Transcranial Doppler and Artificial Intelligence Prediction of Postoperative Delirium in Heart Valve Surgery
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorOsman Sila Aydin
About this trial
Postoperative delirium is a frequent complication after cardiac surgery. This prospective observational study will evaluate whether cerebral blood flow velocity measured by transcranial Doppler before and during elective heart valve surgery is associated with delirium during the first five postoperative days. Bispectral index, near-infrared spectroscopy, and arterial blood gas data will also be recorded. Delirium will be assessed daily by an independent evaluator who is blinded to the intraoperative measurements and artificial intelligence predictions, using CAM-ICU for mechanically ventilated patients or the Turkish 3D-CAM for patients on the ward.
The study will also compare zero-shot delirium risk predictions from five general-purpose large language models (Claude, GPT, Gemini, Grok, and Kimi) with the blinded clinical assessments. The models will not be trained on data from the study cohort.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 18 years or older
Scheduled for elective heart valve surgery
Undergoing surgery under general anesthesia according to the study's standardized anesthesia and analgesia protocol
Adequate signal quality for intraoperative BIS, NIRS, and transcranial Doppler measurements
Disqualifiers
Emergency or salvage surgery
Redo or reoperation cardiac surgery
Preoperative Standardized Mini-Mental State Examination score below 24 of 30, known dementia, active delirium, or psychotic disorder
Stroke or transient ischemic attack within the previous 3 months
Trial population
Adults scheduled for elective heart valve surgery at University of Health Sciences Bursa Yuksek Ihtisas Training and Research Hospital who meet the eligibility criteria.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Not listed
Trial groups
120 Participants
are grouped into 1 trial groupGroup A: Elective Heart Valve Surgery Cohort
Trial outcomes
Primary outcomes
1
Incidence of Postoperative Delirium
Postoperative delirium will be assessed once daily by an independent evaluator blinded to the intraoperative measurements and artificial intelligence predictions. CAM-ICU will be used for mechanically ventilated patients and the Turkish 3D-CAM will be used for patients on the ward. The participant-level outcome is the occurrence of at least one positive delirium assessment during the assessment period.
Time frame
Postoperative days 1 through 5Secondary outcomes
1
Association Between Baseline Middle Cerebral Artery Flow Velocity and Postoperative Delirium
Bilateral mean middle cerebral artery flow velocity will be measured preoperatively by transcranial Doppler in centimeters per second. The association between lower baseline flow velocity and the occurrence of postoperative delirium will be evaluated using logistic regression.
Time frame
Preoperative baseline through postoperative day 52
Association Between Intraoperative Relative Middle Cerebral Artery Flow Velocity and Postoperative Delirium
Mean middle cerebral artery flow velocity measured at the intraoperative TCD time points will be expressed as a percentage of the participant's preoperative baseline value. Exploratory analyses will evaluate whether relative hypoperfusion or hyperperfusion is associated with postoperative delirium.
Time frame
Intraoperative period through postoperative day 53
Predictive Performance of General-Purpose Large Language Models for Postoperative Delirium
Each of five fixed, recorded general-purpose large language model versions will generate an independent zero-shot delirium risk prediction using standardized perioperative data. Predictions will be locked before merging with the blinded reference outcome. Performance will be summarized using sensitivity, specificity, area under the receiver operating characteristic curve, and calibration; discrimination will be compared using the DeLong test.
Time frame
Perioperative prediction through postoperative day 5 reference assessmentSponsors and contacts
Click on the lead sponsor to view all of their trials.
Osman Sila Aydin
Lead sponsor
Bursa Sevket Yilmaz Training and Research Hospital
Sponsor institution
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: