skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Machine learning based multi-modal prediction of future decline toward Alzheimer’s disease: An empirical study
Alzheimer’s disease (AD) is a neurodegenerative condition that progresses over decades. Early detection of individuals at high risk of future progression toward AD is likely to be of critical significance for the successful treatment and/or prevention of this devastating disease. In this paper, we present an empirical study to characterize how predictable an individual subjects’ future AD trajectory is, several years in advance, based on rich multi-modal data, and using modern deep learning methods. Crucially, the machine learning strategy we propose can handle different future time horizons and can be trained with heterogeneous data that exhibit missingness and non-uniform follow-up visit times. Our experiments demonstrate that our strategy yields predictions that are more accurate than a model trained on a single time horizon (e.g. 3 years), which is common practice in prior literature. We also provide a comparison between linear and nonlinear models, verifying the well-established insight that the latter can offer a boost in performance. Our results also confirm that predicting future decline for cognitively normal (CN) individuals is more challenging than for individuals with mild cognitive impairment (MCI). Intriguingly, however, we discover that prediction accuracy decreases with increasing time horizon for CN subjects, but the trend is in the opposite direction for MCI subjects. Additionally, we quantify the contribution of different data types in prediction, which yields novel insights into the utility of different biomarkers. We find that molecular biomarkers are not as helpful for CN individuals as they are for MCI individuals, whereas magnetic resonance imaging biomarkers (hippocampus volume, specifically) offer a significant boost in prediction accuracy for CN individuals. Finally, we show how our model’s prediction reveals the evolution of individual-level progression risk over a five-year time horizon. Our code is available at https://github.com/batuhankmkaraman/mlbasedad .  more » « less
Award ID(s):
1748377 1707312
PAR ID:
10382241
Author(s) / Creator(s):
; ;
Editor(s):
Thung, Kim Han
Date Published:
Journal Name:
PLOS ONE
Volume:
17
Issue:
11
ISSN:
1932-6203
Page Range / eLocation ID:
e0277322
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al (, Applied Neuropsychology: Adult)
    Objective: The interaction of ethnicity, progression of cognitive impairment, and neuroimaging biomarkers of Alzheimer’s Disease remains unclear. We investigated the stability in cognitive status classification (cognitively normal [CN] and mild cognitive impairment [MCI]) of 209 participants (124 Hispanics/Latinos and 85 European Americans). Methods: Biomarkers (structural MRI and amyloid PET scans) were compared between Hispanic/Latino and European American individuals who presented a change in cognitive diagnosis during the second or third follow-up and those who remained stable over time. Results: There were no significant differences in biomarkers between ethnic groups in any of the diagnostic categories. The frequency of CN and MCI participants who were progressors (progressed to a more severe cognitive diagnosis at follow-up) and non-progressors (either stable through follow-ups or unstable [progressed but later reverted to a diagnosis of CN]) did not significantly differ across ethnic groups. Progressors had greater atrophy in the hippocampus (HP) and entorhinal cortex (ERC) at baseline compared to unstable non-progressors (reverters) for both ethnic groups, and more significant ERC atrophy was observed among progressors of the Hispanic/Latino group. For European Americans diagnosed with MCI, there were 60% more progressors than reverters (reverted from MCI to CN), while among Hispanics/Latinos with MCI, there were 7% more reverters than progressors. Binomial logistic regressions predicting progression, including brain biomarkers, MMSE, and ethnicity, demonstrated that only MMSE was a predictor for CN participants at baseline. However, for MCI participants at baseline, HP atrophy, ERC atrophy, and MMSE predicted progression. 
    more » « less
  2. ; ; ; (, Biometrics)
    Abstract It has become consensus that mild cognitive impairment (MCI), one of the early symptoms onset of Alzheimer’s disease (AD), may appear 10 or more years after the emergence of neuropathological abnormalities. Therefore, understanding the progression of AD biomarkers and uncovering when brain alterations begin in the preclinical stage, while patients are still cognitively normal, are crucial for effective early detection and therapeutic development. In this paper, we develop a Bayesian semiparametric framework that jointly models the longitudinal trajectory of the AD biomarker with a changepoint relative to the occurrence of symptoms onset, which is subject to left truncation and right censoring, in a heterogeneous population. Furthermore, unlike most existing methods assuming that everyone in the considered population will eventually develop the disease, our approach accounts for the possibility that some individuals may never experience MCI or AD, even after a long follow-up time. We evaluate the proposed model through simulation studies and demonstrate its clinical utility by examining an important AD biomarker, ptau181, using a dataset from the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD) study. 
