Home // GLOBAL HEALTH 2012, The First International Conference on Global Health Challenges // View article

Accurate and Reliable Recommender System for Chronic Disease Diagnosis

Authors:
Asmaa S. Hussein
Wail Omer
Xue Li
Modafar Ati

Keywords: E-Health; Remote Chronic Disease Diagnosis prediction; Diabetes healthcare management system; Decision Tree; Random Forest.

Abstract:
With the rapid growth of chronic disease cases around the world, healthcare support systems like recommender systems play a major role in controlling the disease, through providing accurate and trustworthy disease risk diagnosis prediction and acknowledgement of disease risk status, that assists healthcare providers to have 24/7 remote patient monitoring system and assist patients to have 24 hour access to the medical care. Providing an accurate real-time recommendation for medical data is a challenge according to its complexity represented by unbalance, large, noisy and/or missing data. The Chronic Disease Diagnosis (CDD) recommender system expectation is to give a high accuracy and reliable disease risk prediction. This paper presents a CDD recommender system model using multiple decision tree classification algorithms. Decision tree algorithms are applied to achieve high accuracy disease risk predictive model. Historical patients’ medical data from the Middle East is used to train the model. Determining the relevant features through Attribute Selection method is used to reduce data generation and improve the predictive model performance. Merging patients’ lab and home test readings is considered to leverage the diagnosis fidelity. Diabetes diagnosis case study is designed through this research as experiment to show the feasibility of our model.

Pages: 113 to 118

Copyright: Copyright (c) IARIA, 2012

Publication date: October 21, 2012

Published in: conference

ISSN: 2308-4553

ISBN: 978-1-61208-243-1

Location: Venice, Italy

Dates: from October 21, 2012 to October 26, 2012