Early-Stage Alzheimer's Disease Prediction Using Machine Learning Models.

Area of Science:

• Neuroscience
• Medical Informatics

Background:

• Alzheimer's disease (AD) is a leading cause of dementia, impacting a growing global population.
• Early diagnosis of AD is challenging but crucial for effective treatment and minimizing neurodegeneration.
• Increasing AD incidence poses significant social, financial, and economic burdens.

Purpose of the Study:

• To apply machine learning (ML) techniques for accurate prediction of Alzheimer's disease.
• To identify optimal ML parameters for early AD detection.
• To provide clinicians with a tool for improved AD diagnosis.

Main Methods:

• Utilized several ML algorithms including Decision Tree, Random Forest, Support Vector Machine, Gradient Boosting, and Voting classifiers.
• Employed the Open Access Series of Imaging Studies (OASIS) dataset for AD prediction.
• Evaluated model performance using metrics such as Precision, Recall, Accuracy, and F1-score.

Main Results:

• The proposed ML classification scheme achieved a high average accuracy of 83% on test data.
• The achieved accuracy significantly outperforms existing methods for AD prediction.
• The models demonstrated strong performance in identifying key parameters for AD diagnosis.

Conclusions:

• Machine learning offers a promising approach for the early and accurate prediction of Alzheimer's disease.
• Early diagnosis via ML can lead to more effective treatments and reduced mortality.
• The developed classification scheme can support clinical decision-making in AD diagnosis.