WATCH-SS: Warning Assessment and Alerting Tool for Cognitive Health from Spontaneous Speech

WATCH-SS is a trustworthy and interpretable modular framework for detecting cognitive impairment from a patient's speech sample. The manuscript for WATCH-SS is currently under review. A preprint is available here.

Contents

|- data/							# Code to load and preprocess ADReSS/OBSERVER datasets
|- detectors/						# Code for the detectors for CI indicators
|- notebooks/						# Jupyter notebooks for detector development and experiments
|- fig/								# Figure files for Markdown files
|- utils.py							# Code for supporting functions
|- compute_init.sh					# Microsoft Azure Databricks compute initialization script
|- requirements.txt					# List of Python dependencies for WATCH-SS
|- supplementary_material.pdf		# PDF version of supplementary material for WATCH-SS manuscript
|- supplementary_material.md		# Markdown version of supplementary material for WATCH-SS manuscript
|- README.md 						# This file

Citation

If you use the code or findings from this work in your research, please cite our paper:

@article {pugh2025watchss,
	author = {Pugh, Sydney and Hill, Matthew and Hwang, Sy and Wu, Rachel and Jang, Kuk and Iannone, Stacy L and O{\textquoteright}Connor, Karen and O{\textquoteright}Brien, Kyra and Eaton, Eric and Johnson, Kevin B},
	title = {WATCH-SS: A Trustworthy and Explainable Modular Framework for Detecting Cognitive Impairment from Spontaneous Speech},
	elocation-id = {2025.08.06.25333047},
	year = {2025},
	doi = {10.1101/2025.08.06.25333047},
	publisher = {Cold Spring Harbor Laboratory Press},
	URL = {https://www.medrxiv.org/content/early/2025/08/08/2025.08.06.25333047},
	eprint = {https://www.medrxiv.org/content/early/2025/08/08/2025.08.06.25333047.full.pdf},
	journal = {medRxiv}
}