Health Recommender Systems: Concepts, Requirements, Technical Basics and Challenges

Abstract

During the last decades huge amounts of data have been collected in clinical databases representing patients' health states (e.g., as laboratory results, treatment plans, medical reports). Hence, digital information available for patient-oriented decision making has increased drastically but is often scattered across different sites. As as solution, personal health record systems (PHRS) are meant to centralize an individual's health data and to allow access for the owner as well as for authorized health professionals. Yet, expert-oriented language, complex interrelations of medical facts and information overload in general pose major obstacles for patients to understand their own record and to draw adequate conclusions. In this context, recommender systems may supply patients with additional laymen-friendly information helping to better comprehend their health status as represented by their record. However, such systems must be adapted to cope with the specific requirements in the health domain in order to deliver highly relevant information for patients. They are referred to as health recommender systems (HRS). In this article we give an introduction to health recommender systems and explain why they are a useful enhancement to PHR solutions. Basic concepts and scenarios are discussed and a first implementation is presented. In addition, we outline an evaluation approach for such a system, which is supported by medical experts. The construction of a test collection for case-related recommendations is described. Finally, challenges and open issues are discussed.

Marathon Race Planning: A Case-Based Reasoning Approach

“…Note too how the prediction accuracy (and profile similarity) for all strategies is better for women than for men, regardless of k. In short, women run more evenly paced (predictable) races [Trubee, 2011;Deaner, 2006]. Our results suggest that this also extends to the matter of predicting a personal best time and recommending a bespoke pacing plan.…”

“…A key concept is pace, which is measured in minutes per mile/km -the inverse of speed -so that higher values correspond to slower speeds and vice versa [Trubee, 2011;Foster et al, 1994;Deaner, 2006;Haney Jr, 2010]. There are three basic pacing strategies.…”

“…While health applications of AI are not new [Peek et al, 2015;Buchanan and Shortliffe, 1984;Bichindaritz et al, 2008;Wiesner and Pfeifer, 2014;, always-on smartphones and wearables are creating an even greater opportunity for novel preventative, proactive, and personalised interventions [Ohlin and Olsson, 2015;Geleijnse et al, 2011]. The sports world has embraced the data-centric world of sensors [Campbell et al, 2008] and mobile apps, as athletes explore the power of data to optimise training and performance [Lewis, 2004;Kelly et al, 2012;Leijdekkers and Gay, 2015;Möller et al, 2011;Hermens et al, 2014].…”

Shared decision-making using personal health record technology: a scoping review at the crossroads

“…Additionally, the interplay between multiple sources in one comprehensive electronic health records platform may not only improve patient self-management, it can transform the tradition of episodic care to a more continuous, collaborative one supporting decision making, care coordination, and communication between providers and patients [27], [42]. As an unconnected collection of personal health information, the PHR is limited but as an interconnected account with the healthcare system as a whole, it offers a wide array of benefits [43].…”

“…Only 4 articles examined a PHR whose functionality met all four SDM elements and not a single article in the review had a PHR which operated using all SDM-enabled functionality as identified by the PHR functional subcategories. [28] , [29] , [21] , [30] , [23] , [31] , [32] , [33] , [34] , [35] , [5] , [36] , [37] , [38] , [25] 14 reminders [26] , [23] , [31] , [22] , [24] , [27] , [20] , [39] , [34] , [35] , [5] , [36] , [8] , [37] 1 SDM infobutton -initiate and track [28] Options 23 personalized decision support [28] , [29] , [21] , [26] , [23] , [31] , [40] , [22] , [32] , [41] , [27] , [42] , [33] , [20] , [39] , [34] , [35] , …”