{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:48:07Z","timestamp":1775872087035,"version":"3.50.1"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,8]],"date-time":"2023-04-08T00:00:00Z","timestamp":1680912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,8]],"date-time":"2023-04-08T00:00:00Z","timestamp":1680912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>There is a growing gap between studies describing the capabilities of artificial intelligence (AI) diagnostic systems using deep learning versus efforts to investigate how or when to integrate AI systems into a real-world clinical practice to support physicians and improve diagnosis. To address this gap, we investigate four potential strategies for AI model deployment and physician collaboration to determine their potential impact on diagnostic accuracy. As a case study, we examine an AI model trained to identify findings of the acute respiratory distress syndrome (ARDS) on chest X-ray images. While this model outperforms physicians at identifying findings of ARDS, there are several reasons why fully automated ARDS detection may not be optimal nor feasible in practice. Among several collaboration strategies tested, we find that if the AI model first reviews the chest X-ray and defers to a physician if it is uncertain, this strategy achieves a higher diagnostic accuracy (0.869, 95% CI 0.835\u20130.903) compared to a strategy where a physician reviews a chest X-ray first and defers to an AI model if uncertain (0.824, 95% CI 0.781\u20130.862), or strategies where the physician reviews the chest X-ray alone (0.808, 95% CI 0.767\u20130.85) or the AI model reviews the chest X-ray alone (0.847, 95% CI 0.806\u20130.887). If the AI model reviews a chest X-ray first, this allows the AI system to make decisions for up to 79% of cases, letting physicians focus on the most challenging subsets of chest X-rays.<\/jats:p>","DOI":"10.1038\/s41746-023-00797-9","type":"journal-article","created":{"date-parts":[[2023,4,8]],"date-time":"2023-04-08T05:02:55Z","timestamp":1680930175000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Collaborative strategies for deploying artificial intelligence to complement physician diagnoses of acute respiratory distress syndrome"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1200-5274","authenticated-orcid":false,"given":"Negar","family":"Farzaneh","sequence":"first","affiliation":[]},{"given":"Sardar","family":"Ansari","sequence":"additional","affiliation":[]},{"given":"Elizabeth","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5939-409X","authenticated-orcid":false,"given":"Kevin R.","family":"Ward","sequence":"additional","affiliation":[]},{"given":"Michael W.","family":"Sjoding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,8]]},"reference":[{"key":"797_CR1","unstructured":"Rajpurkar, P., Hannun, A. Y., Haghpanahi, M, C., Bourn, C. & Ng A. Y. Cardiologist-level arrhythmia detection with convolutional neural networks. Preprint at: arXiv:1707.01836 (2017)."},{"key":"797_CR2","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","volume":"25","author":"AY Hannun","year":"2019","unstructured":"Hannun, A. Y. et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 25, 65\u201369 (2019).","journal-title":"Nat. Med."},{"key":"797_CR3","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1111\/j.1755-3768.2012.02435.x","volume":"91","author":"S Andersson","year":"2013","unstructured":"Andersson, S., Heijl, A., Bizios, D. & Bengtsson, B. Comparison of clinicians and an artificial neural network regarding accuracy and certainty in performance of visual field assessment for the diagnosis of glaucoma. Acta Ophthalmol. 91, 413\u2013417 (2013).","journal-title":"Acta Ophthalmol."},{"key":"797_CR4","unstructured":"Rajpurkar, P. et al. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. Preprint at arXiv:1711.05225 (2017)."},{"key":"797_CR5","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356 (2019).","journal-title":"Nat. Med."},{"key":"797_CR6","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1038\/s41591-020-0942-0","volume":"26","author":"P Tschandl","year":"2020","unstructured":"Tschandl, P. et al. Human-computer collaboration for skin cancer recognition. Nat. Med. 26, 1229\u20131234 (2020).","journal-title":"Nat. Med."},{"key":"797_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00322-2","volume":"3","author":"P Rajpurkar","year":"2020","unstructured":"Rajpurkar, P. et al. CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV. NPJ Digit. Med. 3, 1\u20138 (2020).","journal-title":"NPJ Digit. Med."},{"key":"797_CR8","doi-asserted-by":"publisher","first-page":"e2141096","DOI":"10.1001\/jamanetworkopen.2021.41096","volume":"4","author":"F Homayounieh","year":"2021","unstructured":"Homayounieh, F. et al. An artificial intelligence\u2013based chest x-ray model on human nodule detection accuracy from a multicenter study. JAMA Netw. open 4, e2141096\u2013e2141096 (2021).","journal-title":"JAMA Netw. open"},{"key":"797_CR9","doi-asserted-by":"publisher","first-page":"e1002699","DOI":"10.1371\/journal.pmed.1002699","volume":"15","author":"N Bien","year":"2018","unstructured":"Bien, N. et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet. PLoS Med. 15, e1002699 (2018).","journal-title":"PLoS Med."},{"key":"797_CR10","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1056\/NEJM200005043421806","volume":"342","author":"LB Ware","year":"2000","unstructured":"Ware, L. B. & Matthay, M. A. The acute respiratory distress syndrome. N. Engl. J. Med. 342, 1334\u20131349 (2000).","journal-title":"N. Engl. J. Med."},{"key":"797_CR11","doi-asserted-by":"publisher","first-page":"1685","DOI":"10.1056\/NEJMoa050333","volume":"353","author":"GD Rubenfeld","year":"2005","unstructured":"Rubenfeld, G. D. et al. Incidence and outcomes of acute lung injury. N. Engl. J. Med. 353, 1685\u20131693 (2005).","journal-title":"N. Engl. J. Med."