Mortality Prediction based on Imbalanced New Born and Perinatal Period Data

Abstract

This study was carried out by the New York State Department of Health, between 2012 and 2016. This experiment relates to six supervised machine learning methods: Support Vector Machine (SVM), Logistic Regression (LR), Gradient Boosting (GB), Random Forest (RF), Deep Learning (DL) and the Ensemble Model, all of which are used in the prediction of infant mortality. This experiment applied ensemble model that concentrated on assigning different weights to different models per output class in order to obtain a better predictive performance for infant mortality. Efforts were made to measure the performance and compare the classifier accuracy of each model. Several criteria, including the area under ROC curve, were considered when comparing the ensemble model (GB, RF and DL) with the other five models (SVM, LR, DL, GB and RF). In terms of these different criteria, the ensemble model outperformed the others in predicting survival rates among infant patients given a balanced data set (the areas under the ROC curve for minor, moderate, major and extreme were 98%, 95%, 92% and 97% respectively, giving a total accuracy of 80.65%). For the imbalanced dataset, (the areas under the ROC curve for minor, moderate, major and extreme were 98%, 98%, 99% and 99% respectively, giving total accuracy increased to 97.44%). The results of the experiments used in this dissertation showed that using the ensemble model provided a better level of prediction for infant mortality than the other five models, based on the relative prediction accuracy for each model for each output class. Therefore, the ensemble model provides and extremely promises classifier in terms of predicting infant mortality.

Authors and Affiliations

Wafa M. AlShwaish, Maali Ibr. Alabdulhafith

Keywords

Related Articles

Study of Hybrid Autonomous Power System Modelling Via Multi-Agents Strategy

In this paper, a design of a Hybrid autonomous Power System is proposed and detailed. The studied system integrates several components as solar energy source, Energy Recovery system based on a proton membrane exchange fu...

Software Effort Prediction using Statistical and Machine Learning Methods

Accurate software effort estimation is an important part of software process. Effort is measured in terms of person months and duration. Both overestimation and underestimation of software effort may lead to risky conseq...

Detecting Inter-Component Vulnerabilities in Event-based Systems

Event-based system (EBS) has become popular because of its high flexibility, scalability, and adaptability. These advantages are enabled by its communication mechanism—implicit invocation and implicit concurrency between...

Person Detection from Overhead View: A Survey

In recent years, overhead view based person detection gained importance, due to handling occlusion problem and providing better coverage in scene, as com-pared to frontal view. In computer vision, overhead based person d...

Comparison of Localization Free Routing Protocols in Underwater Wireless Sensor Networks

Underwater Wireless Sensor Network (UWSN) is newly developed branch of Wireless Sensor network (WSN). UWSN is used for exploration of underwater resources, oceanographic data collection, flood or disaster prevention, tac...

Download PDF file
  • EP ID EP626542
  • DOI 10.14569/IJACSA.2019.0100808
  • Views 90
  • Downloads 0

How To Cite

Wafa M. AlShwaish, Maali Ibr. Alabdulhafith (2019). Mortality Prediction based on Imbalanced New Born and Perinatal Period Data. International Journal of Advanced Computer Science & Applications, 10(8), 51-60. https://europub.co.uk/articles/-A-626542