Predictive Analytics And The Health Care Industry

Before proceeding to review a range of predictive analytic algorithms, it is important to know how critical predictive analytics is to the health care industry. The growth rate of US healthcare expenditures, increasing annually by nearly 5% in real terms over the last decade and a major contributor to the high national debt levels projected over the next two decades. McKinsey estimates that Big Data can enable more than $300 billion savings per year in US healthcare, with two-thirds of that through reductions of around 8% to national healthcare expenditures. Imagine if there were health care analytics in the middle ages. The black plague could have been avoided saving millions of lives of people as it would have been easy to single out the†¦show more content†¦It could consist of patient-related data, data from healthcare devices like monitors and sensors, hospital records, application data measuring health metrics and everything including social media posts, webpages, emerg ency correspondence, research data from genomics to innovative drugs, advertisement data, newsfeeds and articles in medical journals. As much as there is scope for finding out patterns among these data, it is not easy to implement predictive analytics in healthcare industry because of the limitations like hand-written prescriptions, scanned images and medical records which comprise of unstructured and disintegrated data. Moreover, medical data is involved with legal and privacy issues. The adoption rate of analytics in healthcare industry is quite slow making it more challenging. The Why of applying predictive analytics in healthcare: If predictive analytics is applied extensively to the rapidly growing healthcare industry, limitless advantages can be realized. Some of the advantages are: 1) Improved real-time decisions about treatment and support, consumer commitment 2) Effortless revenue management with focus on global as well as local markets 3) Standardized clinical processes, guidelines and protocols greatly improving operational efficiency 4) Reduction in fraud claims, security threats greatly helping insurance companies 5) Mining for unknown variables that determine quality such as â€Å"hidden† re-admission factors or finding out