{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T07:30:38Z","timestamp":1782459038511,"version":"3.54.5"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T00:00:00Z","timestamp":1780099200000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Stanford Medical Scholars Research Program"},{"DOI":"10.13039\/100000092","name":"U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["2T15LM007033"],"award-info":[{"award-number":["2T15LM007033"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02545-1","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T08:26:04Z","timestamp":1773822364000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["From tool to teammate in a randomized controlled trial of clinician-AI collaborative workflows for diagnosis"],"prefix":"10.1038","volume":"9","author":[{"given":"Selin S.","family":"Everett","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan J.","family":"Bunning","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyank","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Lopez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anup","family":"Agarwal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manisha","family":"Desai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Gallo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethan","family":"Goh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinay B.","family":"Kadiyala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zahir","family":"Kanjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob M.","family":"Koshy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Olson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Rodman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Schulman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Strong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan H.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Horvitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"2545_CR1","doi-asserted-by":"publisher","unstructured":"Nori, H., King, N., McKinney, S. M., Carignan, D. & Horvitz, E. Capabilities of GPT-4 on medical challenge problems. CS https:\/\/doi.org\/10.48550\/arXiv.2303.13375 (2023).","DOI":"10.48550\/arXiv.2303.13375"},{"key":"2545_CR2","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1001\/jamainternmed.2024.0295","volume":"84","author":"S Cabral","year":"2024","unstructured":"Cabral, S. et al. Clinical reasoning of a generative artificial intelligence model compared with physicians. JAMA Intern. Med. 84, 581\u2013583 (2024).","journal-title":"JAMA Intern. Med."},{"key":"2545_CR3","doi-asserted-by":"publisher","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh, E. et al. Large language model influence on diagnostic reasoning: a randomized clinical trial. JAMA Netw. Open 7, e2440969 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2545_CR4","doi-asserted-by":"publisher","unstructured":"McDuff D., et al. Towards accurate differential diagnosis with large language models. Nature. 1\u20137. https:\/\/doi.org\/10.1038\/s41586-025-08869-4 (2025).","DOI":"10.1038\/s41586-025-08869-4"},{"key":"2545_CR5","doi-asserted-by":"crossref","unstructured":"Tversky, A., Kahneman, D. Judgment under uncertainty: heuristics and biases: biases in judgments reveal some heuristics of thinking under uncertainty. Science. 185:1124\u20131131. 1974.","DOI":"10.1126\/science.185.4157.1124"},{"key":"2545_CR6","doi-asserted-by":"publisher","unstructured":"Fogliato, R. et al. Who goes first? Influences of human-AI workflow on decision making in clinical imaging. In Proc. 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT \u201822), 1362\u20131374 (Association for Computing Machinery, New York, NY, USA, 2022). https:\/\/doi.org\/10.1145\/3531146.3533193.","DOI":"10.1145\/3531146.3533193"},{"key":"2545_CR7","doi-asserted-by":"crossref","unstructured":"Nourani, M. et al. (2021). Anchoring bias affects mental model formation and user reliance in explainable AI systems. 