Social networks for eHealth solutions on cloud

Traditional experimentation based healthcare solutions are constrained by limited data that can confirm or refute the initial hypothesis. Big medical data in individual Electronic Health Records, labs, imaging systems, physician notes, medical correspondence and claims, provides a resource for extracting complementary information that can enhance the data available from traditional approaches based on experimentation. Datamining algorithms are being used to analyze data to get a more insightful understanding of human health, both preventive and clinical. But despite their sophistication, they are far from flawless. One way to solve the problem is crowdsourcing citizens connected in a social network, who can provide data, get it analyzed, and consume data for preventive health insights (Swan, 2009). Several challenges come along with it, for instance: performance, scalability, speed, storage, and power, which we believe could be addressed by cloud-enabled social networks for eHealth services. Such services could be composed of many other services, for instance, user authentication, email, payroll management, calendars, tele-consultation, e-Prescribing, e-Referral, e-Reimbursement, and alerting services, aiming to change the way big medical data in social networking web sites could be used making it actionable to save lives. This paper aims to explore the opportunities and challenges for realization of cloud-enabled social networks for eHealth solutions, by examining efforts already underway, and recommending solutions to improve it. We discuss a three-tier ecosystem to advance this key field leveraging the Cloud computing technologies. In Tier-1 is “Build Sustainable eHealth System” to create a foundation that facilitates secure creation, storage, exchange, and analysis of data between actors. In Tier-2 is “Crowdsourced Social Networks for eHealth Services” to utilize the power of crowdsourcing. In Tier-3 is “Increasing Access to eHealth” to minimize risk and improve patient outcome. Failure to address these issues is believed to result in inefficient use of big medical data toward preventive healthcare.