Privacy Enhanced Cloud-Based Recommendation Service for Implicit Discovery of Relevant Support Groups in Healthcare Social Networks

Privacy Enhanced Cloud-Based Recommendation Service for Implicit Discovery of Relevant Support Groups in Healthcare Social Networks

Ahmed M. Elmisery, Mirela Sertovic
Copyright: © 2017 |Pages: 17
DOI: 10.4018/IJGHPC.2017010107
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Recommending support-groups in healthcare social networks is the problem of detecting for each patient his/her membership to one support-group of relevant patients. The patients in each support-group share some relevant preferences which guarantee that the support-group as a whole satisfies some desired properties of similarity. As a result, forming these support-groups requires the availability of personal data of different patients. This is a crucial requirement for different recommender services. With the increasing trend of service providers to collect a large volume of personal data regarding their end-users, presumably to better serve them. However, a significant part of the data that is typically collected is not essential to the service being offered, or to the completion of the services it was presumably released for. Gathering such unnecessary data can be seen as a privacy threat, and storing it exposes the end-users to further unavoidable risks. In this paper, a privacy enhanced cloud-based recommendation service is proposed for the implicit discovery of appropriate support groups in healthcare social network. A fog based middleware (FMCP) was introduced that runs at patients' sides and allows exchanging of their information to facilities recommending and creating support-groups without disclosing their real preferences to other parties. The membership of patients in various support groups allows receiving highly appropriate and reliable healthcare-related advices. The system utilizes two protocols to attain this goal. Experiments were performed on real dataset.
Article Preview
Top

Introduction

The social networks are fundamentally enhancing the way many people interact with each other. The proliferation of social networks as an efficient gadget to promote the interaction and to facilitate information sharing between members of the network drives the emerging of more purpose driven social networks in different domains. Employing social networks in the healthcare domain had a considerable influence in e-health systems. This in turn aids in raising the term healthcare social networks (HSNs). The emergence of healthcare social networks has facilitated the patient-specialist interaction and allowed the care providers to continuously offer health and wellness services to a wide variety of patients wherever they may be. Currently, the patients utilize healthcare social networks to extract relevant information related to their health conditions from the massive amount of information available online. The Healthcare Social networks hold a substantial value for healthcare providers (Giustini, 2007), since these networks create an interaction space where patients can collaborate together and gather information related to their experiences and observations. Based on a recent statistics, One-third of patients in United States goes online and search for fellow patients who have similar health conditions like them (Elkin, 2008) and 36% of the patients use other patients’ opinions and experiences on healthcare social networks before making healthcare related decisions (Levy, 2007). Healthcare Social networks (HSNs) were originally developed to patients with a reduced mobility and/or older adults; however, different healthcare originations and health personnel can participate in it. HSNs accumulate experiences and recommendations for the best practices to deal with certain health conditions. The next generation of the healthcare domain requires applications that have social interaction capabilities. Until now, there have been different paradigms for healthcare social networks such as PatientsLikeMe®, peoplejam®, DailyStrength®, OrganizedWisdom®, and CureTogether®. The biggest healthcare social network is PatientsLikeMe which launched in 2004, and currently has more than 200,000. It allows patients to use ready-made tools to track the progress of their health status and to access health information related to their medical conditions. Patients can benefit from the experiences of other patients with similar health status, share their life-style with likely similar patients and healthcare professionals. PatientsLikeMe® also offers specialized access to anonymized data to various healthcare organizations. Another healthcare social network is CureTogether®, which allows patients to track healthcare related data in an anonymous way to understand their current health status and take considered decisions regarding the required treatments for their conditions. DailyStrength® is a healthcare social network created to support patients-groups. Where patients seek to know other fellow patients to offer emotional support in an open platform that supports discussion of their attempts and useful advices. This network contains numerous online patients-groups regarding different healthcare diseases.

Within healthcare social networks, each patient has his/her own profile that represents his/her preferences in joining different support-groups and in using various services in the social healthcare platform. Support-group’s recommendation service is one of these services running on the social healthcare platform and utilizes patient’s preferences to provide numerous recommendations to join personalized support-groups out of the large number of candidate support-groups. This kind of cloud-based recommendation service relies on the assumption that patients with related preferences have the same concerns. The extraction of these recommendations depends on the private profiles of these patients, which contain their personal data and sensitive preferences. This service is usually accessible to different kinds of registered patients, which in turn, brings new kinds of threats and problems to the patients from the service provider and other registered patients sides, such as malignant behaviors. For instance, malignant users might perform certain attacks to get one another’s personal information, such as current health conditions, place of work and/or relationship status. This kind of attacks could reveal patients’ personal information even if it is not supposed to be exposed to the public.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 2 Issues (2023)
Volume 14: 6 Issues (2022): 1 Released, 5 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing