Needs Assessment Survey Identifying Research Processes Which may be Improved by Automation or Artificial Intelligence: ICU Community Modeling and Artificial Intelligence to Improve Efficiency (ICU-Comma)

Authors

Vincent I. Lau, University of Alberta
Alexandra Binnie, William Osler Health System
John Basmaji, Western University
Nadia Baig, University of Alberta
Dawn Opgenorth, University of Alberta
Saoirse Cameron, London Health Sciences CentreFollow
Katie O’Hearn, Children's Hospital of Eastern Ontario, Ottawa
Ellen McDonald, McMaster University
Janek Senaratne, University of Alberta
Wendy Sligl, University of Alberta
Danny J. Zuege, University of Calgary
Oleksa Rewa, University of Alberta
Sean M. Bagshaw, University of Alberta
Jennifer Tsang, McMaster University

Document Type

Article

Publication Date

1-1-2021

Journal

Journal of Intensive Care Medicine

URL with Digital Object Identifier

10.1177/08850666211064844

Abstract

Background: Critical care research in Canada is conducted primarily in academically-affiliated intensive care units with established research infrastructure, including research coordinators (RCs). Recently, efforts have been made to engage community hospital ICUs in research albeit with barriers. Automation or artificial intelligence (AI) could aid the performance of routine research tasks. It is unclear which research study processes might be improved through AI automation. Methods: We conducted a cross-sectional survey of Canadian ICU research personnel. The survey contained items characterizing opinions regarding research processes that may be amenable to AI automation. We distributed the questionnaire via email distribution lists of 3 Canadian research societies. Open-ended questions were analyzed using a thematic content analysis approach. Results: A total of 49 survey responses were received (response rate: 8%). Tasks that respondents felt were time-consuming/tedious/tiresome included: screening for potentially eligible patients (74%), inputting data into case report forms (65%), and preparing internal tracking logs (53%). Tasks that respondents felt could be performed by AI automation included: screening for eligible patients (59%), inputting data into case report forms (55%), preparing internal tracking logs (51%), and randomizing patients into studies (45%). Open-ended questions identified enthusiasm for AI automation to improve information accuracy and efficiency while freeing up RCs to perform tasks that require human interaction. This enthusiasm was tempered by the need for proper AI education and oversight. Conclusions: There were balanced supportive (increased efficiency and re-allocation of tasks) and challenges (informational accuracy and oversight) with regards to AI automation in ICU research.