Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach
Background: The detrimental impact of fluid overload (FO) on intensive care unit (ICU) morbidity and mortality is well known. However, research to identify subgroups of patients particularly prone to fluid overload is scarce. The aim of this cohort study was to derive “FO phenotypes” in the critical...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/11/2/336 |
| _version_ | 1797493071792832512 |
|---|---|
| author | Anna S. Messmer Michel Moser Patrick Zuercher Joerg C. Schefold Martin Müller Carmen A. Pfortmueller |
| author_facet | Anna S. Messmer Michel Moser Patrick Zuercher Joerg C. Schefold Martin Müller Carmen A. Pfortmueller |
| author_sort | Anna S. Messmer |
| collection | DOAJ |
| description | Background: The detrimental impact of fluid overload (FO) on intensive care unit (ICU) morbidity and mortality is well known. However, research to identify subgroups of patients particularly prone to fluid overload is scarce. The aim of this cohort study was to derive “FO phenotypes” in the critically ill by using machine learning techniques. Methods: Retrospective single center study including adult intensive care patients with a length of stay of ≥3 days and sufficient data to compute FO. Data was analyzed by multivariable logistic regression, fast and frugal trees (FFT), classification decision trees (DT), and a random forest (RF) model. Results: Out of 1772 included patients, 387 (21.8%) met the FO definition. The random forest model had the highest area under the curve (AUC) (0.84, 95% CI 0.79–0.86), followed by multivariable logistic regression (0.81, 95% CI 0.77–0.86), FFT (0.75, 95% CI 0.69–0.79) and DT (0.73, 95% CI 0.68–0.78) to predict FO. The most important predictors identified in all models were lactate and bicarbonate at admission and postsurgical ICU admission. Sepsis/septic shock was identified as a risk factor in the MV and RF analysis. Conclusion: The FO phenotypes consist of patients admitted after surgery or with sepsis/septic shock with high lactate and low bicarbonate. |
| first_indexed | 2024-03-10T01:14:45Z |
| format | Article |
| id | doaj.art-ff8ae451e30f47e895c4ac87a5f6c0f4 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T01:14:45Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-ff8ae451e30f47e895c4ac87a5f6c0f42023-11-23T14:12:17ZengMDPI AGJournal of Clinical Medicine2077-03832022-01-0111233610.3390/jcm11020336Fluid Overload Phenotypes in Critical Illness—A Machine Learning ApproachAnna S. Messmer0Michel Moser1Patrick Zuercher2Joerg C. Schefold3Martin Müller4Carmen A. Pfortmueller5Department of Intensive Care Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Intensive Care Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Intensive Care Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Intensive Care Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Emergency Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandDepartment of Intensive Care Medicine, Inselspital, Bern University Hospital, University of Bern, 3010 Bern, SwitzerlandBackground: The detrimental impact of fluid overload (FO) on intensive care unit (ICU) morbidity and mortality is well known. However, research to identify subgroups of patients particularly prone to fluid overload is scarce. The aim of this cohort study was to derive “FO phenotypes” in the critically ill by using machine learning techniques. Methods: Retrospective single center study including adult intensive care patients with a length of stay of ≥3 days and sufficient data to compute FO. Data was analyzed by multivariable logistic regression, fast and frugal trees (FFT), classification decision trees (DT), and a random forest (RF) model. Results: Out of 1772 included patients, 387 (21.8%) met the FO definition. The random forest model had the highest area under the curve (AUC) (0.84, 95% CI 0.79–0.86), followed by multivariable logistic regression (0.81, 95% CI 0.77–0.86), FFT (0.75, 95% CI 0.69–0.79) and DT (0.73, 95% CI 0.68–0.78) to predict FO. The most important predictors identified in all models were lactate and bicarbonate at admission and postsurgical ICU admission. Sepsis/septic shock was identified as a risk factor in the MV and RF analysis. Conclusion: The FO phenotypes consist of patients admitted after surgery or with sepsis/septic shock with high lactate and low bicarbonate.https://www.mdpi.com/2077-0383/11/2/336fluid resuscitationfluid overloadintensive carerisk factors |
| spellingShingle | Anna S. Messmer Michel Moser Patrick Zuercher Joerg C. Schefold Martin Müller Carmen A. Pfortmueller Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach Journal of Clinical Medicine fluid resuscitation fluid overload intensive care risk factors |
| title | Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach |
| title_full | Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach |
| title_fullStr | Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach |
| title_full_unstemmed | Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach |
| title_short | Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach |
| title_sort | fluid overload phenotypes in critical illness a machine learning approach |
| topic | fluid resuscitation fluid overload intensive care risk factors |
| url | https://www.mdpi.com/2077-0383/11/2/336 |
| work_keys_str_mv | AT annasmessmer fluidoverloadphenotypesincriticalillnessamachinelearningapproach AT michelmoser fluidoverloadphenotypesincriticalillnessamachinelearningapproach AT patrickzuercher fluidoverloadphenotypesincriticalillnessamachinelearningapproach AT joergcschefold fluidoverloadphenotypesincriticalillnessamachinelearningapproach AT martinmuller fluidoverloadphenotypesincriticalillnessamachinelearningapproach AT carmenapfortmueller fluidoverloadphenotypesincriticalillnessamachinelearningapproach |