Affiliations: [a] College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates. E-mail: shayma.alkobaisi@uaeu.ac.ae | [b] Department of Computer Science, Seattle University, Seattle, USA. E-mail: baew@seattleu.edu | [c] Department of Mathematics, Hanyang University, Seoul, South Korea. E-mail: horakm@hanyang.ac.kr | [d] Enterprise Information Technology Group, Lockheed Martin, Denver, USA. E-mail: sada.narayanappa@gmail.com | [e] Department of Informatics, Technical University of Munich, Munich, Germany. E-mail: jongwon.lee@tum.de | [f] Department of New Media Technology, Modul University, Dubai, United Arab Emirates. E-mail: eman.abukhousa@modul.ac.ae | [g] Allergy and Respiratory Medicine, Soonchunhyang University Bucheon Hospital, Bucheon, South Korea. E-mails: mdcspark@hanmail.net, dnwls75@naver.com
Note: [**] Part of this research was performed while the author was visiting Hanyang University, Seoul, South Korea.
Abstract: The emerging predictive health analytics provides great promise in reducing costs and improving health outcomes. However, most predictive models do not capture environmental exposures that impact health risk patterns in several chronic diseases such as asthma. This gap prompted the development of the exposome paradigm to improve health intervention and prevention by providing meaningful and understandable feedback on individuals’ collected data and minimizing their exposures to health risks. The exposome paradigm focuses on the simultaneous monitoring of mobility behaviors and measurement of environmental conditions to capture their impact on human health. In this paper, we introduce the concept of exposome analytics that compliments predictive analytics to develop an effective health monitoring and management system. We present the current analytical developments including our ongoing project to manage risks of asthma exacerbations as a case study. Our proposed approach uses a novel exposome assessment paradigm that utilizes the spatio-temporal properties of the data in the model training process and hence results in improving the accuracy of asthma prediction. The quality of the proposed approach is extensively evaluated using real patients and environmental datasets.
Keywords: Exposome, predictive health analytics, individual-level health analytics, asthma risk management, classification, logistic regression, quantile regression