},{"key":"797_CR12","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/JBHI.2018.2810820","volume":"23","author":"N Reamaroon","year":"2018","unstructured":"Reamaroon, N., Sjoding, M. W., Lin, K., Iwashyna, T. J. & Najarian, K. Accounting for label uncertainty in machine learning for detection of acute respiratory distress syndrome. IEEE J. Biomed. Health Inform. 23, 407\u2013415 (2018).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"797_CR13","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1001\/jama.2016.0291","volume":"315","author":"G Bellani","year":"2016","unstructured":"Bellani, G. et al. Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries. JAMA 315, 788\u2013800 (2016).","journal-title":"JAMA"},{"key":"797_CR14","first-page":"2526","volume":"307","author":"ADT Force","year":"2012","unstructured":"Force, A. D. T. et al. Acute respiratory distress syndrome. JAMA 307, 2526\u20132533 (2012).","journal-title":"JAMA"},{"key":"797_CR15","doi-asserted-by":"publisher","first-page":"1573","DOI":"10.1007\/s00134-012-2682-1","volume":"38","author":"ND Ferguson","year":"2012","unstructured":"Ferguson, N. D. et al. The Berlin definition of ARDS: an expanded rationale, justification, and supplementary material. Intensive Care Med. 38, 1573\u20131582 (2012).","journal-title":"Intensive Care Med."},{"key":"797_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12890-019-0803-0","volume":"19","author":"T Kamo","year":"2019","unstructured":"Kamo, T. et al. Prognostic values of the Berlin definition criteria, blood lactate level, and fibroproliferative changes on high-resolution computed tomography in ARDS patients. BMC Pulm. Med. 19, 1\u20139 (2019).","journal-title":"BMC Pulm. Med."},{"key":"797_CR17","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/j.chest.2017.11.037","volume":"153","author":"MW Sjoding","year":"2018","unstructured":"Sjoding, M. W. et al. Interobserver reliability of the Berlin ARDS definition and strategies to improve the reliability of ARDS diagnosis. Chest 153, 361\u2013367 (2018).","journal-title":"Chest"},{"key":"797_CR18","doi-asserted-by":"publisher","first-page":"e340","DOI":"10.1016\/S2589-7500(21)00056-X","volume":"3","author":"MW Sjoding","year":"2021","unstructured":"Sjoding, M. W. et al. Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation. Lancet Digit. Health 3, e340\u2013e348 (2021).","journal-title":"Lancet Digit. Health"},{"key":"797_CR19","unstructured":"Available at: https:\/\/oxipit.ai\/products\/chesteye\/. Accessed: March 2023."},{"key":"797_CR20","unstructured":"Se\u00e7kin, A. \u00c7., Gen\u00e7er, \u00c7. & Yildirim, M. Deep learning structures used in pulmonary cancer diagnosis. Res. Rev. Health Sci. 1912, (2021)."},{"key":"797_CR21","doi-asserted-by":"crossref","unstructured":"Tadavarthi, Y., Gichoya, J. W., Safdar, N., Banerjee, I. & Trivedi, H. Currently available artificial intelligence softwares for cardiothoracic imaging in Artificial Intelligence in Cardiothoracic Imaging, 217\u2013224 (Springer, 2022).","DOI":"10.1007\/978-3-030-92087-6_21"},{"key":"797_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00376-2","volume":"4","author":"A Esteva","year":"2021","unstructured":"Esteva, A. et al. Deep learning-enabled medical computer vision. NPJ Digit. Med. 4, 1\u20139 (2021).","journal-title":"NPJ Digit. Med."},{"key":"797_CR23","first-page":"61","volume":"10","author":"J Platt","year":"1999","unstructured":"Platt, J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In Advances in Large Margin Classifiers 10, 61\u201374 (1999).","journal-title":"In Advances in Large Margin Classifiers"},{"key":"797_CR24","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1093\/jamia\/ocz228","volume":"27","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Li, W., Macheret, F., Gabriel, R. A. & Ohno-Machado, L. A tutorial on calibration measurements and calibration models for clinical prediction models. J. Am. Med. Inform. Assoc. 27, 621\u2013633 (2020).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"797_CR25","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1111\/j.1467-9868.2007.00593.x","volume":"69","author":"CA Field","year":"2007","unstructured":"Field, C. A. & Welsh, A. H. Bootstrapping clustered data. J. R. Stat. Soc.: Ser. B 69, 369\u2013390 (2007).","journal-title":"J. R. Stat. Soc.: Ser. B"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00797-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00797-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00797-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,8]],"date-time":"2023-04-08T05:07:51Z","timestamp":1680930471000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00797-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,8]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["797"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00797-9","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,8]]},"assertion":[{"value":"8 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The University of Michigan has filed a US Utility Patent application (number 17\/082,145) for the invention, University of Michigan IR number 2020\u2013026, Computer vision technologies for rapid disease detection, which uses software technology to process chest radiographs to detect acute diseases, of which M.W.S. and K.R.W. reports being a co-inventor and which has been licensed to AirStrip Technologies Inc. N.F., S.A., K.R.W., and M.W.S. are included in an invention disclosure with the University of Michigan\u2019s Office of Technology Transfer. Besides, the authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"62"}}