{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T08:38:51Z","timestamp":1792571931926,"version":"4.5.0"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"vor","delay-in-days":161,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Clinical trial statistical programming requires 12\u201324 full-time-equivalent months per Phase 3 study and remains a bottleneck in pharmaceutical research. Modern artificial intelligence coding agents reason capably but lack domain-specific tools: they cannot read proprietary statistical software datasets, parse analysis specifications, or generate standards-compliant code without extensive guidance. We present ClinAgent, a skill and tool layer that augments any artificial intelligence coding agent with clinical programming capabilities through Model Context Protocol tools. Its design separates minimal data access from rich domain logic: skills package prompts, rule engines, and decision trees encoding expert knowledge, while tools provide stateless input-output for statistical software datasets, spreadsheet specifications, and log files. In this single-study proof-of-concept evaluation, we validate ClinAgent\u2019s nine skills on artifacts from a production Phase 2 cardiovascular study, with synthetic datasets spanning 13 analysis domains and 102\u00a0109 observations. All skills pass functional validation. On this small sample, deterministic components identify one error and seven warnings without false positives and match all 56 subject-level variables; corresponding confidence intervals are wide, so these point estimates should be read as upper bounds pending replication. Prompt-based specification generation, dependent on the underlying language model, reaches 72.1% derivation accuracy overall, above 96% in simple domains and below 55% in complex ones, indicating that generated specifications require expert review. Our contributions include an agent-augmentation architecture, nine validated skills, tool implementations for clinical data formats, and a validation methodology distinguishing deterministic tool correctness from language-model-dependent output.<\/jats:p>","DOI":"10.1093\/biomethods\/bpag032","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T11:46:29Z","timestamp":1781091989000},"source":"Crossref","is-referenced-by-count":0,"title":["ClinAgent: AI-assisted methodology for clinical trial data processing and statistical programming"],"prefix":"10.1093","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1786-7259","authenticated-orcid":false,"given":"Jaime","family":"Yan","sequence":"first","affiliation":[{"name":"Harrisburg University of Science and Technology Department of Data Sciences, , Harrisburg, PA 17101,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"2026102103471247200_bpag032-B1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","article-title":"Innovation in the pharmaceutical industry: new estimates of R&D costs","volume":"47","author":"DiMasi","year":"2016","journal-title":"J Health Econ"},{"key":"2026102103471247200_bpag032-B2","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1177\/2168479017713039","article-title":"New benchmarks characterizing growth in protocol design complexity","volume":"52","author":"Getz","year":"2018","journal-title":"Ther Innov Regul Sci"},{"key":"2026102103471247200_bpag032-B3","doi-asserted-by":"publisher","first-page":"5069","DOI":"10.3390\/ijerph110505069","article-title":"Improving protocol design feasibility to drive drug development economics and performance","volume":"11","author":"Getz","year":"2014","journal-title":"Int J Environ Res Public Health"},{"key":"2026102103471247200_bpag032-B4","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1177\/2168479016632271","article-title":"The impact of protocol amendments on clinical trial performance and cost","volume":"50","author":"Getz","year":"2016","journal-title":"Ther Innov Regul Sci"},{"key":"2026102103471247200_bpag032-B5","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s43441-024-00622-9","article-title":"New benchmarks on protocol amendment practices, trends and their impact on clinical trial performance","volume":"58","author":"Getz","year":"2024","journal-title":"Ther Innov Regul Sci"},{"key":"2026102103471247200_bpag032-B6","doi-asserted-by":"publisher","author":"Peng","year":"2023","DOI":"10.48550\/arXiv.2302.06590,"},{"key":"2026102103471247200_bpag032-B7","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.tips.2019.05.005","article-title":"Artificial intelligence for clinical trial design","volume":"40","author":"Harrer","year":"2019","journal-title":"Trends Pharmacol Sci"},{"key":"2026102103471247200_bpag032-B8","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","year":"2024","journal-title":"Nat Commun"},{"key":"2026102103471247200_bpag032-B9","doi-asserted-by":"publisher","DOI":"10.1177\/17407745261422365","article-title":"Leveraging generative AI to transform statistical analysis plan authoring in clinical trials","author":"Landman","year":"2026","journal-title":"Clin Trials"},{"key":"2026102103471247200_bpag032-B10","author":"Anthropic","year":"2024"},{"key":"2026102103471247200_bpag032-B11","author":"CDISC","year":"2023"},{"key":"2026102103471247200_bpag032-B12"},{"key":"2026102103471247200_bpag032-B13","first-page":"68539","volume-title":"Adv Neural Inf Process Syst"},{"key":"2026102103471247200_bpag032-B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.08155"},{"key":"2026102103471247200_bpag032-B15","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1208\/s12248-024-00910-0","article-title":"PmWebSpec: an application to create and manage CDISC-compliant pharmacometric analysis dataset specifications","volume":"26","author":"Chen","year":"2024","journal-title":"AAPS J"},{"key":"2026102103471247200_bpag032-B16","doi-asserted-by":"publisher","first-page":"1392686","DOI":"10.3389\/ftox.2024.1392686","article-title":"sendigR: an R package to leverage the value of CDISC SEND datasets for cross-study analysis","volume":"6","author":"Snyder","year":"2024","journal-title":"Front Toxicol"},{"key":"2026102103471247200_bpag032-B17","doi-asserted-by":"publisher","first-page":"1636809","DOI":"10.3389\/frai.2025.1636809","article-title":"From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development","volume":"8","author":"Vieira-Vieira","year":"2025","journal-title":"Front Artif Intell"},{"key":"2026102103471247200_bpag032-B18","author":"CDISC","year":"2024"},{"key":"2026102103471247200_bpag032-B19","author":"Faraglia","year":"2024"},{"key":"2026102103471247200_bpag032-B20","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1214\/ss\/1009213286","article-title":"Interval estimation for a binomial proportion","volume":"16","author":"Brown","year":"2001","journal-title":"Statist Sci"},{"key":"2026102103471247200_bpag032-B21","author":"Yan","year":"2026"},{"key":"2026102103471247200_bpag032-B22","volume-title":"Computer Software Assurance for Production and Quality System Software. Draft Guidance for Industry","author":"FDA","year":"2022"}],"container-title":["Biology Methods and Protocols"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomethods\/advance-article-pdf\/doi\/10.1093\/biomethods\/bpag032\/68513694\/bpag032.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomethods\/article-pdf\/11\/1\/bpag032\/68513694\/bpag032.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomethods\/article-pdf\/11\/1\/bpag032\/68513694\/bpag032.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T07:47:21Z","timestamp":1792568841000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomethods\/article\/doi\/10.1093\/biomethods\/bpag032\/8706433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,12]]}},"URL":"https:\/\/doi.org\/10.1093\/biomethods\/bpag032","relation":{},"ISSN":["2396-8923"],"issn-type":[{"value":"2396-8923","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"bpag032"}}