{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:12Z","timestamp":1785545052526,"version":"3.56.0"},"reference-count":23,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Interhospital transfer of patients with suspected ST-elevation myocardial infarction (STEMI) requires timely and robust communication. Clinical uptake of potentially useful information from physician-to-physician phone calls authorizing transfer is low at many institutions, at least in part due to relative inaccessibility of call audio and lack of transcripts or summaries. Large language models (LLMs) can transform text into brief, consistently formatted summaries that could be made available in the electronic health record, thus facilitating the timely availability of clinically relevant data to physicians downstream of the transfer call.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n We sought to assess the feasibility of using transcription and LLM summarization to provide written information summarizing transfer calls by adapting the Physician Documentation Quality Instrument (PDQI) to score generated call summaries and evaluate whether LLMs could effectively summarize a curated set of transfer calls.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n STEMI transfer calls for which our institution was the receiving facility were transcribed and summarized by Whisper and ChatGPT (OpenAI), respectively. Each summary was reviewed by 2 of 7 independent physician raters. Summaries were rated using a Likert scale applied to an 8-domain framework adapted from the PDQI. We calculated summary statistics, including means, SDs, and raw and weighted agreement, and produced visual radar plots to demonstrate ratings for each call. We also performed thematic analysis of reviewers\u2019 comments.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n We identified 32 calls, of which 1 (3.1%) was excluded for incompleteness. Raw agreement between raters was 62% (153\/248), and the mean of the pairwise weighted \u03ba coefficients was 0.19 (SD 0.30; slight agreement). The mean rating of all summaries across all domains was 4.6 of 5 (SD 0.7). The \u201cuseful\u201d (mean 4.8\/5, SD 0.5) and \u201cconsistent\u201d (mean 4.9\/5, SD 0.6) domains were the highest rated, and the \u201cthorough\u201d (mean 4.4\/5, SD 1.0) and \u201challucination free\u201d (mean 4.4\/5, SD 0.9) domains were the lowest rated. The mean score for accuracy was 4.6\/5 (SD 0.7). Qualitative analysis found that raters penalized the LLM for inferential hallucinations, although these were often clinically accurate, and discrepancies related to calculation of timing of events.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Despite the limitations inherent in a small pilot cohort, this feasibility study suggests that LLMs can generate accurate and pertinent summaries of interhospital transfer calls for patients with STEMI. Interrater agreement was slight, which may suggest inadequate training of raters, unclear definitions, or a limitation of using the PDQI for this task. We identified several important areas for consideration prior to implementation, including thorough assessment of transcription accuracy, prompt engineering to minimize unwanted LLM behavior, and assessment of the impact of incorporating these summaries into clinical care on clinical outcomes.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/88834","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T21:11:41Z","timestamp":1782421901000},"page":"e88834-e88834","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Model Summarization of Physician-to-Physician Calls for Interhospital Transfer of Patients With ST-Elevation Myocardial Infarction: Observational Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9869-9328","authenticated-orcid":false,"given":"Jesse O","family":"Wrenn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5439-970X","authenticated-orcid":false,"given":"Madelaine","family":"Behrens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0607-1013","authenticated-orcid":false,"given":"Mary S","family":"Hershey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9689-2768","authenticated-orcid":false,"given":"Marc","family":"Maldaver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4077-1384","authenticated-orcid":false,"given":"John","family":"Mitchell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4638-0443","authenticated-orcid":false,"given":"Trevor","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0899-7565","authenticated-orcid":false,"given":"Austin J","family":"Triana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7501-0615","authenticated-orcid":false,"given":"Zain M","family":"Virk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-8277","authenticated-orcid":false,"given":"Yasemin","family":"Akdas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3835-2725","authenticated-orcid":false,"given":"Michael R","family":"Cauley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4561-2946","authenticated-orcid":false,"given":"Michael J","family":"Ward","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1650-4647","authenticated-orcid":false,"given":"Ken","family":"Monahan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"issue":"6","key":"R1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.113.000370","article-title":"Growth in percutaneous coronary intervention capacity relative to population and disease prevalence","volume":"2","author":"Langabeer","journal-title":"J Am Heart Assoc"},{"issue":"25","key":"R2","doi-asserted-by":"publisher","first-page":"2442","DOI":"10.1016\/j.jacc.2008.02.071","article-title":"Time-to-reperfusion in patients undergoing interhospital transfer for primary percutaneous coronary intervention in the US: an analysis of 2005 and 2006 data from the National Cardiovascular Data