A Delphi Process to Identify Relevant Outcomes That May Be Associated With a Predictive Analytic Tool to Detect Hemodynamic Deterioration in the Intensive Care Unit

• Type of Material: Article
• Authors: Andre L. Holder, Emory University; Ashish K. Khanna, Wake Forest University; Michael J. Scott, University of Pennsylvania; Sarah C. Rossetti, Columbia University; Joseph B. Rinehart, University of California Irvine; Dustin D. Linn, Philips Research North America; Jochen Weichert, Philips Research Netherlands BV; R. Philip Dellinger, Cooper University
• Language: English
• Date: 2023-12-08
• Publisher: Cureus
• Publication Version: Final Published Version
• Copyright Statement: © 2023, Holder et al.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): https://doi.org/10.7759/cureus.50169
• Title of Journal or Parent Work: Cureus
• Volume: 15
• Issue: 12
• Start Page: e50169
• Grant/Funding Information: Dustin D. Linn, Jochen Weichert declare(s) employment from Philips. Andre L. Holder, Ashish K. Khanna, Michael J. Scott, Sarah C. Rossetti, Joseph B. Rinehart, R. Phillip Dellinger declare(s) personal fees from Philips. Authors were compensated for participation in the Delphi process; however, the decision to publish results was not decided until after the rounds of the process were complete and no payment was provided to for activities related to preparing the manuscript. Michael J. Scott declare(s) personal fees from Baxter. Advisory board. Ashish K. Khanna declare(s) personal fees from Caretaker Medical. Consultant. Ashish K. Khanna declare(s) personal fees from Retia Medical. Consultant. Ashish K. Khanna declare(s) personal fees from GE Healthcare. Consultant. Ashish K. Khanna declare(s) personal fees from Novartis. Consultant. Ashish K. Khanna declare(s) personal fees from Medtronic. Consultant. Andre L. Holder declare(s) personal fees from Baxter. Consulting. Ashish K. Khanna, Joseph B. Rinehart, Michael J. Scott declare(s) personal fees from Edwards Lifesciences. Consultant. Joseph B. Rinehart declare(s) royalties from Edwards Lifesciences. Michael J. Scott declare(s) personal fees from Deltex. Advisory Board. Ashish K. Khanna declare(s) personal fees from Baxter. Consultant
• Keywords: delphi method; adult intensive care; artificial intelligence and machine learning; decision support system; hemodynamic
• Research Categories: Artificial Intelligence; Health Sciences, Health Care Management

Abstract

Background The critical care literature has seen an increase in the development and validation of tools using artificial intelligence for early detection of patient events or disease onset in the intensive care unit (ICU). The hemodynamic stability index (HSI) was found to have an AUC of 0.82 in predicting the need for hemodynamic intervention in the ICU. Future studies using this tool may benefit from targeting those outcomes that are more relevant to clinicians and most achievable. Methods A three-round Delphi study was conducted with a panel of 10 critical care physicians and three nurses in the United States to identify outcomes that may be most relevant and achievable with the HSI when evaluated for use in the ICU. To achieve criteria for relevance, at least 65% of panelists had to rate an outcome as a 4 or 5 on a 5-point scale. Results Nineteen of 24 outcomes that may be associated with the HSI achieved consensus for relevance. The Kemeny-Young approach was used to develop a matrix depicting the distribution of outcomes considering both relevance and achievability. “Reduces time spent in hemodynamic instability” and “reduces times to recognition of hemodynamic instability” were the highest-ranking outcomes considering both relevance and achievability. Conclusion This Delphi study was a feasible method to identify relevant outcomes that may be associated with an appropriate predictive analytic tool in the ICU. These findings can provide insight to researchers looking to study such tools to impact outcomes relevant to critical care practitioners. Future studies should test these tools in the ICU that target the most clinically relevant and achievable outcomes, such as time spent hemodynamically unstable or time until actionable nursing assessment or treatment.