{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:26:40Z","timestamp":1786112800373,"version":"build-2736575974"},"reference-count":49,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Enrollment in phase I oncology trials remains low largely because potentially eligible patients are not identified and evaluated quickly enough. Current clinical trial matching systems can identify candidate patients from the electronic health record, but cases with missing or uncertain eligibility data are often routed for offline manual review. This delay impedes clarification and prolongs the final eligibility determination.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study evaluated TrialTriage, a semiautonomous system built on the n8n platform and designed to resolve eligibility ambiguity during prescreening for phase I oncology trials. When eligibility information is missing or uncertain, TrialTriage emails the investigator, captures the reply, and reruns classification within the same workflow.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n TrialTriage combined large language model\u2013based variable extraction from free-text clinical narratives and investigator email replies with a deterministic rule engine applying a prespecified 7-criterion protocol. Each case was classified as eligible, not eligible, or ambiguous. Ambiguous cases triggered a structured email query to the investigator, followed by reclassification after a reply. Two requests were sent at 24-hour intervals; after 48 hours without a reply, the case was referred for manual review. The system was tested on 90 synthetic patient cases generated independently by Claude Sonnet 4.6, Gemini 3.1, and Grok 4, with 30 cases per model and balanced distributions of eligible, not eligible, and ambiguous cases. Answer keys were reviewed for accuracy before system execution. Five independent reviewers classified the Claude dataset using a uniform survey form.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n TrialTriage\u2019s classifications were 100% concordant with the author-confirmed ground truth in all 90 synthetic cases (95% CI 96.0%-100.0%). All ambiguous cases were correctly escalated to investigator query. The mean processing time was 2.3 (SD 0.5) minutes per 30-case dataset (range 1.8-2.8 min, approximately 3.5-5.5 s per case). The 5 reviewers achieved a mean accuracy of 96.7% (SD 3.3%), with a Fleiss \u03ba of 0.910, and required a mean of 9.8 (SD 4.8) minutes to review 30 cases. In a subset test of 6 first-pass ambiguous cases, 4 of 6 were reclassified definitively after investigator response, while 2 remained ambiguous because the replies lacked actionable information.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n TrialTriage demonstrates the feasibility of a semiautonomous prescreening workflow in which ambiguous cases trigger an immediate investigator email query and are reclassified after reply capture with new information within the same system. The main contribution is the integration of email ambiguity resolution into the workflow rather than immediate deferral to offline manual review. Because the evaluation used synthetic cases and label definitions aligned with the same protocol rules used to design the rule engine, these findings should be interpreted as proof of concept and implementation fidelity rather than evidence of real-world clinical performance. Prospective validation using data from real-world electronic health records would be a plausible next step.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/100779","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T13:50:09Z","timestamp":1783345809000},"page":"e100779-e100779","source":"Crossref","is-referenced-by-count":0,"title":["TrialTriage, a Semiautonomous Prescreening Workflow for Resolving Ambiguity in Phase I Oncology Trial Eligibility: Development and Proof-of-Concept Study Using Synthetic Cases"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8125-1727","authenticated-orcid":false,"given":"Kenneth A","family":"Kern","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.annonc.2022.09.158","article-title":"Oncology phase I trial design and conduct: time for a change-MDICT Guidelines 2022","volume":"34","author":"Araujo","journal-title":"Ann Oncol"},{"issue":"3","key":"R2","doi-asserted-by":"publisher","first-page":"178","DOI":"10.36401\/JIPO-23-25","article-title":"Oncology early-phase clinical trials in the Middle East and North Africa: a review of the current status, challenges, opportunities, and future directions","volume":"7","author":"Alotaibi","journal-title":"J Immunother Precis Oncol"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1200\/JCO.2014.58.2635","article-title":"American Society of Clinical Oncology policy statement update: the critical role of phase I trials in cancer research and treatment","volume":"33","author":"Weber","journal-title":"J Clin Oncol"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/nrclinonc.2012.22","article-title":"Drug development and clinical trials\u2014the path to an approved cancer drug","volume":"9","author":"Rubin","journal-title":"Nat Rev Clin Oncol"},{"issue":"22","key":"R5","doi-asserted-by":"publisher","first-page":"5408","DOI":"10.1158\/1078-0432.CCR-16-0338","article-title":"Challenges facing early phase trials sponsored by the National Cancer Institute: an analysis of corrective action plans to improve accrual","volume":"22","author":"Massett","journal-title":"Clin Cancer Res"},{"issue":"11","key":"R6","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1093\/jnci\/djac152","article-title":"Implementing modernized eligibility criteria in US National Cancer Institute clinical trials","volume":"114","author":"Denicoff","journal-title":"J