{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:50Z","timestamp":1781725070623,"version":"3.54.5"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health","doi-asserted-by":"publisher","award":["R41MH124581-S1"],"award-info":[{"award-number":["R41MH124581-S1"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Artificial intelligence (AI) systems in healthcare often fail to improve patient outcomes despite high development accuracy. We conducted semi-structured interviews with patients (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200918), health professionals (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u20098), and AI developers (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u20098), using a postpartum depression risk algorithm as a use case. Through thematic analysis informed by sociotechnical frameworks, we identified six themes: harm mitigation, clinical utility, communication strategies, data quality, privacy\/security, and responsible governance. All stakeholders emphasized that patient-centered AI must provide actionable benefits while minimizing bias, stigma, and anxiety. Patients wanted professional interpretation of AI outputs. Participants identified tensions between explainability and accuracy, varying patient preferences for accessing predictions, and unclear accountability when AI recommendations cause adverse outcomes. Our findings support patient-centered implementation through four strategies: providing professionals with competencies and protected time; engaging stakeholders throughout development; offering flexible communication accommodating diverse health literacy; and establishing multi-layered governance with shared accountability across developers, professionals, and institutions.\n                  <\/jats:p>","DOI":"10.1038\/s41746-026-02587-5","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T09:02:57Z","timestamp":1777971777000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A qualitative interview study investigating patient, health professional, and developer perspectives on real-world implementation of patient-centered AI systems"],"prefix":"10.1038","volume":"9","author":[{"given":"Natalie","family":"Benda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooja","family":"Desai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zayan","family":"Reza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoria","family":"Winogora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uday","family":"Suresh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiye","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alison","family":"Hermann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rochelle","family":"Joly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyotishman","family":"Pathak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meghan","family":"Reading Turchioe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,5]]},"reference":[{"key":"2587_CR1","unstructured":"National Science and Technology Council. Preparing for the Future of Artificial Intelligence. Executive Office of the President. https:\/\/obamawhitehouse.archives.gov\/sites\/default\/files\/whitehouse_files\/microsites\/ostp\/NSTC\/preparing_for_the_future_of_ai.pdf. Accessed 3 January 2023 (2016)."},{"key":"2587_CR2","unstructured":"Topol, E. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again (Hachette UK, 2019)."},{"issue":"4","key":"2587_CR3","doi-asserted-by":"publisher","first-page":"e12286","DOI":"10.2196\/12286","volume":"21","author":"AK Triantafyllidis","year":"2019","unstructured":"Triantafyllidis, A. K. & Tsanas, A. Applications of machine learning in real-life digital health interventions: review of the literature. J. Med. Internet Res. 21(4), e12286 (2019).","journal-title":"J. Med. Internet Res."},{"issue":"5","key":"2587_CR4","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1038\/s41591-018-0029-3","volume":"24","author":"DSW Ting","year":"2018","unstructured":"Ting, D. S. W. et al. AI for medical imaging goes deep. Nat. Med. 24(5), 539\u2013540 (2018).","journal-title":"Nat. Med."},{"issue":"1","key":"2587_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00524-2","volume":"4","author":"Q Zhou","year":"2021","unstructured":"Zhou, Q., Chen, Z. H., Cao, Y. H. & Peng, S. Clinical impact and quality of randomized controlled trials involving interventions evaluating artificial intelligence prediction tools: a systematic review. npj Digit. Med. 4(1), 154 (2021).","journal-title":"npj Digit. Med."