Machine learning: Predicting hospital length of stay in patients admitted for lupus flares
Lupus · 2023-10 · 32 (12) · 1418-1429
DOI: 10.1177/09612033231206830 ↗Kurz gefasst
Fachartikel in der Zeitschrift Lupus, online erschienen am 13.10.2023. Verfasst von Radu Grovu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Internal Medicine Department, Staten Island University Hospital, Staten Island, NY, USA. Hauptthemen laut MEDLINE: Lupus Erythematosus, Systemic. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 49 Literaturangaben.
Abstract (Originalsprache)
Background
Although rare, severe systemic lupus erythematosus (SLE) flares requiring hospitalization account for most of the direct costs of SLE care. New machine learning (ML) methods may optimize lupus care by predicting which patients will have a prolonged hospital length of stay (LOS). Our study uses a machine learning approach to predict the LOS in patients admitted for lupus flares and assesses which features prolong LOS.
Methods
Our study sampled 5831 patients admitted for lupus flares from the National Inpatient Sample Database 2016–2018 and collected 90 demographics and comorbidity features. Four machine learning (ML) models were built (XGBoost, Linear Support Vector Machines, K Nearest Neighbors, and Logistic Regression) to predict LOS, and their performance was evaluated using multiple metrics, including accuracy, receiver operator area under the curve (ROC-AUC), precision-recall area under the curve (PR- AUC), and F1-score. Using the highest-performing model (XGBoost), we assessed the feature importance of our input features using Shapley value explanations (SHAP) to rank their impact on LOS.
Results
Our XGB model performed the best with a ROC-AUC of 0.87, PR-AUC of 0.61, an F1 score of 0.56, and an accuracy of 95%. The features with the most significant impact on the model were “the need for a central line,” “acute dialysis,” and “acute renal failure.” Other top features include those related to renal and infectious comorbidities.
Conclusion
Our results were consistent with the established literature and showed promise in ML over traditional methods of predictive analyses, even with rare rheumatic events such as lupus flare hospitalizations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Internal Medicine Department, Staten Island University Hospital, Staten Island, NY, USA.
- Department of Engineering, University of Massachusetts, Dartmouth, MA, USA.
- Medicine Department, Harvard Medical School, Boston, MA, USA.
- Medicine Department, Duke-NUS Medical School, Singapore.
- Medicine Department, George Washington University School of Medicine, Washington, DC, USA.
- Rheumatology Department, Staten Island University Hospital, Staten Island, NY, USA.
ORCID-Profile: Radu Grovu
Zitieren
APA
Grovu, R., Huo, Y., Nguyen, A., Mourad, O., Pan, Z., El-Gharib, K., Wei, C., Mustafa, A., Quan, T., & Slobodnick, A. (2023). Machine learning: Predicting hospital length of stay in patients admitted for lupus flares. Lupus, 32(12), 1418-1429. https://doi.org/10.1177/09612033231206830
Vancouver
Grovu R, Huo Y, Nguyen A, Mourad O, Pan Z, El-Gharib K, et al. Machine learning: Predicting hospital length of stay in patients admitted for lupus flares. Lupus. 2023;32(12):1418-1429. doi:10.1177/09612033231206830
BibTeX
@article{Grovu2023,
author = {Grovu, Radu and Huo, Yanran and Nguyen, Andrew and Mourad, Omar and Pan, Zihang and El-Gharib, Khalil and Wei, Chapman and Mustafa, Ahmad and Quan, Theodore and Slobodnick, Anastasia},
title = {Machine learning: Predicting hospital length of stay in patients admitted for lupus flares},
journal = {Lupus},
year = {2023},
volume = {32},
number = {12},
pages = {1418--1429},
doi = {10.1177/09612033231206830}
}
EUVIMED