Comparison of machine learning methods with logistic regression analysis in creating predictive models for risk of critical in-hospital events in COVID-19 patients on hospital admission

Autor: Aaron W. Sievering, Peter Wohlmuth, Nele Geßler, Melanie A. Gunawardene, Klaus Herrlinger, Berthold Bein, Dirk Arnold, Martin Bergmann, Lorenz Nowak, Christian Gloeckner, Ina Koch, Martin Bachmann, Christoph U. Herborn, Axel Stang
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: BMC Medical Informatics and Decision Making, Vol 22, Iss 1, Pp 1-14 (2022)
Druh dokumentu: article
ISSN: 1472-6947
36413089
DOI: 10.1186/s12911-022-02057-4
Popis: Abstract Background Machine learning (ML) algorithms have been trained to early predict critical in-hospital events from COVID-19 using patient data at admission, but little is known on how their performance compares with each other and/or with statistical logistic regression (LR). This prospective multicentre cohort study compares the performance of a LR and five ML models on the contribution of influencing predictors and predictor-to-event relationships on prediction model´s performance. Methods We used 25 baseline variables of 490 COVID-19 patients admitted to 8 hospitals in Germany (March–November 2020) to develop and validate (75/25 random-split) 3 linear (L1 and L2 penalty, elastic net [EN]) and 2 non-linear (support vector machine [SVM] with radial kernel, random forest [RF]) ML approaches for predicting critical events defined by intensive care unit transfer, invasive ventilation and/or death (composite end-point: 181 patients). Models were compared for performance (area-under-the-receiver-operating characteristic-curve [AUC], Brier score) and predictor importance (performance-loss metrics, partial-dependence profiles). Results Models performed close with a small benefit for LR (utilizing restricted cubic splines for non-linearity) and RF (AUC means: 0.763–0.731 [RF–L1]); Brier scores: 0.184–0.197 [LR–L1]). Top ranked predictor variables (consistently highest importance: C-reactive protein) were largely identical across models, except creatinine, which exhibited marginal (L1, L2, EN, SVM) or high/non-linear effects (LR, RF) on events. Conclusions Although the LR and ML models analysed showed no strong differences in performance and the most influencing predictors for COVID-19-related event prediction, our results indicate a predictive benefit from taking account for non-linear predictor-to-event relationships and effects. Future efforts should focus on leveraging data-driven ML technologies from static towards dynamic modelling solutions that continuously learn and adapt to changes in data environments during the evolving pandemic. Trial registration number: NCT04659187.
Databáze: Directory of Open Access Journals
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje