article · IEEE Access
Early detection of Alzheimer's disease is vital for slowing disease progression and improving patient quality of life. This research develops a multi-level stacking ensemble model designed to detect different stages of Alzheimer's disease using cognitive biomarkers from the Alzheimer's Disease Neuroimaging Initiative dataset. The architecture operates across three levels, initially training six distinct base classifiers on individual modalities, including cognitive assessment sub-scores. Subsequent levels assemble intermediate predictions using Random Forest meta-learners before combining all modalities to generate final diagnostic classifications. Particle Swarm Optimisation is employed for feature selection to isolate the most effective cognitive sub-scores. Explainable artificial intelligence techniques are also integrated to provide interpretability and build clinical trust. When evaluated, the multi-level stacking model with optimised features achieved an accuracy of 92.08 percent on two-class predictions and 90.03 percent on three-class predictions, outperforming single-modality methods and standard machine learning classifiers.
Alzheimer's disease impacts millions globally, making accurate early detection essential for administering timely care. By pairing advanced multi-level ensemble learning with explainable artificial intelligence and optimised cognitive sub-scores, this approach offers a transparent and highly accurate diagnostic aid. It demonstrates how routine cognitive test results can be better harnessed to support reliable clinical assessments without relying exclusively on invasive or complex screening procedures.
The methodology could inform clinical decision-support software for healthcare providers seeking to identify early-stage cognitive decline from standard diagnostic assessments. Because the model was developed and tested solely on retrospective data from the Alzheimer's Disease Neuroimaging Initiative dataset, it represents early-stage research. Real-world commercialisation would require extensive prospective validation, clinical trials, and regulatory clearance before integration into healthcare diagnostic pathways.
AI-generated from the published abstract. Always read the original work before citing.
Alzheimer’s disease (AD) is a progressive neurological disorder characterized by memory loss and cognitive decline, affecting millions worldwide. Early detection is crucial for effective treatment, as it can slow disease progression and improve quality of life. Machine learning has shown promise in AD detection using various medical modalities. In this paper, we propose a novel multi-level stacking model that combines heterogeneous models and modalities to predict different classes of AD. The modalities include cognitive sub-scores (e.g., clinical dementia rating – sum of boxes, Alzheimer’s disease assessment scale) from the Alzheimer’s Disease Neuroimaging Initiative dataset. In the proposed approach, in level 1, we used six base models (Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), Logistic Regression (LR), K-nearest Neighbors (KNN), and Native Bayes (NB)to train each modality (ADAS, CDR, and FQA). Then, we build stacking training that combines the outputs of each base model for the training set and staking testing that combines the outcomes of each model for the testing set. In level 2, three stacking models are produced for each modality that trains and evaluates based on the output of 6 base models based on (RF, LR, DT, SVM, KNN, and NB) are combined in training stacking for the training set and testing stacking for the testing set. Stacking training is used to train meta-learners (RF), and stacking testing is used to evaluate meta-learners (RF). Finally, in level 3, the output prediction of the stacking model from each modality (ADAS, CDR, and FQA) in the training and testing datasets is merged to build a new dataset, which is staking training and stacking testing. Training stacking is used to train the meta-learner, and the testing set is used to evaluate the meta-learner and produce the final prediction. Our research also aims to provide model explanations, ensuring efficiency, effectiveness, and trust through explainable artificial intelligence (XAI). Feature selection optimization based on Particle Swarm Optimization is used to select the most appropriate sub-scores. The proposed model shows significant potential for improving early disease diagnosis. The results demonstrate that the multi-modality approach outperforms single-modality approaches. Moreover, the proposed multi-level stacking models achieve the highest performance with selected features compared to regular ML classifiers and stacking models using full multi-modalities, achieving accuracy, precision, recall, and F1-scores of 92.08%, 92.07%, 92.08%, and 92.01% for two classes, and 90.03%, 90.19%, 90.03%, and 90.05% for three classes, respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2023.3328331
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