Natl Cancer Inst"},{"issue":"3","key":"R7","doi-asserted-by":"publisher","DOI":"10.2196\/14185","article-title":"A real-time automated patient screening system for clinical trials eligibility in an emergency department: design and evaluation","volume":"7","author":"Ni","journal-title":"JMIR Med Inform"},{"issue":"7","key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtocrr.2022.100357","article-title":"Brief report: implementation of a universal prescreening protocol to increase recruitment to lung cancer studies at a Veterans Affairs Cancer Center","volume":"3","author":"Xiang","journal-title":"JTO Clin Res Rep"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1177\/1740774514558307","article-title":"Unsuccessful trial accrual and human subjects protections: an empirical analysis of recently closed trials","volume":"12","author":"Carlisle","journal-title":"Clin Trials"},{"issue":"5","key":"R10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0127242","article-title":"Terminated trials in the ClinicalTrials.gov results database: evaluation of availability of primary outcome data and reasons for termination","volume":"10","author":"Williams","journal-title":"PLoS ONE"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1056\/AIcs2400360","article-title":"Zero-shot clinical trial patient matching with LLMs","volume":"2","author":"Wornow","journal-title":"NEJM AI"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1200\/OP.2024.20.10_suppl.10","article-title":"The cost of doing business: drug costs in federally sponsored cancer clinical trials","volume":"20","author":"Unger","journal-title":"JCO Oncol Pract"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1093\/jnci\/djaa155","article-title":"\u201cWhen offered to participate\u201d: a systematic review and meta-analysis of patient agreement to participate in cancer clinical trials","volume":"113","author":"Unger","journal-title":"J Natl Cancer Inst"},{"issue":"12","key":"R14","doi-asserted-by":"publisher","first-page":"e1351","DOI":"10.1634\/theoncologist.2019-0166","article-title":"Inclusion of older patients with cancer in clinical trials: the SAGE prospective multicenter cohort survey","volume":"24","author":"Canou\u00ef-Poitrine","journal-title":"Oncologist"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s43441-019-00030-4","article-title":"Improving clinical trial participant prescreening with artificial intelligence (AI): a comparison of the results of AI-assisted vs standard methods in 3 oncology trials","volume":"54","author":"Calaprice-Whitty","journal-title":"Ther Innov Regul Sci"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1007\/s10637-012-9894-7","article-title":"Determinants of patient screen failures in phase 1 clinical trials","volume":"31","author":"Mckane","journal-title":"Invest New Drugs"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-014-0535-7","article-title":"Improving the pre-screening of eligible patients in order to increase enrollment in cancer clinical trials","volume":"16","author":"Campillo-Gimenez","journal-title":"Trials"},{"issue":"5","key":"R18","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.4787","article-title":"Model of a queuing approach for patient accrual in phase 1 oncology studies","volume":"3","author":"Frankel","journal-title":"JAMA Netw Open"},{"issue":"5","key":"R19","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1200\/CCI.21.00003","article-title":"Natural language processing for patient selection in phase I or II oncology clinical trials","volume":"5","author":"Delorme","journal-title":"JCO Clin Cancer Inform"},{"key":"R20","unstructured":"Ferber D Hilgers L Wiest IC et al. End-to-end clinical trial matching with large language models. arXiv. Preprint posted online on Jul 18, 2024. [doi: 10.48550\/arXiv.2407.13463]"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","DOI":"10.2196\/27767","article-title":"Accuracy of an artificial intelligence system for cancer clinical trial eligibility screening: retrospective pilot study","volume":"9","author":"Haddad","journal-title":"JMIR Med Inform"},{"issue":"4","key":"R22","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.2013","article-title":"Clinical trial notifications triggered by artificial intelligence\u2013detected cancer progression: a randomized trial","volume":"8","author":"Mazor","journal-title":"JAMA Netw Open"},{"issue":"8","key":"R23","doi-asserted-by":"publisher","DOI":"10.1200\/PO.23.00507","article-title":"Identifying oncology clinical trial candidates using artificial intelligence predictions of treatment change: a pilot implementation study","volume":"8","author":"Kehl","journal-title":"JCO Precis Oncol"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-025-15311-5","article-title":"Patient characteristics related to screening failure in phase I trials","volume":"26","author":"Ozaki","journal-title":"BMC Cancer"},{"issue":"9","key":"R25","doi-asserted-by":"publisher","first-page":"1953","DOI":"10.1093\/jamia\/ocae073","article-title":"Distilling large language models for matching patients to clinical trials","volume":"31","author":"Nievas","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-01916-6","article-title":"Piloting an automated clinical trial eligibility surveillance and provider alert system based on artificial intelligence and standard data models","volume":"23","author":"Meystre","journal-title":"BMC Med Res Methodol"},{"issue":"4","key":"R27","doi-asserted-by":"publisher","first-page":"e620","DOI":"10.1200\/OP.21.00629","article-title":"Prescreening to increase therapeutic oncology trial enrollment at the largest public hospital in the United States","volume":"18","author":"Wu","journal-title":"JCO