Novel hybrid intelligence model for early Alzheimer's diagnosis utilizing multimodal biomarker fusion

Abstract

One of the significant causes of dementia and a leading peril to global public health is Alzheimer's disease (AD), which calls for early and accurate diagnosis. The paper proposes a novel hybrid machine learning framework that integrates Gradient Boosting Machine (GBM) and Deep Neural Networks (DNN) for predicting Alzheimer's disease from multimodal biomarkers. The database comprises 35 demographic, behavioral, and clinical features. Feature selection procedures produced key predicting variables (i.e., MMSE scores, performance in Activities of Daily Living (ADL), cholesterol level, and behavior problems). A hybrid model was created by combining individual models, and it proved to be the most effective compared to particular models, achieving 92.6 % accuracy and a 0.94 AUC score on the database. The synergy between the capability of GBM for tabular data and the ability of DNN for complex interaction gives a good outcome. The research demonstrates the efficacy of blending machine learning techniques for supporting Alzheimer's disease (AD) identification and provides a method for early identification at a broader level. It is hoped that more biomarkers will be incorporated, and the model will be validated on larger and more phenotypically diverse databases to achieve clinical usability and generalizability.