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
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
- NSF-PAR ID:
- 10382241
- 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
-
-
more » « less
Abstract In the Alzheimer’s disease (AD) continuum, the prodromal state of mild cognitive impairment (MCI) precedes AD dementia and identifying MCI individuals at risk of progression is important for clinical management. Our goal was to develop generalizable multivariate models that integrate high-dimensional data (multimodal neuroimaging and cerebrospinal fluid biomarkers, genetic factors, and measures of cognitive resilience) for identification of MCI individuals who progress to AD within 3 years. Our main findings were i) we were able to build generalizable models with clinically relevant accuracy (~93%) for identifying MCI individuals who progress to AD within 3 years; ii) markers of AD pathophysiology (amyloid, tau, neuronal injury) accounted for large shares of the variance in predicting progression; iii) our methodology allowed us to discover that expression of
CR1 (complement receptor 1), an AD susceptibility gene involved in immune pathways, uniquely added independent predictive value. This work highlights the value of optimized machine learning approaches for analyzing multimodal patient information for making predictive assessments. -
Jenner, Adrianne (Ed.)With the recent approval by the FDA of the first disease-modifying drug for Alzheimer’s Disease (AD), personalized medicine will be increasingly important for appropriate management and counseling of patients with AD and those at risk. The growing availability of clinical biomarker data and data-driven computational modeling techniques provide an opportunity for new approaches to individualized AD therapeutic planning. In this paper, we develop a new mathematical model, based on AD cognitive, cerebrospinal fluid (CSF) and MRI biomarkers, to provide a personalized optimal treatment plan for individuals. This model is parameterized by biomarker data from the AD Neuroimaging Initiative (ADNI) cohort, a large multi-institutional database monitoring the natural history of subjects with AD and mild cognitive impairment (MCI). Optimal control theory is used to incorporate time-varying treatment controls and side-effects into the model, based on recent clinical trial data, to provide a personalized treatment regimen with anti-amyloid-beta therapy. In-silico treatment studies were conducted on the approved treatment, aducanumab, as well as on another promising anti-amyloid-beta therapy under evaluation, donanemab. Clinical trial simulations were conducted over both short-term (78 weeks) and long-term (10 years) periods with low-dose (6 mg/kg) and high-dose (10 mg/kg) regimens for aducanumab, and a single-dose regimen (1400 mg) for donanemab. Results confirm those of actual clinical trials showing a large and sustained effect of both aducanumab and donanemab on amyloid beta clearance. The effect on slowing cognitive decline was modest for both treatments, but greater for donanemab. This optimal treatment computational modeling framework can be applied to other single and combination treatments for both prediction and optimization, as well as incorporate new clinical trial data as it becomes available.more » « less
-
A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s diseaseEarly detection of Alzheimer’s disease (AD) during the Mild Cognitive Impairment (MCI) stage could enable effective intervention to slow down disease progression. Computer-aided diagnosis of AD relies on a sufficient amount of biomarker data. When this requirement is not fulfilled, transfer learning can be used to transfer knowledge from a source domain with more amount of labeled data than available in the desired target domain. In this study, an instance-based transfer learning framework is presented based on the gradient boosting machine (GBM). In GBM, a sequence of base learners is built, and each learner focuses on the errors (residuals) of the previous learner. In our transfer learning version of GBM (TrGB), a weighting mechanism based on the residuals of the base learners is defined for the source instances. Consequently, instances with different distribution than the target data will have a lower impact on the target learner. The proposed weighting scheme aims to transfer as much information as possible from the source domain while avoiding negative transfer. The target data in this study was obtained from the Mount Sinai dataset which is collected and processed in a collaborative 5-year project at the Mount Sinai Medical Center. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset was used as the source domain. The experimental results showed that the proposed TrGB algorithm could improve the classification accuracy by 1.5 and 4.5% for CN vs. MCI and multiclass classification, respectively, as compared to the conventional methods. Also, using the TrGB model and transferred knowledge from the CN vs. AD classification of the source domain, the average score of early MCI vs. late MCI classification improved by 5%.more » « less
-
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
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1371/journal.pone.0277322
