A Survey on Prediction Using Big Data Analytics

A Survey on Prediction Using Big Data Analytics

M. Supriya (Anna University, Chennai, India) and A.J. Deepa (Ponjesly College of Engineering, Kaniyakumari, India)
Copyright: © 2017 |Pages: 15
DOI: 10.4018/IJBDAH.2017010101
OnDemand PDF Download:
No Current Special Offers


This article describes how nowadays, the growth of big data in bio-medical and healthcare community services is increasing rapidly. The early detection of diseases and patient care are analyzed with the help of accurate analysis of medical data includes diagnosed patients' details. The analysis of accuracy rate is considerably reduced when the quality of medical data is unclear since every part of the body has unique characteristics of certain regional diseases that may suppress the prediction of diseases. This article reviews the detailed survey of different prediction methods developed for analyzing the accuracy rate of disease affected patients in 2015-2016 mainly focuses on choosing the efficient predictions based on the quality of medical data not only provides the overall view of prediction methods but also gives the idea of big data analytics in medical data further discusses the methods, techniques used and the pros and cons of prediction methods.
Article Preview

1. Introduction

Nowadays 50% of Americans have one or more chronic diseases, and 80% of American medical care fee is spent on chronic disease treatment. With the improvement of living standards, the incidence of chronic disease is increasing. The United States has spent an average of 2.7 trillion USD annually on chronic disease treatment. This amount comprises 18% of the entire annual GDP of the United States. The healthcare problem of chronic diseases is also very important in many other countries

In China, chronic diseases are the main cause of death, according to a Chinese report on nutrition and chronic diseases in 2015, 86.6% of deaths are caused by chronic diseases. Therefore, it is essential to perform risk assessments for chronic diseases. Electronic health records (EHRs) are digital versions of a patient’s medical history, maintained over time by health care providers that contain information relevant to a patient’s care, including to demographics, diagnoses, medical procedures, medications, vital signs, immunizations, laboratory results, and radiology images. With the growth in medical data collecting electronic health records is more convenient. One of the applications is to identify high-risk patients which can be utilized to reduce medical cost since high-risk patients often require expensive healthcare (Chen Hao, Hwang, & Wang, 2016).

Convolutional Neural Network-based Multimodal Disease Risk Prediction (CNN-MDRP) algorithm is applicable for structured and unstructured data. The disease risk model is obtained by the combination of structured and unstructured features and the accuracy is analysed.

Complete Article List

Search this Journal:
Volume 7: 1 Issue (2022): Forthcoming, Available for Pre-Order
Volume 6: 2 Issues (2021)
Volume 5: 2 Issues (2020)
Volume 4: 2 Issues (2019)
Volume 3: 2 Issues (2018)
Volume 2: 2 Issues (2017)
Volume 1: 1 Issue (2016)
View Complete Journal Contents Listing