Oncol Pract"},{"issue":"23","key":"R28","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.70466","article-title":"\u201cThe truth is, we must miss some\u201d: a qualitative study of the patient eligibility screening process, and automation perspectives, for cancer clinical trials","volume":"13","author":"La Rosa","journal-title":"Cancer Med"},{"key":"R29","unstructured":"Considerations for the use of artificial intelligence to support regulatory decision-making for drug and biological products: guidance for industry and other interested parties. U.S. Food and Drug Administration; 2025. URL: https:\/\/www.fda.gov\/media\/184830\/download [Accessed 10-07-2026]"},{"key":"R30","unstructured":"Guiding principles of good AI practice in drug development. European Medicines Agency; 2026. URL: https:\/\/www.ema.europa.eu\/en\/documents\/other\/guiding-principles-good-ai-practice-drug-development_en.pdf [Accessed 10-07-2026]"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","journal-title":"Nat Med"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","journal-title":"Biometrics"},{"issue":"19","key":"R33","doi-asserted-by":"publisher","first-page":"2272","DOI":"10.1001\/archinte.165.19.2272","article-title":"Effect of a clinical trial alert system on physician participation in trial recruitment","volume":"165","author":"Embi","journal-title":"Arch Intern Med"},{"issue":"7","key":"R34","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.3446","article-title":"Employing computers for the recruitment into clinical trials: a comprehensive systematic review","volume":"16","author":"K\u00f6pcke","journal-title":"J Med Internet Res"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-015-0149-3","article-title":"Increasing the efficiency of trial-patient matching: automated clinical trial eligibility pre-screening for pediatric oncology patients","volume":"15","author":"Ni","journal-title":"BMC Med Inform Decis Mak"},{"issue":"6","key":"R36","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1089\/aipo.2024.0030","article-title":"Optimizing clinical trial subject selection: insights from Exigent Research Network and the Tempus AI TIME Program collaboration","volume":"1","author":"Mallahan","journal-title":"AI Precis Oncol"},{"issue":"1","key":"R37","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-70509-w","article-title":"TrialMatchAI: an end-to-end AI-powered clinical trial recommendation system to streamline patient-to-trial matching","volume":"17","author":"Abdallah","journal-title":"Nat Commun"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01274-7","article-title":"PRISM: patient records interpretation for semantic clinical trial matching system using large language models","volume":"7","author":"Gupta","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R39","doi-asserted-by":"publisher","first-page":"9074","DOI":"10.1038\/s41467-024-53081-z","article-title":"Matching patients to clinical trials with large language models","volume":"15","author":"Jin","journal-title":"Nat Commun"},{"issue":"2","key":"R40","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1093\/jamiaopen\/ooaa002","article-title":"Evaluation of an artificial intelligence clinical trial matching system in Australian lung cancer patients","volume":"3","author":"Alexander","journal-title":"JAMIA Open"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2024.102443","article-title":"Impact on costs and outcomes of multi-gene panel testing for advanced solid malignancies: a cost-consequence analysis using linked administrative data","volume":"69","author":"Hernando-Calvo","journal-title":"EClinicalMedicine"},{"issue":"6","key":"R42","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1200\/JOP.2012.000646","article-title":"Effort required in eligibility screening for clinical trials","volume":"8","author":"Penberthy","journal-title":"J Oncol Pract"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1200\/PO.19.00398","article-title":"Evolving landscape of molecular prescreening strategies for oncology early clinical trials","volume":"4","author":"Dienstmann","journal-title":"JCO Precis Oncol"},{"issue":"7818","key":"R44","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1038\/s41586-020-2481-8","article-title":"The National Lung Matrix Trial of personalized therapy in lung cancer","volume":"583","author":"Middleton","journal-title":"Nature"},{"key":"R45","volume":"2022","author":"Beigi","journal-title":"AMIA Annu Symp Proc"},{"issue":"e2","key":"R46","doi-asserted-by":"publisher","first-page":"e311","DOI":"10.1136\/amiajnl-2013-001922","article-title":"Correlating electronic health record concepts with healthcare process events","volume":"20","author":"Hripcsak","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"R47","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1136\/amiajnl-2011-000681","article-title":"Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research","volume":"20","author":"Weiskopf","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"R48","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.13063\/2327-9214.1244","article-title":"A harmonized data quality assessment terminology and framework for the secondary use of electronic health record data","volume":"4","author":"Kahn","journal-title":"EGEMS (Wash DC)"},{"key":"R49","volume":"2010","author":"Botsis","journal-title":"Summit Transl Bioinform"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T16:11:17Z","timestamp":1785946277000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e100779"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":49,"URL":"https:\/\/doi.org\/10.2196\/100779","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"v10i1e100779"}}