Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Exploring the Hierarchical Influence of Cognitive Functions for Alzheimer’s Disease in a Cohort Study
Huitong Ding;
Ning An;
Rhoda Au;
Sherral Devine;
Sanford H. Auerbach;
Joseph Massaro;
Prajakta Joshi;
Xue Liu;
Yulin Liu;
Elizabeth Mahon;
Ting F. A. Ang;
Honghuang Lin
ABSTRACT
Background:
While some neuropsychological tests are considered more central for the diagnosis of Alzheimer’s disease (AD), there is a lack of understanding about the interaction of scores across different cognitive functions.
Objective:
Demonstrating a global view of hierarchical probabilistic dependencies between neuropsychological tests and likelihood of cognitive impairment could assist physicians in recognizing AD precursors.
Methods:
Based on 4,512 neuropsychological (NP) test scores from 2,091 participants from the Framingham Heart Study, we proposed heterogeneous cognitive Bayesian networks using a clustering-based discretization method to provide an in-depth understanding of interrelated neuropsychological tests and cognitive status.
Results:
We developed an AD probabilistic diagnostic system for subjects that exhibit more heterogeneous profiles and/or are missing responses from some NP tests. After stratification of subjects by sex or education, the sensitivity of probabilistic inferences of AD was improved from 63% to 90%, which illustrates the importance of accurate patient stratification for AD precision medicine.
Conclusions:
Our study is the first attempt to utilize probabilistic machine learning framework to explore the hierarchical interaction pattern of various cognitive function and contribute specific targets for AD intervention based on cognitively heterogeneous profiles.
Citation
Please cite as:
Ding H, An N, Au R, Devine S, Auerbach SH, Massaro J, Joshi P, Liu X, Liu Y, Mahon E, Ang TFA, Lin H
Exploring the Hierarchical Influence of Cognitive Functions for Alzheimer Disease: The Framingham Heart Study