},{"issue":"10","key":"2587_CR6","doi-asserted-by":"publisher","first-page":"e2337789","DOI":"10.1001\/jamanetworkopen.2023.37789","volume":"6","author":"SC Walker","year":"2023","unstructured":"Walker, S. C. et al. Model-guided decision-making for thromboprophylaxis and hospital-acquired thromboembolic events among hospitalized children and adolescents: the CLOT randomized clinical trial. JAMA Netw. Open 6(10), e2337789 (2023).","journal-title":"JAMA Netw. Open"},{"issue":"4","key":"2587_CR7","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooab092","volume":"4","author":"CG Walsh","year":"2021","unstructured":"Walsh, C. G. et al. Risky business: a scoping review for communicating results of predictive models between providers and patients. JAMIA Open 4(4), ooab092 (2021).","journal-title":"JAMIA Open"},{"issue":"5","key":"2587_CR8","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1093\/jamia\/ocaa021","volume":"27","author":"NC Benda","year":"2020","unstructured":"Benda, N. C. et al. \u201cHow did you get to this number?\u201d Stakeholder needs for implementing predictive analytics: a pre-implementation qualitative study. J. Am. Med. Inform. Assoc. 27(5), 709\u2013716 (2020).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2587_CR9","doi-asserted-by":"publisher","unstructured":"Dai, T. & Tayur, S. Designing AI-augmented healthcare delivery systems for physician buy-in and patient acceptance. Prod. Oper. Manag. https:\/\/doi.org\/10.1111\/poms.13850 (2022).","DOI":"10.1111\/poms.13850"},{"issue":"1","key":"2587_CR10","doi-asserted-by":"publisher","first-page":"e40973","DOI":"10.2196\/40973","volume":"2","author":"T Jeyakumar","year":"2023","unstructured":"Jeyakumar, T. et al. Preparing for an artificial intelligence-enabled future: patient perspectives on engagement and health care professional training for adopting artificial intelligence technologies in health care settings. JMIR AI 2(1), e40973 (2023).","journal-title":"JMIR AI"},{"issue":"1","key":"2587_CR11","doi-asserted-by":"publisher","first-page":"e066322","DOI":"10.1136\/bmjopen-2022-066322","volume":"13","author":"C Wu","year":"2023","unstructured":"Wu, C. et al. Public perceptions on the application of artificial intelligence in healthcare: a qualitative meta-synthesis. BMJ Open 13(1), e066322 (2023).","journal-title":"BMJ Open"},{"key":"2587_CR12","doi-asserted-by":"publisher","unstructured":"Lee, T. C., Shah, N. U., Haack, A. & Baxter, S. L. Clinical implementation of predictive models embedded within electronic health record systems: a systematic review. Informatics (MDPI) 7, https:\/\/doi.org\/10.3390\/informatics7030025 (2020).","DOI":"10.3390\/informatics7030025"},{"key":"2587_CR13","unstructured":"Reale, C. et al. User-centered design of a machine learning intervention for suicide risk prediction in a military setting. In Proc. AMIA Annual Symposium Vol. 2020, 1050\u20131058 (2020)."},{"issue":"4","key":"2587_CR14","doi-asserted-by":"publisher","first-page":"e26964","DOI":"10.2196\/26964","volume":"8","author":"S Matthiesen","year":"2021","unstructured":"Matthiesen, S. et al. Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning: near-live feasibility and qualitative study. JMIR Hum. Factors 8(4), e26964 (2021).","journal-title":"JMIR Hum. Factors"},{"issue":"2","key":"2587_CR15","doi-asserted-by":"publisher","first-page":"e108","DOI":"10.1055\/s-0040-1716748","volume":"4","author":"SL Baxter","year":"2020","unstructured":"Baxter, S. L., Bass, J. S. & Sitapati, A. M. Barriers to implementing an artificial intelligence model for unplanned readmissions. ACI Open 4(2), e108\u2013e113 (2020).","journal-title":"ACI Open"},{"issue":"3","key":"2587_CR16","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooab076","volume":"4","author":"P Nong","year":"2021","unstructured":"Nong, P. & Adler-Milstein, J. Socially situated risk: challenges and strategies for implementing algorithmic risk scoring for care management. JAMIA Open 4(3), ooab076 (2021).","journal-title":"JAMIA Open"},{"issue":"16_suppl","key":"2587_CR17","first-page":"e13567","volume":"40","author":"ME Salwei","year":"2022","unstructured":"Salwei, M. E. et al. Preventing clinical deterioration in cancer outpatients: human centered design of a predictive model and response system. J. Clin. Orthod. 40(16_suppl), e13567\u2013e13567 (2022).","journal-title":"J. Clin. Orthod."},{"key":"2587_CR18","unstructured":"21st Century Cures Act. Pub L No. 114-255. Stat 1033. Accessed August 18, 2024. https:\/\/www.congress.gov\/114\/plaws\/publ255\/PLAW-114publ255.pdf (2016)."},{"issue":"1","key":"2587_CR19","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1038\/s41746-024-01326-y","volume":"7","author":"N Hassan","year":"2024","unstructured":"Hassan, N. et al. Systematic review to understand users perspectives on AI-enabled decision aids to inform shared decision making. npj Digit. Med. 7(1), 332 (2024).","journal-title":"npj Digit. Med."