The Future of AI and Informatics in Radiology: 10 Predictions

HomeRadiologyVol. 309, No. 1 PreviousNext Reviews and CommentaryEditorial–Centennial ContentThe Future of AI and Informatics in Radiology: 10 PredictionsCurtis P. Langlotz Curtis P. Langlotz Author AffiliationsFrom the Departments of Radiology, Medicine, and Biomedical Data Science, Stanford University School of Medicine, 300 Pasteur Dr, Stanford, CA 94305.Address correspondence to the author (email: [email protected]).Curtis P. Langlotz Published Online:Oct 24 2023https://doi.org/10.1148/radiol.231114MoreSectionsFull textPDF ToolsAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookXLinked In References1. Schwartz WB. Medicine and the computer. The promise and problems of change. N Engl J Med 1970;283(23):1257–1264. Crossref, Medline, Google Scholar2. Center for Devices and Radiological Health. Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices. U.S. Food and Drug Administration. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices. Accessed April 15, 2023. Google Scholar3. Tiu E, Talius E, Patel P, Langlotz CP, Ng AY, Rajpurkar P. Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nat Biomed Eng 2022;6(12):1399–1406. Crossref, Medline, Google Scholar4. Berlin L. Accuracy of diagnostic procedures: has it improved over the past five decades? AJR Am J Roentgenol 2007;188(5):1173–1178. Crossref, Medline, Google Scholar5. Jamadar DA, Carlos R, Caoili EM, et al. Estimating the effects of informal radiology resident teaching on radiologist productivity: what is the cost of teaching? Acad Radiol 2005;12(1):123–128. Crossref, Medline, Google Scholar6. Naringrekar HV, Dave J, Akyol Y, Deshmukh SP, Roth CG. Comparing the productivity of teaching and non-teaching workflow models in an academic abdominal imaging division. Abdom Radiol (NY) 2021;46(6):2908–2912. Crossref, Medline, Google Scholar7. Wu JT, Wong KCL, Gur Y, et al. Comparison of chest radiograph interpretations by artificial intelligence algorithm vs radiology residents. JAMA Netw Open 2020;3(10):e2022779. Crossref, Medline, Google Scholar8. Buvat I, Weber W. Nuclear medicine from a novel perspective: Buvat and Weber talk with OpenAI's ChatGPT. J Nucl Med 2023;64(4):505–507. Crossref, Medline, Google Scholar9. Chang PJ. Imaging informatics: maturing beyond adolescence to enable the return of the doctor's doctor. Radiology 2023;309(1):e230936. Link, Google Scholar10. Krupinski E, Bronkalla M, Folio L, et al. Advancing the diagnostic cockpit of the future: an opportunity to improve diagnostic accuracy and efficiency. Acad Radiol 2019;26(4):579–581. Crossref, Medline, Google Scholar11. Schläpfer J, Wellens HJ. Computer-interpreted electrocardiograms: benefits and limitations. J Am Coll Cardiol 2017;70(9):1183–1192. Crossref, Medline, Google Scholar12. Landau MS, Pantanowitz L. Artificial intelligence in cytopathology: a review of the literature and overview of commercial landscape. J Am Soc Cytopathol 2019;8(4):230–241. Crossref, Medline, Google Scholar13. Leibig C, Brehmer M, Bunk S, Byng D, Pinker K, Umutlu L. Combining the strengths of radiologists and AI for breast cancer screening: a retrospective analysis. Lancet Digit Health 2022;4(7):e507–e519. Crossref, Medline, Google Scholar14. Sarraju A, Bruemmer D, Van Iterson E, Cho L, Rodriguez F, Laffin L. Appropriateness of cardiovascular disease prevention recommendations obtained from a popular online chat-based artificial intelligence model. JAMA 2023;329(10):842–844. Crossref, Medline, Google Scholar15. Nori H, King N, McKinney SM, Carignan D, Horvitz E. Capabilities of GPT-4 on medical challenge problems. arXiv 2303.13375 [preprint]. https://arxiv.org/abs/2303.13375. Posted March 20, 2023. Accessed May 2023. Google Scholar16. Zumbrun J. AI Bot ChatGPT Needs Some Help With Math Assignments. WSJ Online. https://www.wsj.com/articles/ai-bot-chatgpt-needs-some-help-with-math-assignments-11675390552. Published February 3, 2023. Accessed May 13, 2023. Google Scholar17. Hutto E. Dr. OpenAI Lied to Me. https://www.medpagetoday.com/opinion/faustfiles/102723. Published January 20, 2023. Accessed May 13, 2023. Google Scholar18. Harvey H, Pogose M. How to get ChatGPT regulatory approved as a medical device. Hardian Health. https://www.hardianhealth.com/blog/how-to-get-regulatory-approval-for-medical-large-language-models. Published April 5, 2023. Accessed May 13, 2023. Google Scholar19. 21st Century Cures Act, HR 34, 114th Cong (2015). Google Scholar20. Elkassem AA, Smith AD. Potential use cases for ChatGPT in radiology reporting. AJR Am J Roentgenol 2023AJR.23.29198. Google Scholar21. OpenAI. GPT-3.5. https://chat.openai.com. Accessed April 28, 2023. Google Scholar22. Acosta JN, Falcone GJ, Rajpurkar P, Topol EJ. Multimodal biomedical AI. Nat Med 2022;28(9):1773–1784. Crossref, Medline, Google Scholar23. Krishnan R, Rajpurkar P, Topol EJ. Self-supervised learning in medicine and healthcare. Nat Biomed Eng 2022;6(12):1346–1352. Crossref, Medline, Google Scholar24. Eng D, Chute C, Khandwala N, et al. Automated coronary calcium scoring using deep learning with multicenter external validation. NPJ Digit Med 2021;4(1):88. Crossref, Medline, Google Scholar25. Pickhardt PJ. Value-added opportunistic CT screening: state of the art. Radiology 2022;303(2):241–254. Link, Google Scholar26. Vreeland A, Persons KR, Primo HR, et al. Considerations for exchanging and sharing medical images for improved collaboration and patient care: HIMSS-SIIM collaborative white paper. J Digit Imaging 2016;29(5):547–558. Crossref, Medline, Google Scholar27. Sodickson A, Opraseuth J, Ledbetter S. Outside imaging in emergency department transfer patients: CD import reduces rates of subsequent imaging utilization. Radiology 2011;260(2):408–413. Link, Google Scholar28. Flanagan PT, Relyea-Chew A, Gross JA, Gunn ML. Using the Internet for image transfer in a regional trauma network: effect on CT repeat rate, cost, and radiation exposure. J Am Coll Radiol 2012;9(9):648–656. Crossref, Medline, Google Scholar29. Scott KW, Liu A, Chen C, et al. Healthcare spending in U.S. emergency departments by health condition, 2006–2016. PLoS One 2021;16(10):e0258182. Crossref, Medline, Google Scholar30. Kassavin MH, Parikh KD, Tirumani SH, Ramaiya NH. Trends in Medicare Part B payments and utilization for imaging services between 2009 and 2019. Curr Probl Diagn Radiol 2022;51(4):478–485. Crossref, Medline, Google Scholar31. Vest JR, Kaushal R, Silver MD, Hentel K, Kern LM. Health information exchange and the frequency of repeat medical imaging. Am J Manag Care 2014;20(11 Spec No. 17):eSP16–eSP24. Medline, Google Scholar32. Larson DB, Magnus DC, Lungren MP, Shah NH, Langlotz CP. Ethics of using and sharing clinical imaging data for artificial intelligence: a proposed framework. Radiology 2020;295(3):675–682. Link, Google Scholar33. Huang SC, Pareek A, Jensen M, Lungren MP, Yeung S, Chaudhari AS. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digit Med 2023;6(1):74. Crossref, Medline, Google Scholar34. Bommasani R, Hudson DA, Adeli E, et al. On the opportunities and risks of foundation models. arXiv 2108.07258 [preprint] https://arxiv.org/abs/2108.07258. Posted August 16, 2021. Accessed May 2023. Google Scholar35. Center for Devices and Radiological Health. Marketing Submission Recommendations for a Predetermined Change Control Plan for Artificial Intelligence/Machine Learning (AI/ML)-Enabled Device Software Functions. U.S. Food and Drug Administration. https://www.fda.gov/regulatory-information/search-fda-guidance-documents/marketing-submission-recommendations-predetermined-change-control-plan-artificial. Published April 3, 2023. Accessed April 15, 2023. Google Scholar36. Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis 2015;115(3):211–252. Crossref, Google Scholar37. Kaushal A, Altman R, Langlotz C. Geographic distribution of US cohorts used to train deep learning algorithms. JAMA 2020;324(12):1212–1213. Crossref, Medline, Google Scholar38. MIDRC Web site. https://www.midrc.org. Accessed April 15, 2023. Google Scholar39. Haendel MA, Chute CG, Bennett TD, et al. The National COVID Cohort Collaborative (N3C): rationale, design, infrastructure, and deployment. J Am Med Inform Assoc 2021;28(3):427–443. Crossref, Medline, Google Scholar40. Mei X, Liu Z, Robson PM, et al. RadImageNet: an open radiologic deep learning research dataset for effective transfer learning. Radiol Artif Intell 2022;4(5):e210315. Link, Google Scholar41. Sankar PL, Parker LS. The Precision Medicine Initiative's All of Us Research Program: an agenda for research on its ethical, legal, and social issues. Genet Med 2017;19(7):743–750. Crossref, Medline, Google Scholar42. Bennett AM, Ulrich H, van Damme P, Wiedekopf J, Johnson AEW. MIMIC-IV on FHIR: converting a decade of in-patient data into an exchangeable, interoperable format. J Am Med Inform Assoc 2023;30(4):718–725. Crossref, Medline, Google Scholar43. Flanders AE, Prevedello LM, Shih G, et al. Construction of a machine learning dataset through collaboration: the RSNA 2019 Brain CT Hemorrhage Challenge. Radiol Artif Intell 2020;2(3):e190211. Link, Google Scholar44. Shared Datasets. Center for Artificial Intelligence in Medicine & Imaging. https://aimi.stanford.edu/shared-datasets. Accessed April 15, 2023. Google Scholar45. Chen IY, Pierson E, Rose S, Joshi S, Ferryman K, Ghassemi M. Ethical machine learning in healthcare. Annu Rev Biomed Data Sci 2021;4(1):123–144. Crossref, Medline, Google Scholar46. Recht MP, Dewey M, Dreyer K, et al. Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations. Eur Radiol 2020;30(6):3576–3584. Crossref, Medline, Google ScholarArticle HistoryReceived: Apr 29 2023Revision requested: May 12 2023Revision received: May 16 2023Accepted: May 22 2023Published online: Oct 24 2023 FiguresReferencesRelatedDetailsCited ByInvited Commentary: The Double-edged Sword of Bias in Medical Imaging Artificial IntelligencePouria Rouzrokh, Bradley J. Erickson, 18 April 2024 | RadioGraphics, Vol. 44, No. 5Human-AI Symbiosis: A Path Forward to Improve Chest Radiography and the Role of Radiologists in Patient CareWarren B. Gefter, Mathias Prokop, Joon Beom Seo, Suhail Raoof, Curtis P. Langlotz, Hiroto Hatabu, 23 January 2024 | Radiology, Vol. 310, No. 1Editor's Note: 2023—The Year in Review for RadiologyLinda Moy, 30 January 2024 | Radiology, Vol. 310, No. 1Development and optimization of AI algorithms for wrist fracture detection in children using a freely available datasetTristanTill, SebastianTschauner, GeorgSinger, KlausLichtenegger, HolgerTill21 December 2023 | Frontiers in Pediatrics, Vol. 11Accompanying This ArticleFuture of AI and InformaticsJan 30 2024Default Digital Object SeriesRecommended Articles Deep Learning: A Primer for RadiologistsRadioGraphics2017Volume: 37Issue: 7pp. 2113-2131Clinical Validation Is the Key to Adopting AI in Clinical PracticeRadiology: Artificial Intelligence2021Volume: 3Issue: 4Current Applications and Future Impact of Machine Learning in RadiologyRadiology2018Volume: 288Issue: 2pp. 318-328Preparing Medical Imaging Data for Machine LearningRadiology2020Volume: 295Issue: 1pp. 4-15Machine Learning Applied to Alzheimer DiseaseRadiology2016Volume: 281Issue: 3pp. 665-668See More RSNA Education Exhibits Why AI Misses Small Organs and How to Improve Their Recognition PerformancesDigital Posters2020Outsmarting AI: What Role Can The Radiologist Play In The Making And Deployment Of Artificial Intelligence ApplicationsDigital Posters2021Uncertainty Estimation in Auto-Segmentation and Image Reconstruction TasksDigital Posters2022 RSNA Case Collection Ischemic stroke in moyamoya diseaseRSNA Case Collection2020Intermittent Port Malfunction RSNA Case Collection2021Fahr's syndromeRSNA Case Collection2021 Vol. 309, No. 1 PodcastMetrics Altmetric Score PDF download