NCASR-driven spectral feature recalibration for early Alzheimer's disease detection

Alzheimer's disease (AD) is a progressive form of neurodegenerative disorder causing impairments in memory functions and cognitive abilities. Therefore, early diagnosis of AD or Mild Cognitive Impairment (MCI) is an essential step toward the successful treatment of patients. Many of the existing classifiers for Alzheimer's disease depend heavily on utilizing deep learning algorithms along with MRI image processing to identify patterns related to the dementia disorder. Nevertheless, many state-of-the-art methods primarily depend on imaging-derived features and do not effectively incorporate neurocognitive accuracy, relying predominantly on imaging-based features. This study proposes a Neuro Cognitive Adaptive Spectral Recalibration Convolutional Neural Network (NCASR-CNN) Framework as a technique for detecting Alzheimer's disease with the use of OASIS MRI datasets. The proposed NCASR-CNN model incorporates the clinical variables age and Mini-Mental State Examination (MMSE) to enhance the discriminative capability of extracted features. Final classification was performed using a hybrid stacking ensemble comprising a Multi-Layer Perceptron (MLP), LightGBM, XGBoost, and Logistic Regression, using three diagnostic categories: Alzheimer's disease, Mild Cognitive Impairment, and Cognitively Normal (CN) subjects. The proposed framework achieved an overall ROC–AUC of 99.70% and a classification accuracy of 94.38%, while also attaining high precision, recall, and F1-score across all diagnostic categories. The results show that integration of Reinforcement Learning (RL) to choose slices, adaptive parameter optimisation, combining deep features, and hybrid ensemble learning work well-together for accurately classifying Alzheimer's disease.

Authors

Institutions

Publication Details

Journal
Frontiers in Artificial Intelligence
Published
2026-11-18
DOI
https://doi.org/10.3389/frai.2026.1926367
Primary Topic
Dementia and Cognitive Impairment Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

NCASR-driven spectral feature recalibration for early Alzheimer's disease detection

Swasthika Bhaskar, Vanitha Mohanraj
2 links
Frontiers in Artificial Intelligence
Dementia and Cognitive Impairment Research
article

NCASR-driven spectral feature recalibration for early Alzheimer's disease detection

Swasthika Bhaskar, Vanitha Mohanraj
article en

Abstract

Alzheimer's disease (AD) is a progressive form of neurodegenerative disorder causing impairments in memory functions and cognitive abilities. Therefore, early diagnosis of AD or Mild Cognitive Impairment (MCI) is an essential step toward the successful treatment of patients. Many of the existing classifiers for Alzheimer's disease depend heavily on utilizing deep learning algorithms along with MRI image processing to identify patterns related to the dementia disorder. Nevertheless, many state-of-the-art methods primarily depend on imaging-derived features and do not effectively incorporate neurocognitive accuracy, relying predominantly on imaging-based features. This study proposes a Neuro Cognitive Adaptive Spectral Recalibration Convolutional Neural Network (NCASR-CNN) Framework as a technique for detecting Alzheimer's disease with the use of OASIS MRI datasets. The proposed NCASR-CNN model incorporates the clinical variables age and Mini-Mental State Examination (MMSE) to enhance the discriminative capability of extracted features. Final classification was performed using a hybrid stacking ensemble comprising a Multi-Layer Perceptron (MLP), LightGBM, XGBoost, and Logistic Regression, using three diagnostic categories: Alzheimer's disease, Mild Cognitive Impairment, and Cognitively Normal (CN) subjects. The proposed framework achieved an overall ROC–AUC of 99.70% and a classification accuracy of 94.38%, while also attaining high precision, recall, and F1-score across all diagnostic categories. The results show that integration of Reinforcement Learning (RL) to choose slices, adaptive parameter optimisation, combining deep features, and hybrid ensemble learning work well-together for accurately classifying Alzheimer's disease.

Frontiers in Artificial IntelligenceVol. 9
Vellore Institute of Technology University (IN)
Good health and well-being
Dementia and Cognitive Impairment Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon