Predicting outcomes of acute kidney injury in critically ill patients using machine learning

Haredasht, Fateme Nateghi; Viaene, Liesbeth; Pottel, Hans; Corte, Wouter De; Vens, Celine

doi:10.1038/s41598-023-36782-1

Cited by 4 publications

(1 citation statement)

References 30 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 9 In response to these challenges, recent advancements in machine learning (ML) techniques have demonstrated immense promise across various medical domains, particularly in the field of disease risk prediction, including CKD and acute kidney injury. 10 – 12 ML models possess the unique ability to discern intricate patterns and associations hidden within vast and diverse datasets, allowing for a more comprehensive understanding of CKD risk factors, and enhancing the precision of risk assessments. 11 By leveraging ML's computational power, we can potentially improve the predictive capabilities of CKD risk models, and with high accurate prediction, offering a more holistic and personalized approach to patient care and early intervention strategies.…”

Section: Introductionmentioning

confidence: 99%

Interpretable machine learning for predicting chronic kidney disease progression risk

Zheng,

Li,

Zhu

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

Objective Chronic kidney disease (CKD) poses a major global health burden. Early CKD risk prediction enables timely interventions, but conventional models have limited accuracy. Machine learning (ML) enhances prediction, but interpretability is needed to support clinical usage with both in diagnostic and decision-making. Methods A cohort of 491 patients with clinical data was collected for this study. The dataset was randomly split into an 80% training set and a 20% testing set. To achieve the first objective, we developed four ML algorithms (logistic regression, random forests, neural networks, and eXtreme Gradient Boosting (XGBoost)) to classify patients into two classes—those who progressed to CKD stages 3–5 during follow-up (positive class) and those who did not (negative class). For the classification task, the area under the receiver operating characteristic curve (AUC-ROC) was used to evaluate model performance in discriminating between the two classes. For survival analysis, Cox proportional hazards regression (COX) and random survival forests (RSFs) were employed to predict CKD progression, and the concordance index (C-index) and integrated Brier score were used for model evaluation. Furthermore, variable importance, partial dependence plots, and restrict cubic splines were used to interpret the models’ results. Results XGBOOST demonstrated the best predictive performance for CKD progression in the classification task, with an AUC-ROC of 0.867 (95% confidence interval (CI): 0.728–0.100), outperforming the other ML algorithms. In survival analysis, RSF showed slightly better discrimination and calibration on the test set compared to COX, indicating better generalization to new data. Variable importance analysis identified estimated glomerular filtration rate, age, and creatinine as the most important predictors for CKD survival analysis. Further analysis revealed non-linear associations between age and CKD progression, suggesting higher risks in patients aged 52–55 and 65–66 years. The association between cholesterol levels and CKD progression was also non-linear, with lower risks observed when cholesterol levels were in the range of 5.8–6.4 mmol/L. Conclusions Our study demonstrated the effectiveness of interpretable ML models for predicting CKD progression. The comparison between COX and RSF highlighted the advantages of ML in survival analysis, particularly in handling non-linearity and high-dimensional data. By leveraging interpretable ML for unraveling risk factor relationships, contrasting predictive techniques, and exposing non-linear associations, this study significantly advances CKD risk prediction to enable enhanced clinical decision-making.

show abstract

Section: Introductionmentioning

confidence: 99%

Interpretable machine learning for predicting chronic kidney disease progression risk

Zheng,

Li,

Zhu

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

show abstract

Evaluation of risk stratification for acute kidney injury: a comparative analysis of EKFC, 2009 and 2021 CKD-EPI glomerular filtration estimating equations

Cho,

Koh,

Kim

et al. 2024

J Nephrol

View full text Add to dashboard Cite

Background The adoption of the 2021 CKD-EPIcr equation for glomerular filtration rate (GFR) estimation provided a race-free eGFR calculation. However, the discriminative performance for AKI risk has been rarely validated. We aimed to evaluate the differences in acute kidney injury (AKI) prediction or reclassification power according to the three eGFR equations. Methods We performed a retrospective observational study within a tertiary hospital from 2011 to 2021. Acute kidney injury was defined according to KDIGO serum creatinine criteria. Glomerular filtration rate estimates were calculated by three GFR estimating equations: 2009 and 2021 CKD-EPIcr, and EKFC. In three equations, AKI prediction performance was evaluated with area under receiver operator curves (AUROC) and reclassification power was evaluated with net reclassification improvement analysis. Results A total of 187,139 individuals, including 27,447 (14.7%) AKI and 159,692 (85.3%) controls, were enrolled. In the multivariable regression prediction model, the 2009 CKD-EPIcr model (continuous eGFR model 2, 0.7583 [0.755–0.7617]) showed superior performance in AKI prediction to the 2021 CKD-EPIcr (0.7564 [0.7531–0.7597], < 0.001) or EKFC model in AUROC (0.7577 [0.7543–0.761], < 0.001). Moreover, in reclassification of AKI, the 2021 CKD-EPIcr and EKFC models showed a worse classification performance than the 2009 CKD-EPIcr model. (− 7.24 [− 8.21–− 6.21], − 2.38 [− 2.72–− 1.97]). Conclusion Regarding AKI risk stratification, the 2009 CKD-EPIcr equation showed better discriminative performance compared to the 2021 CKD-EPIcr equation in the study population. Graphical abstract

show abstract

Predictive approach for liberation from acute dialysis in ICU patients using interpretable machine learning

Wang,

Huang,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Renal recovery following dialysis-requiring acute kidney injury (AKI-D) is a vital clinical outcome in critical care, yet it remains an understudied area. This retrospective cohort study, conducted in a medical center in Taiwan from 2015 to 2020, enrolled patients with AKI-D during intensive care unit stays. We aimed to develop and temporally test models for predicting dialysis liberation before hospital discharge using machine learning algorithms and explore early predictors. The dataset comprised 90 routinely collected variables within the first three days of dialysis initiation. Out of 1,381 patients who received acute dialysis, 27.3% experienced renal recovery. The cohort was divided into the training group (N = 1135) and temporal testing group (N = 251). The models demonstrated good performance, with an area under the receiver operating characteristic curve of 0.85 (95% CI, 0.81–0.88) and an area under the precision-recall curve of 0.69 (95% CI, 0.62–0.76) for the XGBoost model. Key predictors included urine volume, Charlson comorbidity index, vital sign derivatives (trend of respiratory rate and SpO2), and lactate levels. We successfully developed early prediction models for renal recovery by integrating early changes in vital signs and inputs/outputs, which have the potential to aid clinical decision-making in the ICU.

show abstract

Predicting outcomes of acute kidney injury in critically ill patients using machine learning

Cited by 4 publications

References 30 publications

Interpretable machine learning for predicting chronic kidney disease progression risk

Interpretable machine learning for predicting chronic kidney disease progression risk

Evaluation of risk stratification for acute kidney injury: a comparative analysis of EKFC, 2009 and 2021 CKD-EPI glomerular filtration estimating equations

Predictive approach for liberation from acute dialysis in ICU patients using interpretable machine learning

Contact Info

Product

Resources

About