Key result
New RCT protocol tests if machine learning improves anesthesiologist prediction of postoperative death or AKI.
Why the study?
Intraoperative telemedicine and machine learning tools may improve early identification of patients at risk for postoperative complications, but whether anesthesiology clinicians predict complications more accurately with machine learning assistance is unknown.
Does access to machine learning predictions improve the accuracy of anesthesiology clinicians in predicting postoperative complications?
RCT
randomized
Does access to machine learning predictions improve the accuracy of anesthesiology clinicians in predicting postoperative complications?
This protocol outlines a randomized study to determine if machine learning assistance improves the accuracy of anesthesiology clinicians in predicting postoperative complications via telemedicine.
This RCT will test whether ML assistance improves anesthesiology clinicians' accuracy in predicting postoperative complications; leaves open current practice until results emerge.
<ns4:p> <ns4:bold>Background:</ns4:bold> 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. </ns4:p> <ns4:p> <ns4:bold>Methods:</ns4:bold> 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. </ns4:p> <ns4:p> <ns4:bold>Conclusion:</ns4:bold> 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. </ns4:p> <ns4:p> <ns4:bold>Registration:</ns4:bold> ORACLE is registered on ClinicalTrials.gov: NCT05042804; registered September 13, 2021. </ns4:p>
No takes yet. Share an insight, caveat, or question.
Fritz et al. (2022) conducted an RCT in Postoperative complications (30-day in-hospital death or acute kidney injury). Machine learning predictions display vs. No access to machine learning predictions display was evaluated on Accuracy of predictions for 30-day in-hospital death or acute kidney injury. This study protocol describes a randomized trial to evaluate whether anesthesiology clinicians can predict postoperative complications more accurately with machine learning assistance than without.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: