Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Randomized Clinical Trials of Artificial Intelligence in Medicine: Why, When, and How?

  • Seong Ho Park (Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Joon-Il Choi (Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea) ;
  • Laure Fournier (Department of Radiology, Universite Paris Cite, AP-HP, Hopital Europeen Georges Pompidou) ;
  • Baptiste Vasey (Nuffield Department of Surgical Sciences, University of Oxford)
  • Received : 2022.10.29
  • Accepted : 2022.10.30
  • Published : 2022.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Keywords

References

  1. Newman TB, Browner WS, Cummings SR, Hulley SB. Designing studies of medical tests. In: Hulley SB, Cummings SR, Browner WS, Grady DG, Newman TB, eds. Designing clinical research, 4th ed. Philadelphia, PA: Lippincott Williams & Wilkins, 2013:171-187 
  2. Rodger M, Ramsay T, Fergusson D. Diagnostic randomized controlled trials: the final frontier. Trials 2012;13:137 
  3. Liu X, Rivera SC, Moher D, Calvert MJ, Denniston AK; SPIRITAI and CONSORT-AI Working Group. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension. BMJ 2020;370:m3164 
  4. Rivera SC, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRITAI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension. BMJ 2020;370:m3210 
  5. Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology 2018;286:800-809 
  6. Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nat Med 2022;28:31-38 
  7. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med 2019;17:195 
  8. NEJM Group. What is value-based healthcare? NEJM Catalyst Web site. https://catalyst.nejm.org/doi/full/10.1056/CAT.17.0558. Published January 1, 2017. Accessed October 30, 2022 
  9. Plana D, Shung DL, Grimshaw AA, Saraf A, Sung JJY, Kann BH. Randomized clinical trials of machine learning interventions in health care: a systematic review. JAMA Netw Open 2022;5:e2233946 
  10. Zhou Q, Chen ZH, Cao YH, Peng S. Clinical impact and quality of randomized controlled trials involving interventions evaluating artificial intelligence prediction tools: a systematic review. NPJ Digit Med 2021;4:154 
  11. Spadaccini M, Iannone A, Maselli R, Badalamenti M, Desai M, Chandrasekar VT, et al. Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis. Lancet Gastroenterol Hepatol 2021;6:793-802 
  12. Zhang Y, Zhang X, Wu Q, Gu C, Wang Z. Artificial intelligenceaided colonoscopy for polyp detection: a systematic review and meta-analysis of randomized clinical trials. J Laparoendosc Adv Surg Tech A 2021;31:1143-1149 
  13. Deliwala SS, Hamid K, Barbarawi M, Lakshman H, Zayed Y, Kandel P, et al. Artificial intelligence (AI) real-time detection vs. routine colonoscopy for colorectal neoplasia: a metaanalysis and trial sequential analysis. Int J Colorectal Dis 2021;36:2291-2303 
  14. Hassan C, Spadaccini M, Iannone A, Maselli R, Jovani M, Chandrasekar VT, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis. Gastrointest Endosc 2021;93:77-85. e6 
  15. Park SH, Choi J, Byeon JS. Key principles of clinical validation, device approval, and insurance coverage decisions of artificial intelligence. Korean J Radiol 2021;22:442-453 
  16. Paez A, Rovers M, Hutchison K, Rogers W, Vasey B, McCulloch P; IDEAL Collaboration. Beyond the RCT: when are randomized trials unnecessary for new therapeutic devices, and what should we do instead? Ann Surg 2022;275:324-331 
  17. Frieden TR. Evidence for health decision making - beyond randomized, controlled trials. N Engl J Med 2017;377:465-475 
  18. Rothwell PM. External validity of randomised controlled trials: "to whom do the results of this trial apply?". Lancet 2005;365:82-93 
  19. Park SH, Han K, Jang HY, Park JE, Lee JG, Kim DW, et al. Methods for clinical evaluation of artificial intelligence algorithms for medical diagnosis. Radiology 2022 Nov 8. [Epub]. https://doi.org/10.1148/radiol.220182 
  20. Vagal A, Saba L. Artificial intelligence in "code stroke"-a paradigm shift: do radiologists need to change their practice? Radiol Artif Intell 2022;4:e210204 
  21. Morey JR, Zhang X, Yaeger KA, Fiano E, Marayati NF, Kellner CP, et al. Real-world experience with artificial intelligence-based triage in transferred large vessel occlusion stroke patients. Cerebrovasc Dis 2021;50:450-455 
  22. Wijnberge M, Geerts BF, Hol L, Lemmers N, Mulder MP, Berge P, et al. Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial. JAMA 2020;323:1052-1060 
  23. Park SY, Park JE, Kim H, Park SH. Review of statistical methods for evaluating the performance of survival or other time-to-event prediction models (from conventional to deep learning approaches). Korean J Radiol 2021;22:1697-1707 
  24. Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ 2020;368:m689 
  25. Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. BMJ 2022;377:e070904 
  26. Skivington K, Matthews L, Simpson SA, Craig P, Baird J, Blazeby JM, et al. A new framework for developing and evaluating complex interventions: update of Medical Research Council guidance. BMJ 2021;374:n2061 
  27. Hirst A, Philippou Y, Blazeby J, Campbell B, Campbell M, Feinberg J, et al. No surgical innovation without evaluation: evolution and further development of the IDEAL framework and recommendations. Ann Surg 2019;269:211-220