Open AccessMachine learning to predict in‐hospital mortality among patients with severe obesity: Proof of concept study
Author(s) -
Soffer Shelly,
Zimlichman Eyal,
Levin Matthew A.,
Zebrowski Alexis M.,
Glicksberg Benjamin S.,
Freeman Robert,
Reich David L.,
Klang Eyal
Publication year - 2022
Publication title -
obesity science and practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.654
H-Index - 14
ISSN - 2055-2238
DOI - 10.1002/osp4.571
Subject(s) - medicine , obesity , mortality rate , population , emergency medicine , youden's j statistic , univariate analysis , multivariate analysis , receiver operating characteristic , environmental health
Objectives Hospitalized patients with severe obesity require adapted hospital management. The aim of this study was to evaluate a machine learning model to predict in‐hospital mortality among this population. Methods Data of unselected consecutive emergency department admissions of hospitalized patients with severe obesity (BMI ≥ 40 kg/m 2 ) was analyzed. Data was retrieved from five hospitals from the Mount Sinai health system, New York. The study time frame was between January 2011 and December 2019. Data was used to train a gradient‐boosting machine learning model to identify in‐hospital mortality. The model was trained and evaluated based on the data from four hospitals and externally validated on held‐out data from the fifth hospital. Results A total of 14,078 hospital admissions of inpatients with severe obesity were included. The in‐hospital mortality rate was 297/14,078 (2.1%). In univariate analysis, albumin (area under the curve [AUC] = 0.77), blood urea nitrogen (AUC = 0.76), acuity level (AUC = 0.73), lactate (AUC = 0.72), and chief complaint (AUC = 0.72) were the best single predictors. For Youden’s index, the model had a sensitivity of 0.77 (95% CI: 0.67–0.86) with a false positive rate of 1:9. Conclusion A machine learning model trained on clinical measures provides proof of concept performance in predicting mortality in patients with severe obesity. This implies that such models may help to adopt specific decision support tools for this population.