26th International Conference on Intelligent User Interfaces, 340\u2013350.","DOI":"10.1145\/3397481.3450639"},{"key":"2545_CR8","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2022.01454","author":"J Yin","year":"2022","unstructured":"Yin, J., Ngiam, K. Y., Tan, S. S. L. & Teo, H. H. Designing AI-based work processes: how the timing of AI advice affects diagnostic decision making. Manag. Sci. https:\/\/doi.org\/10.1287\/mnsc.2022.01454 (2022).","journal-title":"Manag. Sci."},{"key":"2545_CR9","doi-asserted-by":"crossref","unstructured":"Sellen, A. & Horvitz, E. The rise of the AI co-pilot: Lessons for design from aviation and beyond. Commun. ACM 67, 18\u201323 (2024).","DOI":"10.1145\/3637865"},{"key":"2545_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3449287","volume":"5","author":"Z Bu\u00e7inca","year":"2021","unstructured":"Bu\u00e7inca, Z., Malaya, M. B. & Gajos, K. Z. To trust or to think: cognitive forcing functions can reduce overreliance on AI in AI-assisted decision-making. Proc. ACM Hum.-Comput. Interact. 5, 1\u201321 (2021).","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"2545_CR11","doi-asserted-by":"crossref","unstructured":"Hemmer, P. et al. (2023). Human-AI collaboration: the effect of AI delegation on human task performance and task satisfaction. In Proceedings of the 28th International Conference on Intelligent User Interfaces (pp. 453\u2013463).","DOI":"10.1145\/3581641.3584052"},{"key":"2545_CR12","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1287\/isre.2021.1079","volume":"33","author":"A F\u00fcgener","year":"2022","unstructured":"F\u00fcgener, A., Grahl, J., Gupta, A. & Ketter, W. Cognitive challenges in human\u2013artificial intelligence collaboration: Investigating the path toward productive delegation. Inf. Syst. Res. 33, 678\u2013696 (2022).","journal-title":"Inf. Syst. Res."},{"key":"2545_CR13","doi-asserted-by":"crossref","unstructured":"Bussone, A., Stumpf, S., & O\u2019Sullivan, D. The Role of Explanations on Trust and Reliance in Clinical Decision Support Systems. Proceedings of the 2015 International Conference on Healthcare Informatics, 160\u2013169 (2015).","DOI":"10.1109\/ICHI.2015.26"},{"key":"2545_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-021-00385-9","volume":"4","author":"S Gaube","year":"2021","unstructured":"Gaube, S. et al. Do as AI say: Susceptibility in deployment of clinical decision-aids. Npj Digit. Med. 4, 1\u20138 (2021).","journal-title":"Npj Digit. Med."},{"key":"2545_CR15","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1177\/0018720814564422","volume":"57","author":"VL Pop","year":"2015","unstructured":"Pop, V. L., Shrewsbury, A. & Durso, F. T. Individual differences in the calibration of trust in automation. Hum. Factors 57, 545\u2013556 (2015).","journal-title":"Hum. Factors"},{"key":"2545_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Liao, Q. V., & Bellamy, R. K. E. Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 295\u2013305. https:\/\/doi.org\/10.1145\/3351095.3372852 (2020).","DOI":"10.1145\/3351095.3372852"},{"key":"2545_CR17","doi-asserted-by":"publisher","unstructured":"Passi, S., Dhanorkar, S., Vorvoreanu, M. Addressing Overreliance on AI. In: Xu, W. (eds) Handbook of Human-Centered Artificial Intelligence. Springer, Singapore. https:\/\/doi.org\/10.1007\/978-981-97-8440-0_98-1 (2025).","DOI":"10.1007\/978-981-97-8440-0_98-1"},{"key":"2545_CR18","doi-asserted-by":"publisher","unstructured":"Drosos, I., Sarkar, A., Toronto, N. \u201c It makes you think\u201d. Provocations Help Restore Critical Thinking to AI-Assisted Knowledge Work. ArXiv Prepr. https:\/\/doi.org\/10.48550\/arXiv.2501.17247 (2025).","DOI":"10.48550\/arXiv.2501.17247"},{"key":"2545_CR19","unstructured":"Herbert H. Clark. Using language. Cambridge University Press. (1996)."},{"key":"2545_CR20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.13975","author":"O Shaikh","year":"2025","unstructured":"Shaikh, O., Mozannar, H., Bansal, G., Fourney, A. & Horvitz, E. Navigating Rifts in Human-LLM Grounding: Study and Benchmark. ACL 2025: Proc. 63rd Annu. Meet. Assoc. Comput. Linguist. https:\/\/doi.org\/10.48550\/arXiv.2503.13975 (2025).","journal-title":"ACL 2025: Proc. 63rd Annu. Meet. Assoc. Comput. Linguist."