Machine learning: Predicting hospital length of stay in patients admitted for lupus flares

• Published in: Lupus Vol. 32; no. 12; pp. 1418 - 1429
• Main Authors: Grovu, Radu, Huo, Yanran, Nguyen, Andrew, Mourad, Omar, Pan, Zihang, El-Gharib, Khalil, Wei, Chapman, Mustafa, Ahmad, Quan, Theodore, Slobodnick, Anastasia
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01-10-2023; Sage Publications Ltd
• Subjects: Comorbidity; Dialysis; Learning algorithms; Length of stay; Lupus; Machine learning; Renal failure; Systemic lupus erythematosus; length of stay; systemic lupus erythematosus; renal lupus; machine learning; subacute lupus erythematosus; lupus flare
• ISSN: 0961-2033; 1477-0962
• DOI: 10.1177/09612033231206830

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.