Predicting Mortality Using Machine Learning Algorithms in Patients Who Require Renal Replacement Therapy in the Critical Care Unit

Prediction of successful weaning from renal replacement therapy in critically ill patients based on machine learning

BACKGROUND

Predicting the successful weaning of acute kidney injury (AKI) patients from renal replacement therapy (RRT) has emerged as a research focus, and we successfully built predictive models for RRT withdrawal in patients with severe AKI by machine learning.

METHODS

This retrospective single-center study utilized data from our general intensive care unit (ICU) Database, focusing on patients diagnosed with severe AKI who underwent RRT. We evaluated RRT weaning success based on patients being free of RRT in the subsequent week and their overall survival. Multiple logistic regression (MLR) and machine learning algorithms were adopted to construct the prediction models.

RESULTS

A total of 976 patients were included, with 349 patients successfully weaned off RRT. Longer RRT duration (7.0 vs. 9.6 d, p = 0.002, OR = 0.94), higher serum cystatin C levels (1.2 vs. 3.2 mg/L, p < 0.001, OR = 0.46), and the presence of septic shock (28.1% vs. 41.5%, p < 0.001, OR = 0.63) were associated with reduced likelihood of RRT weaning. Conversely, a positive furosemide stress test (FST) (60.2% vs. 40.7%, p < 0.001, OR = 2.75) and higher total urine volume 3 d before RRT withdrawal (755 vs. 125 mL/d, p < 0.001, OR = 2.12) were associated with an increased likelihood of successful weaning from RRT. Next, we demonstrated that machine learning models, especially Random Forest and XGBoost, achieving an AUROC of 0.95. The XGBoost model exhibited superior accuracy, yielding an AUROC of 0.849.

CONCLUSION

High-risk factors for unsuccessful RRT weaning in severe AKI patients include prolonged RRT duration. Machine learning prediction models, when compared to models based on multivariate logistic regression using these indicators, offer distinct advantages in predictive accuracy.

Data-driven prediction of continuous renal replacement therapy survival

Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients are typically very ill to begin with, there is always uncertainty whether they will survive during or after CRRT treatment. Because of outcome uncertainty, a large percentage of patients treated with CRRT do not survive, utilizing scarce resources and raising false hope in patients and their families. To address these issues, we present a machine learning-based algorithm to predict short-term survival in patients being initiated on CRRT. We use information extracted from electronic health records from patients who were placed on CRRT at multiple institutions to train a model that predicts CRRT survival outcome; on a held-out test set, the model achieves an area under the receiver operating curve of 0.848 (CI = 0.822-0.870). Feature importance, error, and subgroup analyses provide insight into bias and relevant features for model prediction. Overall, we demonstrate the potential for predictive machine learning models to assist clinicians in alleviating the uncertainty of CRRT patient survival outcomes, with opportunities for future improvement through further data collection and advanced modeling.

Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients

Renal replacement therapy (RRT) is a crucial treatment for sepsis-associated acute kidney injury (S-AKI), but it is uncertain which S-AKI patients should receive immediate RRT. Identifying the characteristics of patients who may benefit the most from RRT is an important task. This retrospective study utilized a public database and enrolled S-AKI patients, who were divided into RRT and non-RRT groups. Uplift modeling was used to estimate the individual treatment effect (ITE) of RRT. The validity of different models was compared using a qini curve. After labeling the patients in the validation cohort, we characterized the patients who would benefit the most from RRT and created a nomogram. A total of 8289 patients were assessed, among whom 591 received RRT, and 7698 did not receive RRT. The RRT group had a higher severity of illness than the non-RRT group, with a Sequential Organ Failure Assessment (SOFA) score of 9 (IQR 6,11) vs. 5 (IQR 3,7). The 28-day mortality rate was higher in the RRT group than the non-RRT group (34.83% vs. 14.61%, p < 0.0001). Propensity score matching (PSM) was used to balance baseline characteristics, 458 RRT patients and an equal number of non-RRT patients were enrolled for further research. After PSM, 28-day mortality of RRT and non-RRT groups were 32.3% vs. 39.3%, P = 0.033. Using uplift modeling, we found that urine output, fluid input, mean blood pressure, body temperature, and lactate were the top 5 factors that had the most influence on RRT effect. The area under the uplift curve (AUUC) of the class transformation model was 0.068, the AUUC of SOFA was 0.018, and the AUUC of Kdigo-stage was 0.050. The class transformation model was more efficient in predicting individual treatment effect. A logistic regression model was developed, and a nomogram was drawn to predict whether an S-AKI patient can benefit from RRT. Six factors were taken into account (urine output, creatinine, lactate, white blood cell count, glucose, respiratory rate). Uplift modeling can better predict the ITE of RRT on S-AKI patients than conventional score systems such as Kdigo and SOFA. We also found that white blood cell count is related to the benefits of RRT, suggesting that changes in inflammation levels may be associated with the effects of RRT on S-AKI patients.

