Key result
A multilayer perceptron with long short-term memory (MLP + LSTM) model outperformed other approaches for predicting RRT-free survival (AUROC 0.70; 95% CI 0.67-0.73).
Why the study?
Continuous renal replacement therapy is preferred in hemodynamically unstable critically ill patients with acute kidney injury, but predicting clinical outcomes in these patients remains challenging.
Can machine learning models accurately predict renal replacement therapy-free survival in critically ill patients with AKI requiring CRRT?
Observational (n=684)
Can machine learning models accurately predict renal replacement therapy-free survival in critically ill patients with AKI requiring CRRT?
A multilayer perceptron with long short-term memory (MLP + LSTM) model outperformed traditional and other machine learning approaches in predicting renal replacement therapy-free survival in critically ill patients with AKI.
BACKGROUND/AIMS: Acute kidney injury (AKI) in critically ill patients is common, and continuous renal replacement therapy (CRRT) is a preferred mode of renal replacement therapy (RRT) in hemodynamically unstable patients. Prediction of clinical outcomes in patients on CRRT is challenging. We utilized several approaches to predict RRT-free survival (RRTFS) in critically ill patients with AKI requiring CRRT. METHODS: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify patients ≥18 years old with AKI on CRRT, after excluding patients who had ESRD on chronic dialysis, and kidney transplantation. We defined RRTFS as patients who were discharged alive and did not require RRT ≥7 days prior to hospital discharge. We utilized all available biomedical data up to CRRT initiation. We evaluated 7 approaches, including logistic regression (LR), random forest (RF), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), and MLP with long short-term memory (MLP + LSTM). We evaluated model performance by using area under the receiver operating characteristic (AUROC) curves. RESULTS: Out of 684 patients with AKI on CRRT, 205 (30%) patients had RRTFS. The median age of patients was 63 years and their median Simplified Acute Physiology Score (SAPS) II was 67 (interquartile range 52-84). The MLP + LSTM showed the highest AUROC (95% CI) of 0.70 (0.67-0.73), followed by MLP 0.59 (0.54-0.64), LR 0.57 (0.52-0.62), SVM 0.51 (0.46-0.56), AdaBoost 0.51 (0.46-0.55), RF 0.44 (0.39-0.48), and XGBoost 0.43 (CI 0.38-0.47). CONCLUSIONS: A MLP + LSTM model outperformed other approaches for predicting RRTFS. Performance could be further improved by incorporating other data types.
No takes yet. Share an insight, caveat, or question.
Pattharanitima et al. (2021) conducted an observational in Acute kidney injury requiring continuous renal replacement therapy (n=684). Multilayer perceptron with long short-term memory (MLP + LSTM) model vs. Other machine learning models (MLP, LR, SVM, AdaBoost, RF, XGBoost) was evaluated on Prediction of renal replacement therapy-free survival (AUROC) (AUROC 0.70, 95% CI 0.67-0.73). A multilayer perceptron with long short-term memory (MLP + LSTM) model outperformed other approaches for predicting RRT-free survival (AUROC 0.70; 95% CI 0.67-0.73).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: