Machine learning-based risk profile classification: A case study for heart valve surgery

Ulrich Bodenhofer, Bettina Haslinger-Eisterer, Alexander Minichmayer, Georg Hermanutz, Jens Meier

Research output: Contribution to conferencePaperpeer-review

1 Downloads (Pure)

Abstract

We employ machine learning to predict the 30-days mortality after heart valve surgeries from demographic and preoperative parameters. We achieve AUC values of almost 84%, while the standard EuroSCORE I provides an AUC of only slightly more than 70% for the given cohort. These results indicate (1) that state-of-the-art machine learning is superior to traditional risk models and (2) that calibrating models to specific institutions and surgical procedures allows for more accurate predictions that have the potential to improve medical decision making.
Original languageEnglish (American)
Publication statusPublished - Dec 2017
EventNIPS Workshop on Machine Learning for Health - Long Beach, CA, United States
Duration: 8 Dec 20178 Dec 2017

Workshop

WorkshopNIPS Workshop on Machine Learning for Health
Country/TerritoryUnited States
Period08.12.201708.12.2017

Cite this