AUC) of 80% on the test set.
• The modular, feature-based approach provided a transparent diagnostic profile.

Conclusions:

• WATCH-SS shows potential as a trustworthy and clinically usable screening tool for primary care settings.
• This speech-based analysis represents a significant advancement in early CI detection.
• The explainable nature of the tool supports clinical adoption and patient trust.