The Promise and Challenges of Predictive Analytics in Perioperative Care

Abstract

This editorial accompanies the article on p. 283.

Prediction and Prevention of Intraoperative Hypotension with the Hypotension Prediction Index: A Narrative Review

“…In fact, Enevoldsen and Vistisen [ 41 ] analyzed data from the original [ 13 ] as well as subsequent validation studies and found that the AUC of all studies was skewed towards high specificity. This, as explained by the authors and an accompanying editorial [ 34 ], could potentially lead to an overestimation of the risk of hypotension with resulting overtreatment. On the other hand, the risk of hypertension has not emerged from the majority of the HPI studies (and neither was observed an increase in vasopressor of fluid consumption), suggesting that potential overtreatment might not be clinically relevant if the HPI and the treatment protocol are used correctly.…”

PRO: The hypotension prediction index is clinically relevant

“…We would like to speculate that the relatively more 'performant' HPI is because of the very strong physiologic/pathophysiologic basis of baroreflexes. The current debates that contest the computational approaches behind the HPI technology 13,[23][24][25] seem to ignore the physiologic/pathophysiologic basis of HPI. Criticism of HPI is relevant in that the performance of HPI should be tested against comparators that may be clinically credible 26 such as the continuous measurement of arterial blood pressure.…”

“…When anticipation of IOAH is simply based on the extrapolation of MAP trends, 12 there is no physiologic/pathophysiologic assumption behind this computational approach other than the probability that a parameter that is decreasing (MAP trend) will continue to decrease unless something (a corrective intervention) is done. Simply analysing ‘static’ or trending MAP values 13 is a computational approach that does not take into account underlying physiologic/pathophysiologic mechanisms that may predict occurrence of IOAH.…”

Enhancing anesthesia safety: evaluating artificial intelligence and augmented reality in reducing medication errors

“…36 For instance, AI algorithms can predict patient-specific risks, such as adverse reactions to anesthesia or potential complications, based on historical data, current physiological parameters, and responses to events intraoperatively. 36,37,38 This capability enhances the precision of dosing, monitoring, and intervention strategies, improving patient outcomes and safety. Moreover, AI-driven CDSS can assist in the early detection of critical events, such as hemodynamic instability or respiratory depression, allowing for prompt and informed responses.…”