Related Experiment Video
Updated: Jul 25, 2025
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
PPAD: a deep learning architecture to predict progression of Alzheimer's disease
Mohammad Al Olaimat1, Jared Martinez1, Fahad Saeed2
1Department of Computer Science and Engineering, University of North Texas, Denton, TX, United States.
Motivation:
Alzheimer's disease (AD) is a neurodegenerative disease that affects millions of people worldwide. Mild cognitive impairment (MCI) is an intermediary stage between cognitively normal state and AD. Not all people who have MCI convert to AD. The diagnosis of AD is made after significant symptoms of dementia such as short-term memory loss are already present. Since AD is currently an irreversible disease, diagnosis at the onset of the disease brings a huge burden on patients, their caregivers, and the healthcare sector. Thus, there is a crucial need to develop methods for the early prediction AD for patients who have MCI. Recurrent neural networks (RNN) have been successfully used to handle electronic health records (EHR) for predicting conversion from MCI to AD. However, RNN ignores irregular time intervals between successive events which occurs common in electronic health record data. In this study, we propose two deep learning architectures based on RNN, namely Predicting Progression of Alzheimer's Disease (PPAD) and PPAD-Autoencoder. PPAD and PPAD-Autoencoder are designed for early predicting conversion from MCI to AD at the next visit and multiple visits ahead for patients, respectively. To minimize the effect of the irregular time intervals between visits, we propose using age in each visit as an indicator of time change between successive visits.
Results:
Our experimental results conducted on Alzheimer's Disease Neuroimaging Initiative and National Alzheimer's Coordinating Center datasets showed that our proposed models outperformed all baseline models for most prediction scenarios in terms of F2 and sensitivity. We also observed that the age feature was one of top features and was able to address irregular time interval problem.
Availability And Implementation:
https://github.com/bozdaglab/PPAD.
Insights
Predicting Alzheimer's disease (AD) progression from mild cognitive impairment (MCI) is crucial. New deep learning models, PPAD and PPAD-Autoencoder, effectively predict AD conversion using electronic health records, outperforming existing methods.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Medical Informatics
Background:
- Alzheimer's disease (AD) is a progressive neurodegenerative disorder impacting millions globally.
- Mild cognitive impairment (MCI) is a transitional stage; not all individuals with MCI develop AD.
- Current AD diagnosis occurs after significant dementia symptoms emerge, posing a burden due to the disease's irreversible nature.
Purpose of the Study:
- To develop advanced deep learning models for early prediction of AD conversion in MCI patients.
- To address the challenge of irregular time intervals in electronic health record (EHR) data for time-series analysis.
- To enable prediction of AD conversion at both the next clinical visit and multiple visits ahead.
Main Methods:
- Proposed two recurrent neural network (RNN)-based deep learning architectures: Predicting Progression of Alzheimer's Disease (PPAD) and PPAD-Autoencoder.
- Utilized age at each visit as a temporal feature to mitigate the impact of irregular time intervals in EHR data.
- Evaluated models on the Alzheimer's Disease Neuroimaging Initiative (ADNI) and National Alzheimer's Coordinating Center (NACC) datasets.
Main Results:
- The proposed PPAD and PPAD-Autoencoder models demonstrated superior performance compared to baseline models across various prediction scenarios.
- Key performance metrics included F2 score and sensitivity, where the models showed significant improvements.
- The inclusion of age as a feature was identified as critical for addressing the irregular time interval issue in EHR data.
Conclusions:
- The developed deep learning models (PPAD and PPAD-Autoencoder) offer a promising approach for the early prediction of Alzheimer's disease progression in MCI patients.
- Incorporating age as a temporal indicator effectively handles irregular time intervals in EHR data, a common challenge in clinical time-series analysis.
- These findings highlight the potential of AI-driven tools in improving early diagnosis and management of Alzheimer's disease.
Related Concept Videos
01:26Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
01:22Alzheimer's Disease: Treatment
01:30Dementia
The progression of dementia is generally gradual....