Reliable Prediction of Intraoperative Hypotension using ML

Martin Jacobsson, Associate professor at Division for health informatics and logistics presents: Reliable Prediction of Intraoperative Hypotension using Machine Learning

Join on ZOOM: https://umu.zoom.us/j/62214336486

Abstract:

Hypotension during surgery is associated with an increased risk of postoperative complications including kidney injury, myocardial injury, and death. Early treatment of hypotension, preferably before the blood pressure drop, is critical to reducing the risk and severity of the complications. Today, systems are used that assess the patient's hemodynamical changes. However, it has been shown that information from the arterial blood pressure curve is useful in predicting whether hypotension is about to occur.

In this presentation, we introduce the problem and potential solutions based on machine learning classification for the early prediction of hypotension. We highlight encountered problems and present our preliminary results. These results also includes investigations of the reliability across different patient cohorts and different centers.