Perioperative Outcome Risk Assessment With Computer Learning Enhancement

NCT05042804 | Completed

• 1 other identifier: 202108022
• Study Type: interventional
• Target: 5,114
• Locations: 1 country
• Sites: 1

Brief Summary

This study will test whether anesthesiology clinicians working in a telemedicine setting can predict patient risk for postoperative complications (death and acute kidney injury) more accurately with access to a machine learning display than without it.

Conditions

Morality; Acute Kidney Injury

Outcome Measures

Primary Outcomes (2)

• Area under receiver-operating characteristic curve of clinician prediction for postoperative death

  Clinicians will predict the likelihood of postoperative death for each case using a categorical scale. A logistic regression will be constructed using the clinician predictions as inputs, and the area under the receiver-operating characteristic curve will be determined.

  30 days

• Area under receiver-operating characteristic curve of clinician prediction for postoperative acute kidney injury

  Clinicians will predict the likelihood of postoperative acute kidney injury for each case using a categorical scale. A logistic regression will be constructed using the clinician predictions as inputs, and the area under the receiver-operating characteristic curve will be determined.

  7 days

Study Arms (2)

Machine Learning Assistance

EXPERIMENTAL

Clinicians in the Anesthesia Control Tower will review patient data using the electronic health record and using AlertWatch, and they will also view the machine learning display. They will then predict how likely the patient is to experience postoperative death and postoperative acute kidney injury.

Other: Machine learning models predicting postoperative death and acute kidney injury

No Assistance

NO INTERVENTION

Clinicians in the Anesthesia Control Tower will review patient data using the electronic health record and using AlertWatch, but they will not view the machine learning display. They will then predict how likely the patient is to experience postoperative death and postoperative acute kidney injury.

Interventions

Machine learning models predicting postoperative death and acute kidney injury OTHER

The machine learning display uses data from the electronic health record to predict the likelihood of postoperative death and postoperative acute kidney injury.

Machine Learning Assistance

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Surgery in the main operating suite at Barnes-Jewish Hospital
• Surgery during hours of ACT operation (weekdays 7:00am-4:00pm)
• Enrolled in the TECTONICS randomized clinical trial (NCT03923699)

You may not qualify if:

• None

Sponsors & Collaborators

• Washington University School of Medicine: lead
• Foundation for Anesthesia Education and Research: collaborator

Study Sites (1)

Washington University School of Medicine

St Louis, Missouri, 63110, United States

Location

Related Publications (3)

• Fritz BA, King CR, Abdelhack M, Chen Y, Kronzer A, Abraham J, Tripathi S, Ben Abdallah A, Kannampallil T, Budelier TP, Helsten D, Montes de Oca A, Mehta D, Sontha P, Higo O, Kerby P, Gregory SH, Wildes TS, Avidan MS. Effect of machine learning models on clinician prediction of postoperative complications: the Perioperative ORACLE randomised clinical trial. Br J Anaesth. 2024 Nov;133(5):1042-1050. doi: 10.1016/j.bja.2024.08.004. Epub 2024 Sep 10.

  PMID: 39261226 DERIVED

• Fritz BA, King CR, Abdelhack M, Chen Y, Kronzer A, Abraham J, Tripathi S, Abdallah AB, Kannampallil T, Budelier TP, Helsten D, Montes de Oca A, Mehta D, Sontha P, Higo O, Kerby P, Gregory SH, Wildes TS, Avidan MS. Effect of Machine Learning on Anaesthesiology Clinician Prediction of Postoperative Complications: The Perioperative ORACLE Randomised Clinical Trial. medRxiv [Preprint]. 2024 May 23:2024.05.22.24307754. doi: 10.1101/2024.05.22.24307754.

  PMID: 38826471 DERIVED

• Fritz B, King C, Chen Y, Kronzer A, Abraham J, Ben Abdallah A, Kannampallil T, Budelier T, Montes de Oca A, McKinnon S, Tellor Pennington B, Wildes T, Avidan M. Protocol for the perioperative outcome risk assessment with computer learning enhancement (Periop ORACLE) randomized study. F1000Res. 2022 Sep 29;11:653. doi: 10.12688/f1000research.122286.2. eCollection 2022.

  PMID: 37547785 DERIVED

MeSH Terms

Conditions

Acute Kidney Injury

Condition Hierarchy (Ancestors)

Renal Insufficiency; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases

Study Officials

• Bradley A Fritz, MD

  Washington University School of Medicine

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Instructor in Anesthesiology

Study Record Dates

• First Submitted: September 1, 2021
• First Posted: September 13, 2021
• Study Start: September 1, 2021
• Primary Completion: November 1, 2022
• Study Completion: November 1, 2022
• Last Updated: November 14, 2022

Record last verified: 2022-11

Locations

US (1)