Format

Send to

Choose Destination
J Alzheimers Dis. 2019;70(1):277-286. doi: 10.3233/JAD-190165.

Episodic-Memory Performance in Machine Learning Modeling for Predicting Cognitive Health Status Classification.

Author information

1
SIVOTEC Analytics, Boca Raton, FL, USA.
2
Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA.
3
HAPPYneuron, S.A.S., Lyon, France.
4
MemTrax, LLC., Redwood City, CA, USA.
5
War-Related Illness and Injury Study Center, VA Palo Alto Health Care System and Department of Psychiatry & Behavioral Sciences, Stanford University School of Medicine, Palo Alto, CA, USA.

Abstract

BACKGROUND:

Memory dysfunction is characteristic of aging and often attributed to Alzheimer's disease (AD). An easily administered tool for preliminary assessment of memory function and early AD detection would be integral in improving patient management.

OBJECTIVE:

Our primary aim was to utilize machine learning in determining initial viable models to serve as complementary instruments in demonstrating efficacy of the MemTrax online Continuous Recognition Tasks (M-CRT) test for episodic-memory screening and assessing cognitive impairment.

METHODS:

We used an existing dataset subset (n = 18,395) of demographic information, general health screening questions (addressing memory, sleep quality, medications, and medical conditions affecting thinking), and test results from a convenience sample of adults who took the M-CRT test. M-CRT performance and participant features were used as independent attributes: true positive/negative, percent responses/correct, response time, age, sex, and recent alcohol consumption. For predictive modeling, we used demographic information and test scores to predict binary classification of the health-related questions (yes/no) and general health status (healthy/unhealthy), based on the screening questions.

RESULTS:

ANOVA revealed significant differences among HealthQScore groups for response time true positive (p = 0.000) and true positive (p = 0.020), but none for true negative (p = 0.0551). Both % responses and % correct had significant differences (p = 0.026 and p = 0.037, respectively). Logistic regression was generally the top-performing learner with moderately robust prediction performance (AUC) for HealthQScore (0.648-0.680) and selected general health questions (0.713-0.769).

CONCLUSION:

Our novel application of supervised machine learning and predictive modeling helps to demonstrate and validate cross-sectional utility of MemTrax in assessing early-stage cognitive impairment and general screening for AD.

KEYWORDS:

Aging; Alzheimer’s disease; dementia; mass screening

Supplemental Content

Full text links

Icon for IOS Press Icon for PubMed Central
Loading ...
Support Center