Protocol for the perioperative outcome risk assessment with computer learning enhancement (Periop ORACLE) randomized study

Abstract

Background: More than four million people die each year in the month following surgery, and many more experience complications such as acute kidney injury. Some of these outcomes may be prevented through early identification of at-risk patients and through intraoperative risk mitigation. Telemedicine has revolutionized the way at-risk patients are identified in critical care, but intraoperative telemedicine services are not widely used in anesthesiology. Clinicians in telemedicine settings may assist with risk stratification and brainstorm risk mitigation strategies while clinicians in the operating room are busy performing other patient care tasks. Machine learning tools may help clinicians in telemedicine settings leverage the abundant electronic health data available in the perioperative period. The primary hypothesis for this study is that anesthesiology clinicians can predict postoperative complications more accurately with machine learning assistance than without machine learning assistance. Methods: This investigation is a sub-study nested within the TECTONICS randomized clinical trial (NCT03923699). As part of TECTONICS, study team members who are anesthesiology clinicians working in a telemedicine setting are currently reviewing ongoing surgical cases and documenting how likely they feel the patient is to experience 30-day in-hospital death or acute kidney injury. For patients who are included in this sub-study, these case reviews will be randomized to be performed with access to a display showing machine learning predictions for the postoperative complications or without access to the display. The accuracy of the predictions will be compared across these two groups. Conclusion: Successful completion of this study will help define the role of machine learning not only for intraoperative telemedicine, but for other risk assessment tasks before, during, and after surgery. Registration: ORACLE is registered on ClinicalTrials.gov: NCT05042804; registered September 13, 2021.

Keywords: Anesthesiology; Machine Learning; Postoperative Complications; Protocol; Surgery.

Figure 1.. Simulation results from power calculation for death.

Power achieved in simulations of various sample sizes and effect sizes for postoperative death. Blue line is minimum clinically meaningful difference.

Figure 2.. Simulation results from power calculation for AKI.

Power achieved in simulations of various sample sizes and effect sizes for postoperative AKI. Blue line is minimum clinically meaningful difference.

Figure 3.. Flow chart showing treatment allocation.

Periop ORACLE participants will be randomizated to ML assistance or no ML assistance, stratified by intervention or control status of the parent TECTONICS trial.

Figure 4.. Case review form in AlertWatch.

The first two sections contain fields for documentation of clinician predictions of postoperative complications, and the Periop ORACLE randomization allocation is disclosed in the header of the second section. The treatment recommendations documented in the third section are utilized for the parent TECTONICS trial but not for this sub-study. The amount of time the clinician in the ACT spends completing each case review will be retrieved from the Epic audit log.