RETRACTED ARTICLE: MapReduce-based big data framework using modified artificial neural network classifier for diabetic chronic disease prediction

Recently, healthcare data consist of an enormous amount of information, which is challenging to maintain by manual methods. Due to the development of big data in the communities of biomedical and health care, accurate study of the medical data helps the recognition of the disease in early stage, patient care and community services. It mainly focuses on predicting and exploring the conditions due to some significant effects on health which are on the increase in multiple cities. The existing system in the medical field cannot extract complete information from the chronic disease database. It is complicated for the healthcare practitioner to analyze and diagnose constant disease since it plays a challenging task. This paper presents a modified artificial neural network (ANN) classifier technique with a MapReduce framework for the prediction of disease. For preprocessing, min–max normalization is carried out to enhance the accuracy of system. This MapReduce is applied for providing a feasible framework in predictive programming algorithms for the map and reduce functions. This is a simple programming interface, which helps in efficiently solving predictive problems. The primary intention of the proposed system is to analyze accurate, fast and optimal results on chronic disease datasets. It increases the throughput and redundancy in cases of retrieving the vast data. Thus, integrating a modified ANN classifier with a reduced framework is useful in providing better outcomes. The experimental results over chronic diabetic dataset prove that the proposed artificial neural network with MapReduce structure is capable of predicting the precision, sensitivity and specificity level modified on comparing with other existing deep neural network approaches.