ON THE COVER:
The Hypotension Prediction Index software is a machine learning algorithm that detects physiologic changes that may lead to hypotension; however, the original validation used a case control (backward) analysis that has been suggested to be biased. In this issue of Anesthesiology, Davies et al. conducted a cohort (forward) analysis and compared it to the original validation technique. It has also been recently suggested that the index algorithm is highly correlated with the mean arterial pressure itself. Therefore, Mulder et al. compared the index with mean arterial pressure–based prediction methods. In an accompanying editorial, Vistisen et al. analyze these new studies and the evaluation of artificial intelligence use in prediction models. Cover illustration: A. Johnson, Vivo Visuals Studio.
Davies et al.: Comparison of Differences in Cohort (Forward) and Case Control (Backward) Methodologic Approaches for Validation of the Hypotension Prediction Index, p. 443
Mulder et al.: Hypotension Prediction Index Is Equally Effective in Predicting Intraoperative Hypotension during Noncardiac Surgery Compared to a Mean Arterial Pressure Threshold: A Prospective Observational Study, p. 453
Vistisen et al.: Shedding Needed Light on a Black Box Approach to Prediction of Hypotension, p. 421
