A Recommender System with Advanced Time Series Medical Data Analysis for Diabetes Patients in a Telehealth Environment

Abstract

Intelligent technologies are enjoying growing popularity in a telehealth environment for helping improve the quality of chronic patients’ lives and provide better clinical decision-making to reduce the costs and workload involved in their daily healthcare. Obtaining a short-term disease risk prediction and thereby offering medical recommendations reliably and accurately are challenging in teleheath systems. In this work, a novel medical recommender system is proposed based upon time series data analysis for diabetes patients. It uses three decomposition methods, i.e., dual-tree complex wavelet transform (DTCWT), fast Fourier transformation (FFT) and dual-tree complex wavelet transform-coupled fast Fourier transform (DWCWT-FFT), with least square-support vector machine (LS-SVM) for short-term disease risk prediction for diabetes disease patients which then generates appropriate recommendations on their need to take a medical test or not on the coming day based on the analysis of their medical data. A real-life time series dataset is used for experimental evaluation. The experimental results show that the proposed system yields very good recommendation accuracy and can effectively reduce the workload for diabetes disease patients in conducting daily body tests.