Use of an Artificial Intelligence Device for Evaluating Blood Loss in Complex Major Orthopaedic Surgery Procedures

An artificial intelligence algorithm that analyzes the pulse oximeter waveform in the fingertip can be used to determine the compensatory reserve index (CRI) in trauma patients. This measurement shows the remaining cardiovascular capacity and is known to be more specific and sensitive in detecting blood loss than are routine vital signs. We hypothesized that the CRI measurement could predict loss of reserve cardiovascular capacity in patients undergoing major orthopaedic surgery, and therefore could help in their management.

A total of 304 patients undergoing lower extremity arthroplasty consented to participate in waveform monitoring. Pulse oximeter waveforms were sensed with a fingertip probe and processed with a tablet computer that remained with the patient during surgery and recovery in the hospital. The CRI, systolic blood pressure, and heart rate were evaluated throughout the postoperative period.

The CRI measurement identified a group of patients who were significantly more likely to require transfusions and emergency medical care (P = .000021). Patients who had morbid obesity were especially likely to have low CRI results and a high percentage of clinical events. A CRI of 0.40 or more was evaluated retrospectively as the criterion for withholding transfusion in 54 patients, but that group had a significantly higher incidence of transfusion later in treatment than did the cohort as a whole. The systolic blood pressure and heart rate were not useful in predicting the need for transfusion until late in treatment.

This study suggests that the CRI measurement can identify patients at risk for transfusion and the need for urgent medical care and may aid in the management of blood loss and transfusion in major orthopedic surgery.