ML-based AI risk prediction using EHR data predicted cardiac surgery-associated acute kidney injury within 72 h with AUROC 0.79 and acute kidney disease at 30 days with AUROC 0.83 in adults undergoing cardiac surgery with cardiopulmonary bypass.
Observational (n=130)
Sí
Does an EHR-based machine learning model accurately predict acute kidney injury and acute kidney disease in patients undergoing cardiac surgery with cardiopulmonary bypass?
An EHR-based machine learning model provides clinically actionable discrimination for predicting acute kidney injury and acute kidney disease following cardiac surgery, enabling proactive risk management.
Estimación del efecto: AUROC 0.79 for CSA-AKI (95% CI 0.70-0.86); AUROC 0.83 for AKD at 30 days (95% CI 0.73-0.92) (95% CI 95% CI 0.70-0.86 for CSA-AKI; 0.73-0.92 for AKD)
valor p: p=<0.001 for differences in predicted risk between groups (ANOVA)
Introduction Acute kidney injury after cardiac surgery (CSA-AKI) is a common complication after cardiac surgery and an independent predictor of morbidity and mortality. Since evidence-based care is based on risk mitigation and implementation of supportive measures, early risk stratification and consequent adjustment of treatment strategies are elemental. Artificial intelligence screening can aid in pre- and perioperative risk stratification. Methods This is a secondary analysis of 130 prospectively recruited patients from one center of a multicenter observational trial that investigated the implementation of a bundle of supportive measures to prevent AKI in patients undergoing cardiac surgery with cardiopulmonary bypass. Machine learning (ML) enabled artificial intelligence (AI) was used to retrospectively analyze patients' electronic health record (EHR) data and generate an AKI risk estimate. The aim of this study was to investigate the feasibility of AI-based risk scores to predict AKI within 72 hours postoperatively and the development of acute kidney disease (AKD) at day 30 after surgery. Results Of 130 patients, 33.1% developed CSA-AKI. Of 119 with 30-day follow-up data, 18.5% developed AKD. Day-of-surgery AI risk-scoring was evaluated with an AUROC of 0.79 for occurrence of CSA-AKI, postoperative risk predictions were evaluated with an AUROC of 0.83 for AKD at 30 days postoperatively. ANOVA testing revealed that patients who developed CSA-AKI or AKD had significantly higher predicted risk scores than those who did not, with large effect sizes. Predicted risk also increased significantly over the perioperative period in patients with adverse outcomes. Conclusions Risk stratification with an ML-based AI approach based solely on EHR data provides a low-effort and high-yield screening method for identifying patients at risk of developing CSA-AKI and AKD. These findings indicate that an EHR (Electronic Health Record)-only model, trained on routine hospital data, provides clinically actionable discrimination in a real-world cardiac surgery cohort, supporting its use for early screening and targeted mitigation.
Fliegenschmidt et al. (Thu,) conducted a observational in Adults between 18 and 90 years undergoing cardiac surgery with cardiopulmonary bypass without preexisting acute kidney injury or chronic kidney disease (eGFR ≥20 mL/min/1.73 m² and no dialysis dependence) (n=130). Machine learning–based AI risk prediction model (clinalytix Medical AI) based on electronic health record data vs. No AI risk prediction (retrospective comparison of predicted risk scores with actual kidney outcomes) was evaluated on Prediction of cardiac surgery-associated acute kidney injury (CSA-AKI) within 72 hours after surgery and acute kidney disease (AKD) within 30 days after surgery based on AI risk scores (AUROC 0.79 for CSA-AKI (95% CI 0.70-0.86); AUROC 0.83 for AKD at 30 days (95% CI 0.73-0.92), 95% CI 95% CI 0.70-0.86 for CSA-AKI; 0.73-0.92 for AKD, p=<0.001 for differences in predicted risk between groups (ANOVA)). ML-based AI risk prediction using EHR data predicted cardiac surgery-associated acute kidney injury within 72 h with AUROC 0.79 and acute kidney disease at 30 days with AUROC 0.83 in adults undergoing cardiac surgery with cardiopulmonary bypass.