Predictive & Preventive Healthcare: A Granular Distributed Model Utilizing An Empirically Effective Activation Function
Healthcare analytics is most confidently considered as an specific domain that has interconnected healthcare analytics for numerous areas, as well as precautionary health, well-being and unwellness management. In particular to chronic diseases management, affected populations in several disease classes, the field of healthcare analytics assists target the customized management procedures and conventions that may alleviate the chronic disease, in addition as hamper the onset of affiliated medical conditions. Due to increase in size of patient related data in hospitals over a decade, development of fast information processing systems for this massive, noisy and fuzzy natured data is the need of the hour. The prototype design and analysis proposed in this paper aims to explore various relations among patient attributes, disease risk factors which can be mapped to built automated disease categorization and preventive healthcare systems. This paper presents the results obtained after performing experimental simulations on a standard healthcare related dataset. To present the advantage of the proposed model, the evaluated results are being compared with some existing approaches implemented in the past years.