Prediction of Acute Kidney Injury in Cardiac Surgery Patients: Interpretation using Local Interpretable Model-agnostic Explanations

Harry Freitas da Cruz, Frederic Schneider, Matthieu-P. Schapranow

2019

Abstract

Acute kidney injury is a common complication of patients who undergo cardiac surgery and is associated with additional risk of mortality. Being able to predict its post-surgical onset may help clinicians to better target interventions and devise appropriate care plans in advance. Existing predictive models either target general intensive care populations and/or are based on traditional logistic regression approaches. In this paper, we apply decision trees and gradient-boosted decision trees to a cohort of surgical heart patients of the MIMIC-III critical care database and utilize the locally interpretable model agnostic approach to provide interpretability for the otherwise opaque machine learning algorithms employed. We find that while gradient-boosted decision trees performed better than baseline (logistic regression), the interpretability approach used sheds light on potential biases that may hinder adoption in practice. We highlight the importance of providing explanations of the predictions to allow scrutiny of the models by medical experts.

Paper Citation

in Harvard Style

Freitas da Cruz H., Schneider F. and Schapranow M. (2019). Prediction of Acute Kidney Injury in Cardiac Surgery Patients: Interpretation using Local Interpretable Model-agnostic Explanations. In Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 5: HEALTHINF; ISBN 978-989-758-353-7, SciTePress, pages 380-387. DOI: 10.5220/0007399203800387

in Bibtex Style

@conference{healthinf19,
author={Harry Freitas da Cruz and Frederic Schneider and Matthieu-P. Schapranow},
title={Prediction of Acute Kidney Injury in Cardiac Surgery Patients: Interpretation using Local Interpretable Model-agnostic Explanations},
booktitle={Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 5: HEALTHINF},
year={2019},
pages={380-387},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007399203800387},
isbn={978-989-758-353-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 5: HEALTHINF
TI - Prediction of Acute Kidney Injury in Cardiac Surgery Patients: Interpretation using Local Interpretable Model-agnostic Explanations
SN - 978-989-758-353-7
AU - Freitas da Cruz H.
AU - Schneider F.
AU - Schapranow M.
PY - 2019
SP - 380
EP - 387
DO - 10.5220/0007399203800387
PB - SciTePress