Predicting Risk-of-Readmission for Congestive Heart Failure Patients on big data solutions

  k.Balachandra reddy,  dr.hariskeharan

Big Data is a collection of data that is large or complex to process using on-hand database management tools or data processing applications. It is becoming very difficult for companies to store, retrieve and process the ever-increasing data. In other words we can say, Big Data is term given to humungous amount of data which is difficult to store and process. The issue lies in using the traditional system is, how to store and analyze Big Data. Risk prediction involves integration of clinical factors with socio-demographic factors like health conditions, disease parameters, hospital care quality parameters, and a variety of variables specific to each health care provider making the task increasingly complex. Unsurprisingly, many of such factors need to be extracted independently from different sources, and integrated back to improve the quality of predictive modeling. Such sources are typically voluminous, diverse, and vary significantly over the time. This project takes Apache Hadoop, an intrinsic part for storing, retrieving, evaluating and processing huge volumes of data for processing effectively. In this work, we study big data driven solutions to predict the 30-day risk of readmission for congestive heart failure (CHF) incidents. We will predict this process by using Logistic Regression and Naive Bayes classification on the basis of data collected from patients. The results are remarkable after the comparison between the two techniques and presented through confusion matrix.

Keywords- Risk prediction, Health care, Logistic Regression, Naive Bayes classification

Unique Identification Number - IJEDR1502052
Page Number(s) - 279-284
Pubished in - Volume 3 | Issue 2 | May 2015
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  k.Balachandra reddy,  dr.hariskeharan,   "Predicting Risk-of-Readmission for Congestive Heart Failure Patients on big data solutions", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 2, pp.279-284, May 2015, Available at :http://www.ijedr.org/papers/IJEDR1502052.pdf