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.