Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 12, 2026International Journal of Imaging Systems and Technology

Predicting Mild Cognitive Impairment to Alzheimer's Disease Progression by Explainable Multi‐Modal Framework Using Deep and Machine Learning Hybrid Model

View Full Paper
Ask AI
Bookmark
Share

Authors

SZSoheil ZareiInstitute for Cognitive Science StudiesMSMohsen SaffarIran University of Science and TechnologyPHPeyman Hassani‐AbharianInstitute for Cognitive Science Studies

Discussion

Loading...

Member takes

Implication

Randomized trial predicts progression from mild cognitive impairment to Alzheimer's disease, suggesting early intervention opportunities.

Key Points

  • This research aims to accurately predict the transition from mild cognitive impairment (MCI) to Alzheimer's disease (AD) using a novel framework.
  • Utilized a hybrid deep learning and machine learning model integrating structural MRI features and neurocognitive assessments.
  • Extracted spatial features from MRI scans using a 3D convolutional neural network.
  • Employed various machine learning classifiers including RF, LR, SVM, and GBM for prediction, with model interpretability evaluated via SHAP.
  • Achieved a classification accuracy of 88.11% with an area under the curve (AUC) of 0.889.
  • The GBM classifier outperformed other models, demonstrating effective integration of imaging and clinical features.
  • Identified critical biomarkers influencing prediction outcomes with strong generalizability across different clinical sites.

Cite This Study

Zarei et al. (2026) studied this question.

synapsesocial.com/papers/6a2ba4a18101cf8926f02fc8https://doi.org/10.1002/ima.70390
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Constructing brain functional networks with adaptive manifold regularization for early mild cognitive impairment2024 · 2 citations
  2. 2Greedy function approximation: A gradient boosting machine.2001 · 30,800 citations
  3. 3Rapid discrimination and ratio quantification of mixed antibiotics in aqueous solution through integrative analysis of SERS spectra via CNN combined with NN-EN model2024 · 58 citations
  4. 4Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative2023 · 84 citations
  5. 5Utility of Combinations of Biomarkers, Cognitive Markers, and Risk Factors to Predict Conversion From Mild Cognitive Impairment to Alzheimer Disease in Patients in the Alzheimer's Disease Neuroimaging Initiative2011 · 347 citations