Abstract
We are among the many that believe that artificial intelligence will not replace practitioners and is most valuable as an adjunct in diagnostic radiology. We suggest a different approach to utilizing the technology, which may help even radiologists who may be averse to adopting AI. A novel method of leveraging AI combines computer vision and natural language processing to ambiently function in the background, monitoring for critical care gaps. This AI Quality workflow uses a visual classifier to predict the likelihood of a finding of interest, such as a lung nodule, and then leverages natural language processing to review a radiologist’s report, identifying discrepancies between imaging and documentation. Comparing artificial intelligence predictions with natural language processing report extractions with artificial intelligence in the background of computer-aided detection decisions may offer numerous potential benefits, including streamlined workflow, improved detection quality, an alternative approach to thinking of AI, and possibly even indemnity against malpractice. Here we consider early indications of the potential of artificial intelligence as the ultimate quality assurance for radiologists.
Similar content being viewed by others
References
Fenton JJ, Taplin SH, Carney PA, Abraham L, Sickles EA, D’Orsi C, Berns EA, Cutter G, Hendrick RE, Barlow WE, Elmore JG. Influence of computer-aided detection on performance of screening mammography. N Engl J Med. 2007 Apr 5;356(14):1399-409.
Ridley EL. Most radiology AI studies lack proper validation. AuntMinnie.com. March 8, 2019. https://www.auntminnie.com/index.aspx?sec=ser&sub=def&pag=dis&ItemID=124838. Accessed 4 Jan 2022.
Kaushal A, Altman R, Langlotz C. Geographic distribution of US cohorts used to train deep learning algorithms. JAMA. 2020 Sep 22;324(12):1212-1213.
Wiesner JB. A novel approach to accurately measuring the distribution of missed lung nodule within an institution using AI-enhanced peer review. Conference on Machine Intelligence in Medical Imaging. September 13–14, 2020.
Tan JR, Cheong EHT, Chan LP, Tham WP. Implementation of an artificial intelligence-based double read system in capturing pulmonary nodule discrepancy in CT studies. Curr Probl Diagn Radiol. 2021 Mar-Apr;50(2):119–122.
April D, Love M, Harrold R, Frischertz S, Kay D, Rudman E, et al. Identification of missed pulmonary nodules through machine learning and natural language processing. Poster presentation, American College of Radiology. October 20, 2020.
Bruno MA, Walker EA, Abujudeh HH. Understanding and confronting our mistakes: the epidemiology of error in radiology and strategies for error reduction. Radiographics. 2015 Oct;35(6):1668-76.
Lee KH, Goo JM, Park CM, Lee HJ, Jin KN. Computer-aided detection of malignant lung nodules on chest radiographs: effect on observers’ performance. Korean J Radiol. 2012 Sep-Oct;13(5):564–71.
Heaven WD. Jumbled-up sentences show that Ais still don’t really understand language. MIT Technology Review. January 12, 2021.
Author information
Authors and Affiliations
Contributions
All authors contributed equally to the writing of this manuscript.
Corresponding author
Ethics declarations
Conflict of Interest
Co-authors Weisberg, Chu, and Fishman received funding from the Lustgarten Foundation, and declare no conflicts of interest. Dr. Nguyen is the product manager of Transcarent, and Mr. Tran is the Chief Executive Officer of Ferrum Health, whose product is mentioned in this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Weisberg, E.M., Chu, L.C., Nguyen, B.D. et al. Is AI the Ultimate QA?. J Digit Imaging 35, 534–537 (2022). https://doi.org/10.1007/s10278-022-00598-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-022-00598-8