},{"key":"2545_CR21","unstructured":"Brennan, S. E. The grounding problem in conversations with and through computers. In Social and cognitive approaches to interpersonal communication, pp. 201\u2013225. Psychology Press. (2014)."},{"key":"2545_CR22","doi-asserted-by":"publisher","unstructured":"Bohus, D. & Eric, H. Facilitating multiparty dialog with gaze, gesture, and speech. In International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction, https:\/\/doi.org\/10.1145\/1891903.1891910 (2010).","DOI":"10.1145\/1891903.1891910"},{"key":"2545_CR23","unstructured":"Traum, D. R. A Computational Theory of Grounding in Natural Language Conversation. PhD thesis, Department of Computer Science, University of Rochester. Also available as TR 545, Department of Computer Science, University of Rochester. (1994)."},{"key":"2545_CR24","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1609\/hcomp.v7i1.5285","volume":"7","author":"G Bansal","year":"2019","unstructured":"Bansal, G. et al. Beyond accuracy: The role of mental models in human-AI team performance. Proc. AAAI Conf. Hum. Comput. Crowdsourc. 7, 2\u201311, https:\/\/doi.org\/10.1609\/hcomp.v7i1.5285 (2019).","journal-title":"Proc. AAAI Conf. Hum. Comput. Crowdsourc."},{"key":"2545_CR25","doi-asserted-by":"publisher","unstructured":"Horvitz, E. Principles of mixed-initiative user interfaces. Proceedings of the SIGCHI conference on Human Factors in Computing Systems (CHI \u201899). Association for Computing Machinery, New York, NY, USA, 159\u2013166. https:\/\/doi.org\/10.1145\/302979.303030.","DOI":"10.1145\/302979.303030"},{"key":"2545_CR26","doi-asserted-by":"publisher","unstructured":"Amershi, S. et al. Guidelines for human-AI interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI \u201819). Association for Computing Machinery, New York, NY, USA, Paper 3, 1\u201313. https:\/\/doi.org\/10.1145\/3290605.3300233.","DOI":"10.1145\/3290605.3300233"},{"key":"2545_CR27","doi-asserted-by":"publisher","unstructured":"Wilder, B., Horvitz, E., Kamar, E. Learning to complement humans. Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, IJCAI'20. 212:1526\u20131533. https:\/\/doi.org\/10.24963\/ijcai.2020\/212.","DOI":"10.24963\/ijcai.2020\/212"},{"key":"2545_CR28","doi-asserted-by":"crossref","unstructured":"Bansal, G., Nushi, B., Kamar, E., Horvitz, E. & Weld, D. S. Is the most accurate AI the best teammate? Optimizing AI for teamwork. In Proc. AAAI Conference on Artificial Intelligence, Vol. 35 11405\u201311414 (2021).","DOI":"10.1609\/aaai.v35i13.17359"},{"key":"2545_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2025.103444","volume":"197","author":"FM Calisto","year":"2025","unstructured":"Calisto, F. M., Abrantes, J. M., Santiago, C., Nunes, N. J. & Nascimento, J. C. Personalized explanations for clinician-AI interaction in breast imaging diagnosis by adapting communication to expertise levels. Int J. Hum.-Comput. Stud. 197, 103444 (2025).","journal-title":"Int J. Hum.-Comput. Stud."},{"key":"2545_CR30","first-page":"5323","volume":"36","author":"H Mozannar","year":"2022","unstructured":"Mozannar, H., Satyanarayan, A. & Sontag, D. Teaching humans when to defer to a classifier via exemplars. Artif. Intell. 36, 5323\u20135331, (2022).","journal-title":"Artif. Intell."},{"key":"2545_CR31","doi-asserted-by":"crossref","unstructured":"Weld, D. S., Bansal, G. The challenge of crafting intelligible intelligence Communications of the ACM 62, 70\u201379.","DOI":"10.1145\/3282486"},{"key":"2545_CR32","doi-asserted-by":"publisher","unstructured":"Bansal, G. et al. Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, Article 81, 1\u201316. https:\/\/doi.org\/10.1145\/3411764.3445717 (2020).","DOI":"10.1145\/3411764.3445717"},{"key":"2545_CR33","unstructured":"Horvitz, E., Heckerman, D., Nathwani, B. & Fagan, L. M. The use of a heuristic problem-solving hierarchy to facilitate the explanation of hypothesis-directed reasoning. In Proc. of Medinfo, 27\u201331 https:\/\/erichorvitz.com\/medinfo_explain_inference.pdf (1986)."