    more » « less
  3. ; ; ; ; ; ; (, Alzheimers dementia)
    INTRODUCTION: It is unclear whether aggregated plasma protein risk scores (PPRS) could be useful to predict the risks of mild cognitive impairment (MCI) and Alzheimer’s disease (AD). METHODS: The Cox proportional hazard model with the LASSO penalty was used to build the PPRS for MCI and AD in 1,515 Framingham Heart Study Generation2 with 1,128 proteins measured in plasma at exam 5 [cognitive normal (CN)=1,258, MCI=129, AD=128]. RESULTS: MCI PPRS had a hazard ratio (HR) of 6.97[5.34,9.12], with a discriminating power (C-index=82.52%). AD PPRS had an HR of 5.74[4.67,7.05] (C-index=88.15%). Both PPRSs were also significantly associated with cognitive changes, brain-atrophy, and plasma AD biomarkers. Proteins in the MCI and AD PPRSs were enriched in several pathways related to leukocyte, chemotaxis, immunity, inflammation, and cellular migration. DISCUSSION: This study suggests that PPRS serve well to predict the risk of developing MCI and AD as well as cognitive changes and AD related pathogenesis in the brain. 
    more » « less
  4. ; ; ; ; ; ; (, Journal of Alzheimer's Disease)
    Background: Biomarkers for Alzheimer’s disease (AD) are crucial for early diagnosis and treatment monitoring once disease modifying therapies become available. Objective: This study aims to quantify the forward magnetization transfer rate (kfor) map from brain tissue water to macromolecular protons and use it to identify the brain regions with abnormal kfor in AD and AD progression. Methods: From the Cardiovascular Health Study (CHS) cognition study, magnetization transfer imaging (MTI) was acquired at baseline from 63 participants, including 20 normal controls (NC), 18 with mild cognitive impairment (MCI), and 25 AD subjects. Of those, 53 participants completed a follow-up MRI scan and were divided into four groups: 15 stable NC, 12 NC-to-MCI, 12 stable MCI, and 14 MCI/AD-to-AD subjects. kfor maps were compared across NC, MCI, and AD groups at baseline for the cross-sectional study and across four longitudinal groups for the longitudinal study. Results: We found a lower kfor in the frontal gray matter (GM), parietal GM, frontal corona radiata (CR) white matter (WM) tracts, frontal and parietal superior longitudinal fasciculus (SLF) WM tracts in AD relative to both NC and MCI. Further, we observed progressive decreases of kfor in the frontal GM, parietal GM, frontal and parietal CR WM tracts, and parietal SLF WM tracts in stable MCI. In the parietal GM, parietal CR WM tracts, and parietal SLF WM tracts, we found trend differences between MCI/AD-to-AD and stable NC. Conclusion: Forward magnetization transfer rate is a promising biomarker for AD diagnosis and progression. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al (, Cognitive Computation)
    Abstract Alzheimer’s disease (AD) is a neurogenerative condition characterized by sharp cognitive decline with no confirmed effective treatment or cure. This makes it critically important to identify the symptoms of Alzheimer’s disease in its early stages before significant cognitive deterioration has taken hold and even before any brain morphology and neuropathology are noticeable. In this study, five different multimodal deep neural networks (MDNN), with different architectures, in search of an optimal model for predicting the cognitive test scores for the Mini-Mental State Examination (MMSE) and the modified Alzheimer’s Disease Assessment Scale (ADAS-CoG13) over a span of 60 months (5 years). The multimodal data utilized to train and test the proposed models were obtained from the Alzheimer’s Disease Neuroimaging Initiative study and includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from the neuropsychological tests (Cog). The models developed herein delve into two main issues: (1) application merits of single-task vs. multitask for predicting future cognitive scores and (2) whether time-varying input data are better suited than specific timepoints for optimizing prediction results. This model yields a high of 90.27% (SD = 1.36) prediction accuracy (correlation) at 6 months after the initial visit to a lower 79.91% (SD = 8.84) prediction accuracy at 60 months. The analysis provided is comprehensive as it determines the predictions at all other timepoints and all MDNN models include converters in the CN and MCI groups (CNc, MCIc) and all the unstable groups in the CN and MCI groups (CNun and MCIun) that reverted to CN from MCI and to MCI from AD, so as not to bias the results. The results show that the best performance is achieved by a multimodal combined single-task long short-term memory (LSTM) regressor with an input sequence length of 2 data points (2 visits, 6 months apart) augmented with a pretrained Neural Network Estimator to fill in for the missing values. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email