Dementia detection using parameter optimization for multimodal datasets

Abstract

Dementia, a neurodegenerative disorder, is more prominent among elderly people. This disease is one of the primary contributors amongst other diseases having a high social impact in continents of Europe and America. Treatment of the neurological disorders of dementia patients have become possible due to the Advances in medical diagnosis as in the use of Magnetic Resonance Imaging (MRI). Artificial Intelligence (AI) and Machine Learning (ML) techniques have provided solutions that enable fast, accurate and autonomous detection of diseases at their early stage. This in turn has improvised the entire health care system. This study proposes a diagnostic method, based on ML, for detecting dementia disease. The Open Access Series of Imaging Studies (OASIS) database and Alzheimer’s dataset (4 class of images) have been used for testing and training of various ML models. This involves the classification of the dependent variable into demented and non-demented patient. ML models as in Support Vector Machine (SVM), Logistic Regression, Naïve Bayes, k-nearest neighbor (KNN), Random Forest, Adaptive Boosting (ADA boost), Gradient Boosting, XG Boost, were trained and tested using OASIS dataset. Models were trained with 70% of data and tested on 30% of data. Hyper tuning of parameters of these models was also carried out to check for improvement in the results. Analysis showed that Naïve Bayes was the best amongst all giving 95% accuracy, 98% precision, 93% recall and 95% F1-score.