Non-invasive Hemodynamic Monitoring During Blood Donation for Developing Models of Early Blood Loss.

This study is part of a Phase II STTR project to develop an algorithm called CipherSensor to apply feature extraction and machine learning techniques to non-invasive hemodynamic data to identify early signs of acute blood loss. The availability of this information may help to establish required interventions for treating trauma patients and battlefield casualties.

Study hypothesis: Hemodynamic changes measured non-invasively during the blood donation process can be modeled to provide early estimations of blood loss.