A lightweight machine learning tool for Alzheimer's disease prediction
Developed a lightweight ML based tool using 19 routinely available features.The lightweight model achieved an ROC-AUC of 0.90 for Alzheimer's disease prediction on NACC multicenter data.Genetic algorithm, IBFE, and manual refinement enabled optimal feature selection.Tool hosted on an open-access platform for clinical and research use.SHAP analysis provided model interpretability and feature-level insights.
Authors
- Hardeep Singh Malhotra (ORCID: https://orcid.org/0000-0003-0438-4446)
- Ananya Sharma (ORCID: https://orcid.org/0000-0002-5077-160X)
- Tulika Nahar (ORCID: https://orcid.org/0000-0001-8766-1765)
- Ayush Mishra
- Vivek Sanker (ORCID: https://orcid.org/0000-0003-0615-8397)
- Ravindra Kumar Garg (ORCID: https://orcid.org/0000-0003-0044-7083)
- Omer Mohammed (ORCID: https://orcid.org/0000-0001-9166-6892)
- Amogh Verma (ORCID: https://orcid.org/0000-0003-2499-4874)
- Devansh Mishra (ORCID: https://orcid.org/0000-0002-1584-3241)
- Vinay Suresh (ORCID: https://orcid.org/0000-0002-1401-9154)
- Suhrud Panchawagh (ORCID: https://orcid.org/0000-0002-8606-4202)
- Muneeb Ahmad Muneer
Institutions
- Turing Institute (GB)
- Queen's University Belfast (GB)
- Government of Tamil Nadu (IN)
- Allama Iqbal Medical College (PK)
- Chhatrapati Shahu Ji Maharaj University (IN)
- Government Medical College (IN)
- King George's Medical University (IN)
- Era's Lucknow Medical College and Hospital (IN)
- Rama Hospital & Research Centre (IN)
- Mayo Clinic in Arizona (US)
- Stanford University (US)
Publication Details
- Journal
- Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring
- Published
- 2025-10-01
- DOI
- https://doi.org/10.1002/dad2.70187
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- National Institutes of Health
- National Institute on Aging