Addressing the Challenges of Implementing Artificial Intelligence Tools in Clinical Practice: Principles From Experience

Bernardo C Bizzo; Giridhar Dasegowda; Christopher Bridge; Benjamin Miller; James M Hillis; Mannudeep K Kalra; Kimberly Durniak; Markus Stout; Thomas Schultz; Tarik Alkasab; Keith J Dreyer

doi:10.1016/j.jacr.2023.01.002

Addressing the Challenges of Implementing Artificial Intelligence Tools in Clinical Practice: Principles From Experience

J Am Coll Radiol. 2023 Mar;20(3):352-360. doi: 10.1016/j.jacr.2023.01.002.

Authors

Affiliations

¹ Senior Director, Data Science Office, Mass General Brigham, Boston, Massachusetts; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts. Electronic address: bbizzo@mgh.harvard.edu.
² Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts.
³ Data Science Office, Mass General Brigham, Boston, Massachusetts; Director of Clinical Operations, Data Science Office, Mass General Brigham, Boston, Massachusetts.
⁴ Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Director, Webster Center for Quality and Safety, Massachusetts General Hospital, Boston, Massachusetts.
⁵ Senior Director, Data Science Office, Mass General Brigham, Boston, Massachusetts.
⁶ Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Senior Director, Medical Imaging Informatics, Mass General Brigham, Boston, Massachusetts.
⁷ Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Senior Director, Enterprise Medical Imaging, Mass General Brigham, Boston, Massachusetts.
⁸ Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Associate Chair for Enterprise IT/Informatics, Massachusetts General Hospital, Boston, Massachusetts; Co-Medical Director, Medical Imaging Informatics, Mass General Brigham, Boston, Massachusetts.
⁹ Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts; Data Science Office, Mass General Brigham, Boston, Massachusetts; Chief Data Science Officer and Chief Imaging Information Officer, Mass General Brigham, Boston, Massachusetts; Vice Chair of Radiology, Massachusetts General Hospital, Boston, Massachusetts; Chief Science Officer, Data Science Institute, American College of Radiology, Reston, Virginia.

PMID: 36922109
DOI: 10.1016/j.jacr.2023.01.002

Abstract

The multitude of artificial intelligence (AI)-based solutions, vendors, and platforms poses a challenging proposition to an already complex clinical radiology practice. Apart from assessing and ensuring acceptable local performance and workflow fit to improve imaging services, AI tools require multiple stakeholders, including clinical, technical, and financial, who collaborate to move potential deployable applications to full clinical deployment in a structured and efficient manner. Postdeployment monitoring and surveillance of such tools require an infrastructure that ensures proper and safe use. Herein, the authors describe their experience and framework for implementing and supporting the use of AI applications in radiology workflow.

Keywords: Artificial intelligence; deployment; implementation; machine learning; radiology.

MeSH terms

Artificial Intelligence*
Commerce
Diagnostic Imaging
Radiology* / methods
Workflow