},{"key":"2587_CR20","doi-asserted-by":"crossref","unstructured":"Sittig, D. F. & Singh, H. A new socio-technical model for studying health information technology in complex adaptive healthcare systems. in Cognitive Informatics for Biomedicine (eds Patel, V. L., Kannampallil, T. G., Kaufman, D. R.) Health Informatics. 59\u201380 (Springer International Publishing, 2015).","DOI":"10.1007\/978-3-319-17272-9_4"},{"issue":"6","key":"2587_CR21","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1370\/afm.245","volume":"2","author":"F Borrell-Carri\u00f3","year":"2004","unstructured":"Borrell-Carri\u00f3, F., Suchman, A. L. & Epstein, R. M. The biopsychosocial model 25 years later: principles, practice, and scientific inquiry. Ann. Fam. Med. 2(6), 576\u2013582 (2004).","journal-title":"Ann. Fam. Med."},{"issue":"7","key":"2587_CR22","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1093\/jamia\/ocaf086","volume":"32","author":"K Williams","year":"2025","unstructured":"Williams, K. et al. Incorporating end-user perspectives into the development of a machine learning algorithm for first time perinatal depression prediction. J. Am. Med. Inform. Assoc. 32(7), 1186\u20131198 (2025).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2587_CR23","unstructured":"National Academy of Medicine. An Artificial Intelligence Code of Conduct for Health and Medicine: Essential Guidance for Aligned Action (National Academies Press, 2025)."},{"issue":"3","key":"2587_CR24","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1097\/ACM.0000000000004963","volume":"98","author":"RG Russell","year":"2023","unstructured":"Russell, R. G. et al. Competencies for the use of artificial intelligence-based tools by health care professionals. Acad. Med. 98(3), 348\u2013356 (2023).","journal-title":"Acad. Med."},{"issue":"3","key":"2587_CR25","doi-asserted-by":"publisher","first-page":"e250449","DOI":"10.1001\/jamanetworkopen.2025.0449","volume":"8","author":"JS Cavalier","year":"2025","unstructured":"Cavalier, J. S. et al. Ethics in patient preferences for artificial intelligence-drafted responses to electronic messages. JAMA Netw. Open 8(3), e250449 (2025).","journal-title":"JAMA Netw. Open"},{"key":"2587_CR26","doi-asserted-by":"publisher","unstructured":"Guo, Y., Hu, D., Zhou, Y., Reynolds, T. L. & Zheng, K. A scoping review of studies on secure messaging through patient portals: persistent challenges and the promise of human-centered AI. Preprint at medRxiv https:\/\/doi.org\/10.1101\/2025.05.19.25327942 (2025).","DOI":"10.1101\/2025.05.19.25327942"},{"key":"2587_CR27","doi-asserted-by":"publisher","unstructured":"Ratwani, R. M. & Booker, E. We need A federal framework for health care AI. Forefront Group. https:\/\/doi.org\/10.1377\/forefront.20250114.858960 (2025).","DOI":"10.1377\/forefront.20250114.858960"},{"key":"2587_CR28","doi-asserted-by":"publisher","unstructured":"Nong, P., Adler-Milstein, J., Apathy, N. C., Holmgren, A. J., Everson, J. Current Use And Evaluation Of Artificial Intelligence And Predictive Models In US Hospitals. Health Aff (Millwood) 44, 90-98 https:\/\/doi.org\/10.1377\/hlthaff.2024.00842 (2025).","DOI":"10.1377\/hlthaff.2024.00842"},{"issue":"6","key":"2587_CR29","doi-asserted-by":"publisher","first-page":"e0000866","DOI":"10.1371\/journal.pdig.0000866","volume":"4","author":"R Abulibdeh","year":"2025","unstructured":"Abulibdeh, R., Celi, L. A. & Sejdi\u0107, E. The illusion of safety: a report to the FDA on AI healthcare product approvals. PLOS Digit. Health 4(6), e0000866 (2025).","journal-title":"PLOS Digit. Health"},{"key":"2587_CR30","doi-asserted-by":"publisher","unstructured":"Ong, J. C. L. et al. International partnership for governing generative artificial intelligence models in medicine. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-025-03787-4 (2025).","DOI":"10.1038\/s41591-025-03787-4"},{"key":"2587_CR31","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1477898","volume":"11","author":"S Aydin","year":"2024","unstructured":"Aydin, S., Karabacak, M., Vlachos, V. & Margetis, K. Large language models in patient education: a scoping review of applications in medicine. Front. Med. 11, 1477898 (2024).","journal-title":"Front. Med."},{"key":"2587_CR32","doi-asserted-by":"publisher","unstructured":"Longhurst, C. A., Singh, K., Chopra, A., Atreja, A. & Brownstein, J. S. A call for artificial intelligence implementation science centers to evaluate clinical effectiveness. NEJM AI 1, https:\/\/doi.org\/10.1056\/aip2400223 (2024).","DOI":"10.1056\/aip2400223"},{"issue":"17","key":"2587_CR33","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1056\/NEJMp2404691","volume":"391","author":"IS Kohane","year":"2024","unstructured":"Kohane, I. S. Compared with what? Measuring AI against the health care we have. N. Engl. J. Med. 391(17), 1564\u20131566 (2024).","journal-title":"N. Engl. J. Med."