Recommender System with Machine Learning and Artificial Intelligence

18Temporal Change Analysis-Based Recommender System for Alzheimer Disease Classification

S. Naganandhini, P. Shanmugavadivu* and M. Mary Shanthi Rani

Department of Computer Science and Applications, The Gandhigram Rural Institute (Deemed to be University), Gandhigram, Tamil Nadu, India

Abstract

The development of recommender systems gathered momentum due its relevance and application in providing personalized recommendation on a product or a service for customer relations management. It has proliferated into medicine and its allied domains for the recommendations on disease prediction/detection, medicine, treatment and on other medical services. This chapter describes about a new composite and comprehensive recommender system named Temporal Change Analysis-based Recommender System for Alzheimer Disease Classification (TCA-RS-AD) using deep learning model. Its performance is evaluated on the dataset with T1-weighted MRI clinical temporal data of OASIS and the results were recorded in terms of Precision, Recall, F1-Score and Accuracy, Hamming Loss, Cohen’s Kappa Coefficient, and Matthews Correlation Coefficient. The improved accuracy of this recommendation model endorses its suitability for its application in the classification of AD.

Keywords: Deep learning models, confusion matrix, Matthews correlation coefficient, hamming loss, Cohen’s Kappa, OASIS dataset

18.1 Introduction

The semi-automated brain image analysis aims to discover or diagnose the Alzheimer’s disease due to ...