{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T20:10:51Z","timestamp":1790367051080,"version":"4.1.0"},"reference-count":23,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Bioinform Biotech"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The manual abstraction of unstructured clinical data is often necessary for granular clinical outcomes research but is time consuming and can be of variable quality. Large language models (LLMs) show promise in medical data extraction yet integrating them into research workflows remains challenging and poorly described.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and integrate an LLM-based system for automated data extraction from unstructured electronic health record (EHR) text reports within an established clinical outcomes database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We implemented a generative artificial intelligence pipeline (UODBLLM) utilizing a flexible language model interface that supports various LLM implementations, including Health Insurance Portability and Accountability Act-compliant cloud services and local open-source models. We used extensible markup language (XML)-structured prompts and integrated using an open database connectivity interface to generate structured data from clinical documentation in the EHR. We evaluated the UODBLLM\u2019s performance on the completion rate, processing time, and extraction capabilities across multiple clinical data elements, including quantitative measurements, categorical assessments, and anatomical descriptions, using sample magnetic resonance imaging (MRI) reports as test cases. System reliability was tested across multiple batches to assess scalability and consistency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Piloted against MRI reports, UODBLLM processed 1800 clinical documents with a 100% completion rate and an average processing time of 8.90 seconds per report. The token utilization averaged 2692 tokens per report, with an input-to-output ratio of approximately 13:2, resulting in a processing cost of US $0.009 per report. UODBLLM had consistent performance across 18 batches of 100 reports each and completed all processing in 4.45 hours. From each report, UODBLLM extracted 16 structured clinical elements, including prostate volume, prostate-specific antigen values, Prostate Imaging Reporting and Data System scores, clinical staging, and anatomical assessments. All extracted data were automatically validated against predefined schemas and stored in standardized JSON format.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We demonstrated the successful integration of an LLM-based extraction system within an existing clinical outcomes database, achieving rapid, comprehensive data extraction at minimal cost. UODBLLM provides a scalable, efficient solution for automating clinical data extraction while maintaining protected health information security. This approach could significantly accelerate research timelines and expand feasible clinical studies, particularly for large-scale database projects.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/70708","type":"journal-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T13:25:08Z","timestamp":1761053108000},"page":"e70708-e70708","source":"Crossref","is-referenced-by-count":4,"title":["Development and Validation of a Generative Artificial Intelligence-Based Pipeline for Automated Clinical Data Extraction From Electronic Health Records: Technical Implementation Study"],"prefix":"10.2196","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6467-0758","authenticated-orcid":false,"given":"Marvin N","family":"Carlisle","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1877-3725","authenticated-orcid":false,"given":"William A","family":"Pace","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8033-2598","authenticated-orcid":false,"given":"Andrew W","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7155-381X","authenticated-orcid":false,"given":"Robert","family":"Krumm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1852-8260","authenticated-orcid":false,"given":"Janet E","family":"Cowan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-4334","authenticated-orcid":false,"given":"Peter R","family":"Carroll","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4339-6685","authenticated-orcid":false,"given":"Matthew R","family":"Cooperberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0975-0812","authenticated-orcid":false,"given":"Anobel Y","family":"Odisho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooab085","article-title":"Improving natural language information extraction from cancer pathology reports using transfer learning and zero-shot string similarity","volume":"4","author":"Park","journal-title":"JAMIA Open"},{"issue":"3","key":"R2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1200\/CCI.18.00084","article-title":"Automating the capture of structured pathology data for prostate cancer clinical care and research","volume":"3","author":"Odisho","journal-title":"JCO Clin Cancer Inform"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1093\/jamiaopen\/ooaa029","article-title":"Natural language processing systems for pathology parsing in limited data environments with uncertainty estimation","volume":"3","author":"Odisho","journal-title":"JAMIA Open"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.2147\/JMDH.S413470","article-title":"Using ChatGPT in medical research: current status and future directions","volume":"16","author":"Ruksakulpiwat","journal-title":"J