In this paper, we had analyzed a large scale Diabetic data sets for several patients to find the length of time taken for treatment for each class of Diabetes and the risk of re-admission of diabetic patients performing Bigdata analytics, the type of diabetes and its outcome which acted as a high risk sample of patient data sets. We have collected and integrated different sources of diabetic information for several patients, from primary and secondary treatment information to administrative information, to analyze novel view of patient care processes such as type of treatments and every patient behaviors on which results multifaceted nature of chronic care that we take into our account to predict the survival factors and length of stay. Nowadays by using electronic medical equipments with high quality and high degree calibrations, we are able to gather large amounts of real-time diabetic data sets. The requires the usage of distributed platforms for making BigData analysis that results on making decisions based on available data and its trends. This type of Bigdata analysis allows geographical and environmental information of patients' enables the capability of interpreting the ethnicity of data gathered and extract new analysis to identify survival options and treatment timelines (LOS) from them.
Sujatha, V., Prasanna Devi, S., Vinu Kiran, S., & Manivannan, S. (2016). Bigdata Analytics on Diabetic Retinopathy Study (DRS) on Real-time Data Set Identifying Survival Time and Length of Stay. In Procedia Computer Science (Vol. 87, pp. 227–232). Elsevier B.V. https://doi.org/10.1016/j.procs.2016.05.153