New Approach based on Machine Learning for Short-Term Mortality Prediction in Neonatal Intensive Care Unit

Abstract

Mortality remains one of the most important outcomes to predict in Intensive Care Units (ICUs). In fact, the sooner mortality is predicted, the better critical decisions are made by doctors based on patient’s illness severity. In this paper, a new approach based on Machine Learning (ML) techniques for short-term mortality prediction in Neonatal Intensive Care Unit (NICU) is proposed. This approach relies on many steps. At first, relevant features are selected from available data upon neonates’ admission and from the time-series variables collected within the two first hours of stay in the NICU from the Medical Information Mart for Intensive Care III (MIMIC-III). After that, to predict mortality, many classifiers were tested which are Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Logistic Regression (LR), Support Vector Machine (SVM), Naïve Bayes (NB) and Random Forest (RF). The experimental results showed that LDA was the best performing classifier with an accuracy equal to 0.947 and AUROC equal to 0.97 with 31 features. The third step of this approach is mortality time prediction using the Galaxy-Random Forest method achieving an f-score equal to 0.871. The proposed approach compared favorably in terms of time, accuracy and AUROC with existing scoring systems and ML techniques. It is the first work predicting neonates mortality based on ML techniques and time-series data after only two hours of admission to the NICU.

Authors and Affiliations

Zaineb Kefi, Kamel Aloui, Mohamed Saber Naceur

Keywords

Related Articles

Modularity Index Metrics for Java-Based Open Source Software Projects

Open Source Software (OSS) Projects are gaining popularity these days, and they become alternatives in building software system. Despite many failures in these projects, there are some success stories with one of the ide...

Developing an Integrated Cloud-based Framework for Securing Dataflow of Wireless Sensors

Cloud computing environment has been developed rapidly and becomes a popular trend in recent years. It provides on-demand services to several applications with access to an unlimited number of resources such as servers,...

An Area-Efficient Carry Select Adder Design by using 180 nm Technology

In this paper, we proposed an area-efficient carry select adder by sharing the common Boolean logic term. After logic simplification and sharing partial circuit, we only need one XOR gate and one inverter gate in each su...

A Robust System for Noisy Image Classification Combining Denoising Autoencoder and Convolutional Neural Network

Image classification, a complex perceptual task with many real life important applications, faces a major challenge in presence of noise. Noise degrades the performance of the classifiers and makes them less suitable in...

State of the Art Exploration Systems for Linked Data: A Review

The ever-increasing amount of data available on the web is the result of the simplicity of sharing data over the current Web. To retrieve relevant information efficiently from this huge dataspace, a sophisticated search...

Download PDF file
  • EP ID EP611501
  • DOI 10.14569/IJACSA.2019.0100778
  • Views 108
  • Downloads 0

How To Cite

Zaineb Kefi, Kamel Aloui, Mohamed Saber Naceur (2019). New Approach based on Machine Learning for Short-Term Mortality Prediction in Neonatal Intensive Care Unit. International Journal of Advanced Computer Science & Applications, 10(7), 583-591. https://europub.co.uk/articles/-A-611501