Multidiscip Healthc"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01079-8","article-title":"A critical assessment of using ChatGPT for extracting structured data from clinical notes","volume":"7","author":"Huang","journal-title":"NPJ Digit Med"},{"issue":"5","key":"R6","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1097\/UPJ.0000000000000599","article-title":"Exploring the feasibility of GPT-4 as a data extraction tool for renal surgery operative notes","volume":"11","author":"Hsueh","journal-title":"Urol Pract"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1007\/s00330-024-11035-5","article-title":"Assessing GPT-4 multimodal performance in radiological image analysis","volume":"35","author":"Brin","journal-title":"Eur Radiol"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1002\/path.6232","article-title":"Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4)","volume":"262","author":"Truhn","journal-title":"J Pathol"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232741","article-title":"Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT: a retrospective analysis","volume":"311","author":"Lehnen","journal-title":"Radiology"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2024.100378","article-title":"An automated information extraction model for unstructured discharge letters using large language models and GPT-4","volume":"7","author":"Siepmann","journal-title":"Healthcare Analytics"},{"key":"R11","doi-asserted-by":"crossref","unstructured":"Verma A Verma P , editors. Research Advances in Intelligent Computing: Volume 2. CRC Press; 2024. [doi: 10.1201\/9781003433941]","DOI":"10.1201\/9781003433941"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/56243","article-title":"Extraction of substance use information from clinical notes: generative pretrained transformer-based investigation","volume":"12","author":"Shah-Mohammadi","journal-title":"JMIR Med Inform"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Chiang CC Luo M Dumkrieger G et al. A large language model-based generative natural language processing framework finetuned on clinical notes accurately extracts headache frequency from electronic health records. Neurology. [doi: 10.1101\/2023.10.02.23296403]","DOI":"10.1101\/2023.10.02.23296403"},{"issue":"10","key":"R14","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1093\/jamia\/ocad133","article-title":"Inferring cancer disease response from radiology reports using large language models with data augmentation and prompting","volume":"30","author":"Tan","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230364","article-title":"Performance of an open-source large language model in extracting information from free-text radiology reports","volume":"6","author":"Le Guellec","journal-title":"Radiol Artif Intell"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1053\/j.gastro.2023.12.019","article-title":"A comparison of a large language model vs manual chart review for the extraction of data elements from the electronic health record","volume":"166","author":"Ge","journal-title":"Gastroenterology"},{"issue":"5S","key":"R17","doi-asserted-by":"publisher","DOI":"10.1097\/01.JU.0001008728.41882.d7.14","article-title":"MP07-14 development of a generative artificial intelligence data pipeline to automate the capture of unstructured MRI data for prostate cancer care","volume":"211","author":"Odisho","journal-title":"Journal of Urology"},{"key":"R18","unstructured":"Flatiron health. Clinical Research Solutions. URL: https:\/\/flatiron.com\/clinical-research-solutions [Accessed 11-12-2024]"},{"key":"R19","unstructured":"UCSF department of urology. Urologic Outcomes Database (UODB). URL: https:\/\/urology.ucsf.edu\/research\/cancer\/urologic-oncology-database-uodb [Accessed 23-11-2024]"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103872","article-title":"Supervised line attention for tumor attribute classification from pathology reports: Higher performance with less data","volume":"122","author":"Altieri","journal-title":"J Biomed Inform"},{"issue":"s1","key":"R21","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1017\/cts.2024.714","article-title":"23 Generative artificial intelligence for automated unstructured MRI data extraction in prostate cancer care","volume":"9","author":"Pace","journal-title":"J Clin Trans Sci"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.2196\/47958","article-title":"Automated electronic health record to electronic data capture transfer in clinical studies in the German health care system: feasibility study and gap analysis","volume":"25","author":"Mueller","journal-title":"J Med Internet Res"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105344","article-title":"The implementation of a multidisciplinary, electronic health record embedded care pathway to improve structured data recording and decrease electronic health record burden","volume":"184","author":"Ebbers","journal-title":"Int J Med Inform"}],"container-title":["JMIR Bioinformatics and Biotechnology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/bioinform.jmir.org\/2026\/1\/e70708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:59:35Z","timestamp":1782842375000},"score":1,"resource":{"primary":{"URL":"https:\/\/bioinform.jmir.org\/2026\/1\/e70708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.2196\/70708","relation":{},"ISSN":["2563-3570"],"issn-type":[{"value":"2563-3570","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]},"article-number":"v7i3e70708"}}