A Machine Learning-Based Prediction Model for Acute Kidney Injury in Patients With Congestive Heart Failure

Abstract

Background: Machine learning (ML) has been used to build high performance prediction model. Patients with congestive heart failure (CHF) are vulnerable to acute kidney injury (AKI) which makes treatment difficult. We aimed to establish an ML-based prediction model for the early identification of AKI in patients with CHF.

Methods: Patients data were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database, and patients with CHF were selected. Comparisons between several common ML classifiers were conducted to select the best prediction model. Recursive feature elimination (RFE) was used to select important prediction features. The model was improved using hyperparameters optimization (HPO). The final model was validated using an external validation set from the eICU Collaborative Research Database. The area under the receiver operating characteristic curve (AUROC), accuracy, calibration curve and decision curve analysis were used to evaluate prediction performance. Additionally, the final model was used to predict renal replacement therapy (RRT) requirement and to assess the short-term prognosis of patients with CHF. Finally, a software program was developed based on the selected features, which could intuitively report the probability of AKI.

Results: A total of 8,580 patients with CHF were included, among whom 2,364 were diagnosed with AKI. The LightGBM model showed the best prediction performance (AUROC = 0.803) among the 13 ML-based models. After RFE and HPO, the final model was established with 18 features including serum creatinine (SCr), blood urea nitrogen (BUN) and urine output (UO). The prediction performance of LightGBM was better than that of measuring SCr, UO or SCr combined with UO (AUROCs: 0.809, 0.703, 0.560 and 0.714, respectively). Additionally, the final model could accurately predict RRT requirement in patients with (AUROC = 0.954). Moreover, the participants were divided into high- and low-risk groups for AKI, and the 90-day mortality in the high-risk group was significantly higher than that in the low-risk group (log-rank p < 0.001). Finally, external validation using the eICU database comprising 9,749 patients with CHF revealed satisfactory prediction outcomes (AUROC = 0.816).

Conclusion: A prediction model for AKI in patients with CHF was established based on LightGBM, and the prediction performance of this model was better than that of other models. This model may help in predicting RRT requirement and in identifying the population with poor prognosis among patients with CHF.

Keywords: LightGBM; acute kidney injury; congestive heart failure; machine learning; prediction model.

Figure 1

Flow chart.

Figure 2

Comparisons of different machine learning models.

Figure 3

Features importance estimated using the Shapley Additive explanations (SHAP) values. (A) All 58 features, the blue to red color represents the feature value (red high, blue low). The x-axis measures the impacts on the model output (right positive, left negative); (B) Compact 18 features; (C) Significance of the predictors in the LightGBM model. CRE, creatinine; BUN, blood urea nitrogen; PO2, partial pressure of oxygen; UO, urine output; HR, heat rate; WBC, white blood cell; PCO2, partial pressure of carbon dioxygen; MAP, mean aortic pressure. RBC, red blood cell; PLT, platelet; CK, creatine kinase.

Figure 4

Hyperparameters optimization. (A) Each blue point represents the result of a trial, and the dark orange line represents the best AUROC value; (B) Each line represents a trial, the shade of color represents the performance of optimization; (C) the empirical distribution function of HPO.

Figure 5

Comparisons of full parameters, pre-HPO and after-HPO compacted parameters models.

Figure 6

Model evaluation and validation. (A) Comparisons of prediction performance between the compact model and measurements of creatinine, urine output, creatinine combined with urine output, and urea nitrogen; (B) Calibration curve; (C) Decision curve analysis; (D) Prediction of renal replacement therapy requirement using the LightGBM model; (E) Kaplan-Meier curve analysis of 90-day mortality between high-and low-risk groups divided using the LightGBM.

Figure 7

Comparisons of different machine learning models in external validation set.

Figure 8

An example of the prediction software.