A general extensible learning approach for multi-disease recommendations in a telehealth environment

Lafta, Raid and Zhang, Ji and Tao, Xiaohui ORCID: https://orcid.org/0000-0002-0020-077X and Zhu, Xiaodong and Li, Hongzhou and Chang, Liang and Deo, Ravinesh ORCID: https://orcid.org/0000-0002-2290-6749 (2020) A general extensible learning approach for multi-disease recommendations in a telehealth environment. Pattern Recognition Letters, 132. pp. 106-114. ISSN 0167-8655


Abstract

In a telehealth environment, intelligent technologies are rapidly evolving toward improving the quality of patients’ lives and providing better clinical decision-making especially those who suffer from chronic diseases and require continuous monitoring and chronic-related medical measurements. A short-term disease risk prediction is a challenging task but is a great importance for teleheath care systems to provide accurate and reliable recommendations to patients. In this work, a general extensible learning approach for multi-disease recommendations is proposed to provide accurate recommendations for patients with chronic diseases in a telehealth environment. This approach generates appropriate recommendations for patients suffering from chronic diseases such as heart failure and diabetes about the need to take a medical test or not on the coming day based on the analysis of their medical data. The statistical features extracted from the sub-bands obtained after a four-level decomposition of the patient's time series data are classified using a machine learning ensemble model. A combination of three classifiers – Least Squares-Support Vector Machine, Artificial Neural Network, and Naive Bayes – are utilized to construct the bagging-based ensemble model used to produce the final recommendations for patients. Two real-life datasets collected from chronic heart and diabetes disease patients are used for experimentations and evaluation. The experimental results show that the proposed approach yields a very good recommendation accuracy and offers an effective way to reduce the risk of incorrect recommendations as well as reduces the workload for chronic diseases patients who undergo body tests most days. Thus, the proposed approach is considered one of a promising tool for analyzing time series medical data of multi diseases and providing accurate and reliable recommendations to patients suffering from different types of chronic diseases.


Statistics for USQ ePrint 38127
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Published online: 15 Nov 2018. Permanent restricted access to ArticleFirst version, in accordance with the copyright policy of the publisher.
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Sciences (6 Sep 2019 -)
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Sciences (6 Sep 2019 -)
Date Deposited: 23 Apr 2020 23:46
Last Modified: 28 Apr 2021 02:47
Uncontrolled Keywords: chronicle heart disease; dual-tree complex wavelet transformation; machine learning ensemble; recommender system; telehealth environment; time series prediction
Fields of Research (2008): 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
Fields of Research (2020): 46 INFORMATION AND COMPUTING SCIENCES > 4699 Other information and computing sciences > 469999 Other information and computing sciences not elsewhere classified
Identification Number or DOI: https://doi.org/10.1016/j.patrec.2018.11.006
URI: http://eprints.usq.edu.au/id/eprint/38127

Actions (login required)

View Item Archive Repository Staff Only