ALERT!

This site is not optimized for Internet Explorer 8 (or older).

Please upgrade to a newer version of Internet Explorer or use an alternate browser such as Chrome or Firefox.

Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach

Friday, August 6, 2021

Submitted by

Source

Source Name: World Journal for Pediatric and Congenital Heart Surgery

Author(s)

Dimitris Bertsimas, PhD, Daisy Zhuo, PhD, Jack Dunn, PhD, Jordan Levine, MΕng, Eugenio Zuccarelli, MBAn, MSc, Nikos Smyrnakis Nikos Smyrnakis, Zdzislaw Tobota, MD,  Bohdan Maruszewski, MD, PhD,  Jose Fragata, MD, PhD Jose Fragata, George E. Sarris ,  MD, PhD
In contrast to traditional risk assessment methods (logistic regression), which assume that risk factors interact linearly and additively, the non-linear machine learning methodology of Optimal Classification Trees provides superior power for predicting risks after congenital heart surgery, with the advantage over other machine learning methods of logical interpretability. This methodology also allows estimation of individual patient risk, based on aggregate database data, and may facilitate decision–making and quality improvements in congenital heart surgery.

Add comment

Log in or register to post comments