{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T19:39:38Z","timestamp":1791574778812,"version":"4.3.4"},"reference-count":27,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"\n While large language models (LLMs) show promise for reducing clinical documentation burden, existing studies rely on simulated environments or require supplemental audio inputs. This study evaluates an AI documentation copilot integrated into real-world electronic health record (EHR) workflows, measuring its impact on physician efficiency and documentation review burden. We conducted a non-randomized controlled trial with 27 ophthalmology clinicians over 12 months (January 2024-February 2025). Participants self-selected into intervention (n\u2009=\u200911) or control (n\u2009=\u200917) groups after a 4-month baseline. The AI system generated inline suggestions for discharge letter conclusions using only the patient\u2019s EHR record as input. The system was based on a Quantized Low-Rank Adaptation (QLoRA) tuned LLM trained on 80,000 institutional records. Primary outcomes included words-per-minute (WPM) rates and the count of required document revisions after checks by the supervising senior physician across 15,615 documents. Intervention group clinicians achieved greater WPM improvements than controls (\n \n \n \n \n \n \u0394<\/mml:mo>\n +<\/mml:mo>\n 7.2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n vs.\n \n \n \n \n \n \u0394<\/mml:mo>\n +<\/mml:mo>\n 2.6<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n ), while revision frequency decreased within the intervention group (from 1.36\u2009\u00b1\u20090.14 to 1.26\u2009\u00b1\u20090.08 per document), with no significant change observed in the control group. Linear mixed-effects modeling confirmed a significant group\n \n \n \n \n \n \n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n exposure interaction for documentation efficiency (p\u2009=\u20090.045), whereas no statistically significant interaction was observed for revision count. This real-world evaluation suggests that AI documentation assistance is associated with improved documentation efficiency under routine clinical conditions, while maintaining documentation standards under established supervision processes. These findings support the cooperative \u201ccopilot\u201d design as a viable approach to enhance documentation efficiency without compromising patient safety protocols and indicate its potential to help reduce documentation burden in clinical practice.\n <\/jats:p>","DOI":"10.1371\/journal.pdig.0001461","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:55:21Z","timestamp":1784832921000},"page":"e0001461","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Implementation outcomes of AI documentation support in routine clinical practice: A non-randomized controlled trial"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9068-2679","authenticated-orcid":true,"given":"Felix A.","family":"Heilmeyer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4358-6163","authenticated-orcid":true,"given":"Lisa","family":"Lyssenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Reinhard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Haverkamp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"B\u00f6hringer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"issue":"5","key":"pdig.0001461.ref001","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1370\/afm.2121","article-title":"Tethered to the EHR: Primary Care Physician Workload Assessment Using EHR Event Log Data and Time-Motion Observations","volume":"15","author":"BG Arndt","year":"2017","journal-title":"Ann Fam Med"},{"issue":"9","key":"pdig.0001461.ref002","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1007\/s11606-019-05055-x","article-title":"Pajama Time: Working After Work in the Electronic Health Record","volume":"34","author":"HS Saag","year":"2019","journal-title":"J Gen Intern Med"},{"issue":"4","key":"pdig.0001461.ref003","doi-asserted-by":"crossref","first-page":"479","DOI":"10.4300\/JGME-D-16-00123.1","article-title":"Electronic Health Record Effects on Work-Life Balance and Burnout Within the I3 Population Collaborative","volume":"9","author":"SL Robertson","year":"2017","journal-title":"J Grad Med Educ"},{"issue":"7","key":"pdig.0001461.ref004","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1016\/j.mayocp.2016.05.007","article-title":"Relationship Between Clerical Burden and Characteristics of the Electronic Environment With Physician Burnout and Professional Satisfaction","volume":"91","author":"TD Shanafelt","year":"2016","journal-title":"Mayo Clin Proc"},{"issue":"7","key":"pdig.0001461.ref005","doi-asserted-by":"crossref","DOI":"10.2196\/19274","article-title":"The Influence of Electronic Health Record Use on Physician Burnout: Cross-Sectional Survey","volume":"22","author":"T Tajirian","year":"2020","journal-title":"J Med Internet Res"},{"issue":"3","key":"pdig.0001461.ref006","doi-asserted-by":"crossref","first-page":"169","DOI":"10.7326\/M18-3684","article-title":"Physician Time Spent Using the Electronic Health Record During Outpatient Encounters: A Descriptive Study","volume":"172","author":"JM Overhage","year":"2020","journal-title":"Ann Intern Med"},{"issue":"4","key":"pdig.0001461.ref007","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","article-title":"Adapted large language models can outperform medical experts in clinical text summarization","volume":"30","author":"D Van Veen","year":"2024","journal-title":"Nat Med"},{"issue":"9","key":"pdig.0001461.ref008","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1007\/s10389-023-02170-2","article-title":"ChatGPT and the healthcare industry: a comprehensive analysis of its impact on medical writing","volume":"33","author":"SS Awal","year":"2023","journal-title":"J Public Health (Berl)"},{"key":"pdig.0001461.ref009","article-title":"Comparison of the Quality of Discharge Letters Written by Large Language Models and Junior Clinicians: Single-Blinded Study","volume":"26","author":"JYM Tung","year":"2024","journal-title":"J Med Internet Res"},{"key":"pdig.0001461.ref010","doi-asserted-by":"crossref","unstructured":"\"Giorgi J, Toma A, Xie R, Chen S, An K, Zheng G, et al. WangLab at MEDIQA-Chat 2023: Clinical note generation from doctor-patient conversations using large language models. In: Proceedings of the 5th Clinical Natural Language Processing Workshop, 2023. 