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.
Postoperative delirium (POD) is a common neurocognitive complication after cardiac surgery in elderly patients and is associated with adverse clinical outcomes. Impaired cerebral autoregulation and reduced cerebrovascular reserve may contribute to POD development. Automated transcranial Doppler sonography (TCD) enables non-invasive assessment of intracranial hemodynamics and may provide additional information for perioperative risk assessment. In this prospective single-center observational study, 108 patients aged >70 years scheduled for elective cardiac surgery with cardiopulmonary bypass were enrolled. Patients who had pre-existing neurological disease, had a pathological carotid Doppler ultrasound, underwent emergency surgery, or were unable to undergo delirium screening were excluded. Preoperative bilateral TCD of the middle cerebral arteries was performed using an automated WAKIe R3 system. POD was assessed on postoperative days 1–3 using the CAM-ICU. The primary endpoint was the occurrence of POD. Twenty-one patients were excluded, leaving 87 patients for analysis. POD occurred in 14 patients (16%). All patients who developed POD had pathological preoperative TCD findings, whereas no POD occurred among patients with normal TCD examinations. Overall, 82 patients (94%) demonstrated pathological intracranial hemodynamic findings despite normal carotid Doppler ultrasound. In multivariable Firth logistic regression adjusted for age and sex, pathological TCD findings remained associated with POD; however, interpretation was limited by the small number of outcome events and quasi-complete separation. In elderly patients undergoing cardiac surgery with cardiopulmonary bypass, pathological preoperative TCD findings were frequently observed and may be associated with an increased risk of postoperative delirium. The marked discrepancy between normal carotid ultrasound and abnormal intracranial hemodynamics suggests that TCD may provide complementary information regarding cerebrovascular function. Given the limited sample size and event rate, these findings should be considered exploratory and require confirmation in larger multicenter studies.