},{"key":"2545_CR34","doi-asserted-by":"publisher","unstructured":"Horvitz, E. & Paek, T. Complementary computing: policies for transferring callers from dialog systems to human receptionists. User Model. User Adapt. Interact. 17 https:\/\/doi.org\/10.1007\/s11257-006-9026-1 (2007).","DOI":"10.1007\/s11257-006-9026-1"},{"key":"2545_CR35","doi-asserted-by":"crossref","unstructured":"Kamar, E., Hacker, S. & Horvitz, E. Combining Human and Machine Intelligence in Large-scale Crowdsourcing, AAMAS 2012, Valencia, Spain, https:\/\/dl.acm.org\/doi\/10.5555\/2343576.2343643 (2012).","DOI":"10.65109\/HMCS1623"},{"key":"2545_CR36","first-page":"10137","volume":"38","author":"H Mozannar","year":"2024","unstructured":"Mozannar, H., Bansal, G., Fourney, A. & Horvitz, E. When to show a suggestion? Integrating human feedback in AI-assisted programming. Artif. Intell. 38, 10137\u201310144 (2024).","journal-title":"Artif. Intell."},{"key":"2545_CR37","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"BE Bejnordi","year":"2017","unstructured":"Bejnordi, B. E. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318, 2199\u20132210 (2017).","journal-title":"JAMA"},{"key":"2545_CR38","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1016\/S0020-7373(83)80067-4","volume":"19","author":"CP Langlotz","year":"1983","unstructured":"Langlotz, C. P. & Shortliffe, E. H. Adapting a consultation system to critique user plans. Int J. Man-Mach. Stud. 19, 479\u2013496 (1983).","journal-title":"Int J. Man-Mach. Stud."},{"key":"2545_CR39","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1109\/TPAMI.1983.4767424","volume":"5","author":"PL Miller","year":"1983","unstructured":"Miller, P. L. ATTENDING: Critiquing a physician\u2019s management plan. IEEE Trans. Pattern Anal. Mach. Intell. 5, 449\u2013461 (1983).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2545_CR40","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L. et al. Training language models to follow instructions with human feedback. Adv. Neural Inf. Process Syst. 35, 27730\u201327744 (2022).","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"2545_CR41","doi-asserted-by":"publisher","first-page":"pgae533","DOI":"10.1093\/pnasnexus\/pgae533","volume":"3","author":"A Salecha","year":"2024","unstructured":"Salecha, A. et al. Large language models display human-like social desirability biases in Big Five personality surveys. PNAS Nexus 3, pgae533 (2024).","journal-title":"PNAS Nexus"},{"key":"2545_CR42","unstructured":"Sharma, M. et al. Towards understanding sycophancy in language models. ArXiv Prepr. Published online, (2023)."},{"key":"2545_CR43","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1093\/jamia\/ocae254","volume":"32","author":"T Savage","year":"2025","unstructured":"Savage, T. et al. Large language model uncertainty proxies: discrimination and calibration for medical diagnosis and treatment. J. Am. Med Inf. Assoc. 32, 139\u2013149 (2025).","journal-title":"J. Am. Med Inf. Assoc."},{"key":"2545_CR44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.10566","author":"V Balachandran","year":"2024","unstructured":"Balachandran, V. et al. Eureka: Evaluating and understanding large foundation models. ArXiv Prepr. Published online https:\/\/doi.org\/10.48550\/arXiv.2409.10566 (2024).","journal-title":"ArXiv Prepr. Published online"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02545-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02545-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02545-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T06:03:51Z","timestamp":1780121031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02545-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2545"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02545-1","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"assertion":[{"value":"6 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"409"}}