Registry","volume":"51","author":"Chakrabarti","journal-title":"J Am Coll Cardiol"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1161\/CIRCULATIONAHA.111.068049","article-title":"Expansion of a regional ST-segment-elevation myocardial infarction system to an entire state","volume":"126","author":"Jollis","journal-title":"Circulation"},{"issue":"20","key":"R4","doi-asserted-by":"publisher","first-page":"2371","DOI":"10.1001\/jama.298.20.joc70124","article-title":"Implementation of a statewide system for coronary reperfusion for ST-segment elevation myocardial infarction","volume":"298","author":"Jollis","journal-title":"JAMA"},{"issue":"24","key":"R5","doi-asserted-by":"publisher","first-page":"2540","DOI":"10.1001\/jama.2011.862","article-title":"Association of door-in to door-out time with reperfusion delays and outcomes among patients transferred for primary percutaneous coronary intervention","volume":"305","author":"Wang","journal-title":"JAMA"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1186\/s12873-020-00355-6","article-title":"Breaking down walls: a qualitative evaluation of perceived emergency department delays for patients transferred with ST-elevation myocardial infarction","volume":"20","author":"Ward","journal-title":"BMC Emerg Med"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.2196\/71434","article-title":"Evaluating the usability, technical performance, and accuracy of artificial intelligence scribes for primary care: competitive analysis","volume":"12","author":"Ha","journal-title":"JMIR Hum Factors"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00432-5","article-title":"The digital scribe in clinical practice: a scoping review and research agenda","volume":"4","author":"van Buchem","journal-title":"NPJ Digit Med"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.60637","article-title":"Clinician experiences with ambient scribe technology to assist with documentation burden and efficiency","volume":"8","author":"Duggan","journal-title":"JAMA Netw Open"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1055\/a-2327-4121","article-title":"Evaluation of a digital scribe: conversation summarization for emergency department consultation calls","volume":"15","author":"Sezgin","journal-title":"Appl Clin Inform"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"164","DOI":"10.4338\/aci-2011-11-ra-0070","article-title":"Assessing electronic note quality using the Physician Documentation Quality Instrument (PDQI-9)","volume":"3","author":"Stetson","journal-title":"Appl Clin Inform"},{"issue":"3","key":"R12","doi-asserted-by":"publisher","DOI":"10.1056\/CAT.23.0404","article-title":"Ambient artificial intelligence scribes to alleviate the burden of clinical documentation","volume":"5","author":"Tierney","journal-title":"NEJM Catal Innov Care Deliv"},{"issue":"9","key":"R13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","journal-title":"ACM Comput Surv"},{"issue":"3","key":"R14","doi-asserted-by":"publisher","first-page":"7","DOI":"10.37765\/ajac.2022.89231","article-title":"Association of physician coordination with interfacility transfer acceptance timeliness","volume":"10","author":"Ward","journal-title":"Am J Accountable Care"},{"issue":"2","key":"R15","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.jbi.2008.08.010","article-title":"Research electronic data capture (REDCap)--a metadata-driven methodology and workflow process for providing translational research informatics support","volume":"42","author":"Harris","journal-title":"J Biomed Inform"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103208","article-title":"The REDCap consortium: building an international community of software platform partners","volume":"95","author":"Harris","journal-title":"J Biomed Inform"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","journal-title":"ACM Trans Inf Syst"},{"issue":"8","key":"R18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3786333","article-title":"A survey on large language models for mathematical reasoning","volume":"58","author":"Wang","journal-title":"ACM Comput Surv"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1691499","article-title":"Assessing the quality of AI-generated clinical notes: validated evaluation of a large language model ambient scribe","volume":"8","author":"Palm","journal-title":"Front Artif Intell"},{"issue":"6","key":"R20","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1093\/jamia\/ocaf068","article-title":"Development and validation of the provider documentation summarization quality instrument for large language models","volume":"32","author":"Croxford","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1055\/a-2559-5791","article-title":"The STREAMLINE pilot study on time reduction and efficiency in AI-mediated logging for improved note-taking experience","volume":"16","author":"Kakaday","journal-title":"Appl Clin Inform"},{"issue":"9","key":"R22","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.32460","article-title":"AI-powered clinical documentation and clinicians\u2019 electronic health record experience: a nonrandomized clinical trial","volume":"7","author":"Liu","journal-title":"JAMA Netw Open"},{"issue":"12","key":"R23","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1097\/00001888-200512000-00005","article-title":"Lost in translation: challenges and opportunities in physician-to-physician communication during patient handoffs","volume":"80","author":"Solet","journal-title":"Acad Med"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e88834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:24:49Z","timestamp":1785536689000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e88834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":23,"URL":"https:\/\/doi.org\/10.2196\/88834","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"article-number":"v28i6e88834"}}