Title: Big data ensemble clinical prediction for healthcare data by using deep learning model

Authors: Sreekanth Rallapalli; R.R. Gondkar

Addresses: R&D Centre, Bharathiyar University, Coimbatore, India ' Department of PG Studies, Nagarjuna College of Engineering and Technology, Bangalore, India

Abstract: Big data has revolutionised the healthcare industry. Electronic health records (EHRs) is growing at an exponential rate. Healthcare data being unstructured in nature requires a complete new technology to process the data. Clinical applications also need machine learning techniques and data mining methods which include decision trees and artificial neural networks. Classification algorithms have to be considered for developing predictive models. Ensemble model is gaining popularity among various other individual contributors. Ensemble systems can provide better accuracy. In this paper, we combine four algorithms support vector machines, naïve Bayes, random forest and deep learning models are used to design the ensemble framework. Deep learning model is used to find the predicted labels. The data sets are collected from MIMIC-III clinical database repository. Results shows that the proposed ensemble model provides the better accuracy results when deep learning model is included as deep learning is an efficient method for complex problems and large data sets.

Keywords: algorithm; big data; classification; decision trees; deep learning; electronic health records; HER; ensemble model; predictive model.

DOI: 10.1504/IJBDI.2018.094994

International Journal of Big Data Intelligence, 2018 Vol.5 No.4, pp.258 - 269

Received: 12 Jul 2017
Accepted: 26 Aug 2017

Published online: 05 Dec 2017 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article