Early Detection of Dementia Using Machine Learning Algorithms

Krishnavarthini K H; Madhu Preetha A; Dr. PREETHA EVANGELINE

doi:10.36948/ijfmr.2026.v08i01.61829

Early Detection of Dementia Using Machine Learning Algorithms

Author(s)	Ms. Krishnavarthini K H, Ms. Madhu Preetha A, Dr. PREETHA EVANGELINE
Country	India
Abstract	Dementia is a progressive neurodegenerative disorder that impairs memory, cognition, and behavior, affecting millions of individuals worldwide. Early detection plays a vital role in improving patient management and therapeutic interventions. This paper presents Phase 1 of a research project on dementia detection using machine learning. In this phase, a predictive framework was developed using clinical and morphometric tabular data from the OASIS Longitudinal Dataset, which includes demographic, clinical, and brain-volume-related features such as age, education, socio-economic status (SES), Mini-Mental State Examination (MMSE), Clinical Dementia Rating (CDR), and normalized whole-brain volume (nWBV). The preprocessing pipeline involved imputation of missing values, categorical encoding, and normalization. Two models—Decision Tree (J48 equivalent) and Artificial Neural Network (ANN/MLP)—were implemented and compared, where the Decision Tree provided interpretability and the ANN effectively captured nonlinear feature relationships. This validated Phase 1 implementation focuses on tabular-data–based dementia prediction. The subsequent Phase 2, currently under development, aims to integrate MRI image-based deep learning and multi-modal decision fusion to enhance diagnostic accuracy and clinical applicability.
Keywords	Dementia Detection, Machine Learning, OASIS Dataset, Decision Tree, Artificial Neural Network, Phase 1 Implementation, MRI Integration.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 1, January-February 2026
Published On	2026-01-22
DOI	https://doi.org/10.36948/ijfmr.2026.v08i01.61829

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Early Detection of Dementia Using Machine Learning Algorithms

Share this