},{"issue":"10","key":"2587_CR34","doi-asserted-by":"publisher","first-page":"e2338275","DOI":"10.1001\/jamanetworkopen.2023.38275","volume":"6","author":"JG Chen","year":"2023","unstructured":"Chen, J. G. Reducing pediatric hospital-acquired venous thromboembolism\u2014overcoming challenges using quality improvement. JAMA Netw. Open 6(10), e2338275\u2013e2338275 (2023).","journal-title":"JAMA Netw. Open"},{"key":"2587_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103655","volume":"113","author":"AF Markus","year":"2021","unstructured":"Markus, A. F., Kors, J. A. & Rijnbeek, P. R. The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies. J. Biomed. Inform. 113, 103655 (2021).","journal-title":"J. Biomed. Inform."},{"key":"2587_CR36","doi-asserted-by":"publisher","unstructured":"Lomis, K. et al. Artificial intelligence for health professions educators. NAM Perspect. 2021, https:\/\/doi.org\/10.31478\/202109a (2021).","DOI":"10.31478\/202109a"},{"issue":"5","key":"2587_CR37","doi-asserted-by":"publisher","first-page":"E98","DOI":"10.1097\/NNE.0000000000001199","volume":"47","author":"M Kleib","year":"2022","unstructured":"Kleib, M. et al. Are future nurses ready for digital health?: informatics competency baseline assessment. Nurse Educ. 47(5), E98\u2013E104 (2022).","journal-title":"Nurse Educ."},{"key":"2587_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jad.2020.09.113","volume":"279","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, S., Hermann, A., Joly, R. & Pathak, J. Development and validation of a machine learning algorithm for predicting the risk of postpartum depression among pregnant women. J. Affect. Disord. 279, 1\u20138 (2021).","journal-title":"J. Affect. Disord."},{"issue":"6","key":"2587_CR39","doi-asserted-by":"publisher","first-page":"1258","DOI":"10.1093\/jamia\/ocae056","volume":"31","author":"Y Liu","year":"2024","unstructured":"Liu, Y. et al. Preparing for the bedside-optimizing a postpartum depression risk prediction model for clinical implementation in a health system. J. Am. Med. Inform. Assoc. 31(6), 1258\u20131267 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2587_CR40","unstructured":"Granger, E. & Skopac, J. An ethical framework for the use of consumer generated data in health care. In Proc. 2021 Health Datapalooza and National Health Policy Conference https:\/\/academyhealth.confex.com\/academyhealth\/2021hdpnhpc\/meetingapp.cgi\/Paper\/44315 (AcademyHealth, 2021)."},{"issue":"2","key":"2587_CR41","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1093\/jamia\/ocad198","volume":"31","author":"PM Desai","year":"2024","unstructured":"Desai, P. M. et al. Visualizing machine learning-based predictions of postpartum depression risk for lay audiences. J. Am. Med. Inform. Assoc. 31(2), 289\u2013297 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2587_CR42","unstructured":"Saldana, J. The Coding Manual For Qualitative Researchers 328 (Sage, 2012)."},{"key":"2587_CR43","unstructured":"Personal Health Records. Health System https:\/\/medlineplus.gov\/personalhealthrecords.html. Accessed 18 November 2004 (2025)."},{"key":"2587_CR44","unstructured":"F, Mann S., Kareddy. V. Narrative Review and Evidence Mapping: Artificial Intelligence in Clinical Care. Patient-Centered Outcomes Research Institute. Prepared by RAND under Contract No. IDIQ-TO#22-RAND-ENG-AOSEPP-04-01-2020 (2021)"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02587-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02587-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02587-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T09:03:06Z","timestamp":1777971786000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02587-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,5]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2587"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02587-5","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,5]]},"assertion":[{"value":"20 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"M.R.T., J.P., and A.H. are co-founders and have equity in Iris OB Health, a postpartum depression-focused startup. A.H. has also been a consultant for Progyny and Uptodate.com. M.R.T. has been a consultant for Boston Scientific. The remaining authors declare no competing financial or non-financial interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"352"}}