Options
Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort
Date Issued
2021-08-17
Author(s)
Magunia, Harry
Lederer, Simone
Verbuecheln, Raphael
Gilot, Bryant J.
Koeppen, Michael
Haeberle, Helene A.
Mirakaj, Valbona
Hofmann, Pascal
Marx, Gernot
Bickenbach, Johannes
Nohe, Boris
Lay, Michael
Spies, Claudia
Edel, Andreas
Schiefenhövel, Fridtjof
Rahmel, Tim
Putensen, Christian
Sellmann, Timur
Koch, Thea
Brandenburger, Timo
Kindgen-Milles, Detlef
Brenner, Thorsten
Berger, Marc
Zacharowski, Kai
Adam, Elisabeth
Posch, Matthias
Scheer, Christian S.
Sedding, Daniel
Weigand, Markus A.
Fichtner, Falk
Nau, Carla
Prätsch, Florian
Wiesmann, Thomas
Koch, Christian
Schneider, Gerhard
Lahmer, Tobias
Straub, Andreas
Meiser, Andreas
Weiss, Manfred
Jungwirth, Bettina
Wappler, Frank
Meybohm, Patrick
Herrmann, Johannes
Malek, Nisar
Kohlbacher, Oliver
Biergans, Stephanie
Rosenberger, Peter
DOI
10.1186/s13054-021-03720-4
Abstract
Abstract
Background
Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes.
Methods
A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported.
Results
1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy.
Conclusions
Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models.
Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.
Background
Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes.
Methods
A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported.
Results
1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy.
Conclusions
Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models.
Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.
