A Data‐driven Approach for Genetic Prediction of Alzheimer's Diseases when Polygenic RiskScores Fail to account AD's Genetic Complexity

This study provided an AI-driven approach for the genetic prediction of AD when PRS fails to account for AD's genetic complexity using advanced machine learning techniques. Our methodology improves feature selection, computational efficiency, and predictive accuracy. Identifying novel genetic markers, outperforming PRS models, and enhancing earlier diagnosis for personalized healthcare. We are planning to extend this study with larger datasets by enhancing the proposed feature engineering methods for more robust predictions.