323\u201334. https:\/\/doi.org\/10.18653\/v1\/2023.clinicalnlp-1.36","DOI":"10.18653\/v1\/2023.clinicalnlp-1.36"},{"issue":"2","key":"pdig.0001461.ref011","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.annemergmed.2024.01.039","article-title":"Harnessing the Power of Generative AI for Clinical Summaries: Perspectives From Emergency Physicians","volume":"84","author":"Y Barak-Corren","year":"2024","journal-title":"Ann Emerg Med"},{"issue":"1","key":"pdig.0001461.ref012","article-title":"Transforming healthcare documentation: harnessing the potential of AI to generate discharge summaries","volume":"8","author":"RAJ Clough","year":"2024","journal-title":"BJGP Open"},{"issue":"3","key":"pdig.0001461.ref013","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.0357","article-title":"Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format","volume":"7","author":"J Zaretsky","year":"2024","journal-title":"JAMA Network Open"},{"issue":"6","key":"pdig.0001461.ref014","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","article-title":"Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum","volume":"183","author":"JW Ayers","year":"2023","journal-title":"JAMA Intern Med"},{"issue":"1","key":"pdig.0001461.ref015","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s41746-023-00896-7","article-title":"Evaluating large language models on medical evidence summarization","volume":"6","author":"L Tang","year":"2023","journal-title":"NPJ Digit Med"},{"issue":"9","key":"pdig.0001461.ref016","article-title":"AI-Powered Clinical Documentation and Clinicians\u2019 Electronic Health Record Experience: A Nonrandomized Clinical Trial","volume":"7","author":"T-L Liu","year":"2024","journal-title":"JAMA Netw Open"},{"issue":"3","key":"pdig.0001461.ref017","doi-asserted-by":"crossref","DOI":"10.1056\/CAT.23.0404","article-title":"Ambient Artificial Intelligence Scribes to Alleviate the Burden of Clinical Documentation","volume":"5","author":"AA Tierney","year":"2024","journal-title":"NEJM Catalyst"},{"key":"pdig.0001461.ref018","doi-asserted-by":"crossref","DOI":"10.2196\/60020","article-title":"Impact of a Digital Scribe System on Clinical Documentation Time and Quality: Usability Study","volume":"3","author":"MM van Buchem","year":"2024","journal-title":"JMIR AI"},{"issue":"4","key":"pdig.0001461.ref019","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1093\/jamia\/ocae022","article-title":"The impact of nuance DAX ambient listening AI documentation: a cohort study","volume":"31","author":"T Haberle","year":"2024","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"pdig.0001461.ref020","doi-asserted-by":"crossref","first-page":"100157","DOI":"10.1016\/j.fhj.2024.100157","article-title":"Use of an ambient artificial intelligence tool to improve quality of clinical documentation","volume":"11","author":"J Balloch","year":"2024","journal-title":"Future Healthc J"},{"issue":"2","key":"pdig.0001461.ref021","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1093\/jamia\/ocae304","article-title":"Ambient artificial intelligence scribes: utilization and impact on documentation time","volume":"32","author":"SP Ma","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"pdig.0001461.ref022","doi-asserted-by":"crossref","DOI":"10.2196\/59617","article-title":"Viability of Open Large Language Models for Clinical Documentation in German Health Care: Real-World Model Evaluation Study","volume":"12","author":"F Heilmeyer","year":"2024","journal-title":"JMIR Med Inform"},{"issue":"1","key":"pdig.0001461.ref023","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1093\/jamia\/ocab230","article-title":"Frequent but fragmented: use of note templates to document outpatient visits at an academic health center","volume":"29","author":"A Rule","year":"2021","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"pdig.0001461.ref024","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s41449-024-00427-4","article-title":"Neuauflage des TAEG Fragebogens: Technikaffinit\u00e4t valide und multidimensional mit einer Kurz- oder Langversion erfassen","volume":"78","author":"K Karrer-Gau\u00df","year":"2024","journal-title":"Z Arb Wiss"},{"issue":"31","key":"pdig.0001461.ref025","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.21105\/joss.01026","article-title":"Pingouin: statistics in Python","volume":"3","author":"R Vallat","year":"2018","journal-title":"Journal of Open Source Software"},{"key":"pdig.0001461.ref026","article-title":"Evaluating Large Language Models for Drafting Emergency Department Discharge Summaries","author":"CYK Williams","year":"2024","journal-title":"medRxiv"},{"issue":"1","key":"pdig.0001461.ref027","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"EJ Topol","year":"2019","journal-title":"Nat Med"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:55:26Z","timestamp":1784832926000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001461"}},"subtitle":[],"editor":[{"given":"Michael","family":"Winter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":27,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001461","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]}}}