ICU Survival Prediction Incorporating Test-Time Augmentation to Improve the Accuracy of Ensemble-Based Models

Seffi Cohen, Noa Dagan, Nurit Cohen-Inger, Dan Ofer, Lior Rokach

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

This work presents a novel method for applying test-time augmentation (TTA) to tabular data. We used TTA along with an ensemble of 42 models to achieve higher performance on the MIT Global Open Source Severity of Illness Score dataset consisting of 131,051 ICU visits and outcomes. This method achieved an AUC of 0.915 on the private test set (19,669 admissions) and won first place at Stanford University's WiDS Datathon 2020 challenge on Kaggle, while the Acute Physiology and Chronic Health Evaluation (APACHE) IV model (commonly used for ICU survival prediction in the literature) achieved an AUC of 0.868. In addition to increasing the AUC score, our method also reduces 'unfair' bias.

Original languageEnglish
Article number9462159
Pages (from-to)91584-91592
Number of pages9
JournalIEEE Access
Volume9
DOIs
StatePublished - 1 Jan 2021

Keywords

  • Ensemble methods
  • healthcare
  • machine learning
  • supervised classification

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering

Fingerprint

Dive into the research topics of 'ICU Survival Prediction Incorporating Test-Time Augmentation to Improve the Accuracy of Ensemble-Based Models'. Together they form a unique fingerprint.

Cite this