AUTHOR=Yao Lihua , Shono Yusuke , Nowinski Cindy , Dworak Elizabeth M. , Kaat Aaron , Chen Shirley , Lovett Rebecca , Ho Emily , Curtis Laura , Wolf Michael , Gershon Richard , Benavente Julia Yoshino 

TITLE=Prediction of cognitive impairment using higher order item response theory and machine learning models

JOURNAL=Frontiers in Psychiatry

VOLUME=Volume 14 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2023.1297952

DOI=10.3389/fpsyt.2023.1297952

ISSN=1664-0640

ABSTRACT=Timely detection of cognitive impairment (CI) is critical for the well-being of elderly individuals. The MyCog assessment employs two validated iPad-based measures from the NIH Toolbox for the Assessment of National Institute of Neurological Disorders and Stroke (NINDS) and National Institute on Aging (NIA). These measures assess pivotal cognitive domains: Picture Sequence Memory (PSM) for episodic memory and Dimensional Change Card Sort (DCCS) for cognitive flexibility. The study involved 86 patients, and explored diverse machine learning models to enhance CI prediction. This encompassed traditional classifiers and neural-network-based methods. After 100 Bootstrap replications, the Random Forest model stood out, delivering compelling results: Precision at 0.803, Recall at