Key result
A random forest machine learning model best predicted ICU mortality in children and young adults receiving continuous renal replacement therapy, achieving an AUROC of 0.791 and AUPRC of 0.878.
Why the study?
Predicting clinical outcomes for patients receiving CRRT is difficult due to population heterogeneity, varying clinical practices, and limited sample sizes.
Can machine learning models predict survival to ICU and hospital discharge in children and young adults receiving CRRT?
Observational (n=933)
Yes
Can machine learning models predict survival to ICU and hospital discharge in children and young adults receiving CRRT?
Effect estimate: AUROC 0.791
Machine learning models, particularly random forest and logistic regression, can predict ICU and hospital survival in children and young adults receiving CRRT.
ML models may aid survival prediction in young CRRT patients; leaves open clinical utility pending prospective validation.
BACKGROUND: Continuous renal replacement therapy (CRRT) is the favored renal replacement therapy in critically ill patients. Predicting clinical outcomes for CRRT patients is difficult due to population heterogeneity, varying clinical practices, and limited sample sizes. OBJECTIVE: We aimed to predict survival to ICUs and hospital discharge in children and young adults receiving CRRT using machine learning (ML) techniques. DERIVATION COHORT: Patients less than 25 years of age receiving CRRT for acute kidney injury and/or volume overload from 2015 to 2021 (80%). VALIDATION COHORT: Internal validation occurred in a testing group of patients from the dataset (20%). PREDICTION MODEL: Retrospective international multicenter study utilizing an 80/20 training and testing cohort split, and logistic regression with L2 regularization (LR), decision tree, random forest (RF), gradient boosting machine, and support vector machine with linear kernel to predict ICU and hospital survival. Model performance was determined by the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC) due to the imbalance in the dataset. RESULTS: Of the 933 patients included in this study, 538 (54%) were male with a median age of 8.97 years and interquartile range (1.81-15.0 yr). The ICU mortality was 35% and hospital mortality was 37%. The RF had the best performance for predicting ICU mortality (AUROC, 0.791 and AUPRC, 0.878) and LR for hospital mortality (AUROC, 0.777 and AUPRC, 0.859). The top two predictors of ICU survival were Pediatric Logistic Organ Dysfunction-2 score at CRRT initiation and admission diagnosis of respiratory failure. CONCLUSIONS: These are the first ML models to predict survival at ICU and hospital discharge in children and young adults receiving CRRT. RF outperformed other models for predicting ICU mortality. Future studies should expand the input variables, conduct a more sophisticated feature selection, and use deep learning algorithms to generate more precise models.
No takes yet. Share an insight, caveat, or question.
Thadani et al. (2024) conducted an observational in Acute kidney injury and/or volume overload requiring continuous renal replacement therapy (n=933). Machine learning prediction models was evaluated on ICU mortality and hospital mortality (AUROC 0.791). A random forest machine learning model best predicted ICU mortality in children and young adults receiving continuous renal replacement therapy, achieving an AUROC of 0.791 and AUPRC of 0.878.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: