Modeling the Importance of Life Exposure Factors on Memory Performance in Diverse Older Adults - A Machine Learning Approach

Aug 5, 2026

Upload by Quinn

Many health life exposure factors (LEFs) shape cognitive decline and dementia risk, yet their relative contribution to episodic memory among diverse older adults remains uncertain. Using machine learning, the study ranks LEFs for episodic memory performance in a large U.S. cohort from KHANDLE and STAR, drawing on neuropsychological testing and questionnaires. XGBoost combined with Shapley Additive explanation values evaluates factor importance overall and within sex and ethnic strata.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Introduction

Methods

Results

Discussion

Background

Dementia prevention framework

Key findings

Model description and interpretability

Stratified effects across groups

UC Davis UC Davis Previously Published Works Title Modeling the importance of life exposure factors on memory performance in diverse older adults: A machine learning approach. Permalink [https://escholarship.org/uc/item/5wb0w4gn](https://escholarship.org/uc/item/5wb0w4gn) Journal Alzheimers and Dementia, 21(8) ISSN 1552-5260 Authors Fletcher, Evan Chanti-Ketterl, Marianne Hokett, Emily et al. Publication Date 2025-08-01 DOI 10.1002/alz.70428 Copyright Information This work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/) Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California DOI: 10.1002/alz.70428 RESEARCH ARTICLE Modeling the importance of life exposure factors on memory performance in diverse older adults: A machine learning approach Evan Fletcher1 Marianne Chanti-Ketterl2 Emily Hokett3 Yi Lor4 Umesh Venkatesan5 Ruijia Chen6 Omonigho M. Bubu7 Rachel Whitmer8 Paola Gilsanz9 Zvinka Z. Zlatar10 1 Department of Neurology, School of Medicine, University of California Davis, Davis, California, USA 2 Department of Psychiatry and Behavioral Sciences, School of Medicine, Duke University, Durham, North Carolina, USA 3 Department of Neurology, Columbia University, New York, New York, USA 4 Department of Public Health Sciences, University of California Davis, Davis, California, USA 5 Moss Rehabilitation Research Institute & Department of Rehabilitation Medicine, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, Pennsylvania, USA 6 Department of Epidemiology, Boston University School of Public Health, Boston, Massachusetts, USA 7 Departments of Psychiatry, Neurology and Population Health and NYU Neuroscience Institute, NYU Grossman School of Medicine, New York, New York, USA 8 Department of Public Health Sciences and Department of Neurology, University of California Davis, Davis, California, USA 9 Kaiser Permanente Division of Research, Oakland, California, USA 10 Department of Psychiatry, University of California San Diego, La Jolla, California, USA Correspondence Evan Fletcher, Department of Neurology, University of California, Davis, 1590 Drew Avenue, Davis, CA 95618 USA. [Email:](Email: emfletcher@ucdavis.edu)[ emfletcher@ucdavis.edu](Email: emfletcher@ucdavis.edu) Evan Fletcher and Marianne Chanti-Ketterl are co-first authors. Funding information National Institute on Aging, Grant/Award Numbers: P30 AG072972, R01 AG031563, R01 AG050782, R01 AG052132, P30AG072958 Abstract INTRODUCTION: Many health life exposure factors (LEFs) influence cognitive decline and dementia incidence, but their relative importance to episodic memory (an early indicator of cognitive decline) among diverse older adults is unclear. We used machine learning to rank LEFs for memory performance in a large and diverse US cohort. METHODS: Kaiser Healthy Aging and Diverse Life Experiences (KHANDLE) and Study of Healthy Aging in African Americans (STAR), participants underwent neuropsychological testing and answered questionnaires about multiple LEFs. XGBoost and Shapley Additive exPlanation values ranked the importance of factors influencing cross-sectional episodic memory in the full sample and by sex and ethnic group. RESULTS: Among 2245 adults (mean age: 74 years; range 54–90), age, sex, education, volunteering, income, vision, hearing, sleep, and exercise contributed to memory performance regardless of group stratification. DISCUSSION: This innovative methodology can help identify risk factors important for memory performance and guide future dementia risk reduction interventions among older adults. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any me

FAQs

What was the study’s main goal?

To determine which life exposure factors are most important for episodic memory performance among diverse older adults, using a machine learning framework.

Which datasets and participant information were used?

Participants came from the KHANDLE and STAR cohorts, with neuropsychological testing and questionnaires capturing multiple life exposure factors.

How did the researchers estimate the importance of different factors?

They used XGBoost to rank predictors and Shapley Additive explanation (SHAP) values to quantify each factor’s contribution to episodic memory performance.

What did the results show across groups?

In a combined model and stratified analyses, factors including age, sex, education, volunteering, income, vision, hearing, sleep, and exercise contributed to memory performance regardless of group stratification.

Aug 5, 2026

Upload by Quinn