Clinical Research Directory

Intelligent Classification of Intraoperative Hemodynamic Phenotypes Based on CADFlow Doppler Monitoring

The goal of this observational study is to learn about intraoperative hemodynamic phenotypes in adult patients undergoing elective surgery under general anesthesia, using a new wearable ultrasound patch (CADFlow) that continuously monitors carotid and jugular blood flow. The main question it aims to answer is: Can a machine learning model built solely on non-invasive carotid and jugular Doppler data accurately identify and classify a patient's hemodynamic phenotype in real time during surgery? Participants undergoing routine elective surgery who are monitored with the CADFlow device as part of standard care will be recorded continuously from after tracheal intubation until the end of surgery. The collected signals will be used to discover distinct hemodynamic phenotypes and to train a model that classifies each patient's phenotype in real time.