Specific patterns and potential risk factors to predict 3-year risk of death among non-cancer patients with advanced chronic kidney disease by machine learning

Chronic kidney disease (CKD) is a major public health concern. But there are limited machine learning studies on non-cancer patients with advanced CKD, and the results of machine learning studies on cancer patients with CKD may not apply directly on non-cancer patients. We aimed to conduct a comprehensive investigation of risk factors for a 3-year risk of death among non-cancer advanced CKD patients with an estimated glomerular filtration rate < 60.0 mL/min/1.73m2 by several machine learning algorithms. In this retrospective cohort study, we collected data from in-hospital and emergency care patients from 2 hospitals in Taiwan from 2009 to 2019, including their international classification of disease at admission and laboratory data from the hospital's electronic medical records (EMRs). Several machine learning algorithms were used to analyze the potential impact and degree of influence of each factor on mortality and survival. Data from 2 hospitals in northern Taiwan were collected with 6565 enrolled patients. After data cleaning, 26 risk factors and approximately 3887 advanced CKD patients from Shuang Ho Hospital were used as the training set. The validation set contained 2299 patients from Taipei Medical University Hospital. Predictive variables, such as albumin, PT-INR, and age, were the top 3 significant risk factors with paramount influence on mortality prediction. In the receiver operating characteristic curve, the random forest had the highest values for accuracy above 0.80. MLP, and Adaboost had better performance on sensitivity and F1-score compared to other methods. Additionally, SVM with linear kernel function had the highest specificity of 0.9983, while its sensitivity and F1-score were poor. Logistic regression had the best performance, with an area under the curve of 0.8527. Evaluating Taiwanese advanced CKD patients' EMRs could provide physicians with a good approximation of the patients' 3-year risk of death by machine learning algorithms.

Machine Learning Predicts 30-Day Outcome among Acute Myeloid Leukemia Patients: A Single-Center, Retrospective, Cohort Study

Acute myeloid leukemia (AML) is a clinical emergency requiring treatment and results in high 30-day (D30) mortality. In this study, the prediction of D30 survival was studied using a machine learning (ML) method. The total cohort consisted of 1700 survivors and 130 non-survivors at D30. Eight clinical and 42 laboratory variables were collected at the time of diagnosis by pathology. Among them, six variables were selected by a feature selection method: induction chemotherapy (CTx), hemorrhage, infection, C-reactive protein, blood urea nitrogen, and lactate dehydrogenase. Clinical and laboratory data were entered into the training model for D30 survival prediction, followed by testing. Among the tested ML algorithms, the decision tree (DT) algorithm showed higher accuracy, the highest sensitivity, and specificity values (95% CI) of 90.6% (0.918-0.951), 70.4% (0.885-0.924), and 92.1% (0.885-0.924), respectively. DT classified patients into eight specific groups with distinct features. Group 1 with CTx showed a favorable outcome with a survival rate of 97.8% (1469/1502). Group 6, with hemorrhage and the lowest fibrinogen level at diagnosis, showed the worst survival rate of 45.5% (25/55) and 20.5 days. Prediction of D30 survival among AML patients by classification of patients with DT showed distinct features that might support clinical decision-making.

Explainable ensemble machine learning model for prediction of 28-day mortality risk in patients with sepsis-associated acute kidney injury

Background

Sepsis-associated acute kidney injury (S-AKI) is a major contributor to mortality in intensive care units (ICU). Early prediction of mortality risk is crucial to enhance prognosis and optimize clinical decisions. This study aims to develop a 28-day mortality risk prediction model for S-AKI utilizing an explainable ensemble machine learning (ML) algorithm.

Methods

This study utilized data from the Medical Information Mart for Intensive Care IV (MIMIC-IV 2.0) database to gather information on patients with S-AKI. Univariate regression, correlation analysis and Boruta were combined for feature selection. To construct the four ML models, hyperparameters were tuned via random search and five-fold cross-validation. To evaluate the performance of all models, ROC, K-S, and LIFT curves were used. The discrimination of ML models and traditional scoring systems was compared using area under the receiver operating characteristic curve (AUC). Additionally, the SHapley Additive exPlanation (SHAP) was utilized to interpret the ML model and identify essential variables. To investigate the relationship between the top nine continuous variables and the risk of 28-day mortality. COX regression-restricted cubic splines were utilized while controlling for age and comorbidities.

Results

The study analyzed data from 9,158 patients with S-AKI, dividing them into a 28-day mortality group of 1,940 and a survival group of 7,578. The results showed that XGBoost was the best performing model of the four ML models with AUC of 0.873. All models outperformed APS-III 0.713 and SAPS-II 0.681. The K-S and LIFT curves indicated XGBoost as the most effective predictor for 28-day mortality risk. The model's performance was evaluated using ROCpr curves, calibration curves, accuracy, precision, and F1 scores. SHAP force plots were utilized to interpret and visualize the personalized predictive power of the 28-day mortality risk model. Additionally, COX regression restricted cubic splines revealed an interesting non-linear relationship between the top nine variables and 28-day mortality.

Conclusion

The use of ensemble ML models has shown to be more effective than the LR model and conventional scoring systems in predicting 28-day mortality risk in S-AKI patients. By visualizing the XGBoost model with the best predictive performance, clinicians are able to identify high-risk patients early on and improve prognosis.