Protocol for LLM-Generated CONSORT Report for Increased Reporting: A Parallel-Arm Randomized Controlled Trial (Protocol)

BackgroundRandomized controlled trials (RCTs) often have incomplete methods reporting despite widespread adoption of the CONSORT guideline. The editorial process is supposed to detect these shortcomings and request clarifications from authors, which is time-consuming. We developed an LLM-based CONSORT Rohe Nordberg Report that highlights which CONSORT items appear fully or partially reported and checks page references claimed by authors, and then creates follow up questions for authors to more easily correct missing information. MethodsThis parallel-arm, superiority RCT will randomize eligible RCT submissions (after desk screening) 1:1 into intervention (editorial team and authors receive the Rohe Nordberg Report) or control (standard editorial review only). The primary outcome is whether manuscripts improve their reporting of CONSORT items in the Methods and Results sections between the original submission and first revision. This will be assessed by blinded human reviewers who evaluate the textual changes for improvements between the original and revised manuscripts for each relevant CONSORT item. Secondary outcomes include time to editorial decisions, rejection and non-resubmission rates, if authors can correctly identify where CONSORT items are reported, and extent of revisions. Human evaluators will be blinded to whether the manuscript was in the intervention or control group. DiscussionBy providing authors and the editorial team with specific follow up questions for each underreported CONSORT item, we hypothesize that basic underreporting will be more efficiently detected and corrected. Using blinded human reviewers as the primary outcome assessors ensures a rigorous, unbiased evaluation. If successful, this approach may help align manuscripts more closely with CONSORT standards, ultimately benefiting evidence synthesis. Trial Registration[To be registered prior to enrollment; e.g., ClinicalTrials.gov or ISRCTN] 1. Administrative Information1.1 TitleLLM-Generated CONSORT Rohe Nordberg Report for Increased Reporting: Protocol for a Parallel-Arm Randomized Controlled Trial. IRB registered name: LLM-Generated CONSORT Report Phase III Trial 1.2 Trial RegistrationThis trial will be registered before enrollment commences in a publicly accessible registry (e.g., ClinicalTrials.gov or ISRCTN). The trial identifier will be inserted here upon registration. All items from the World Health Organization Trial Registration Data Set will be provided at the time of registration, including: primary registry and trial ID, date of registration, secondary IDs, source of funding, contact for public and scientific queries, title, research ethics review, study design, study setting, interventions, eligibility criteria, primary outcome, key secondary outcomes, target sample size, recruitment status, and results dissemination plan. 1.3 Protocol VersionVersion 1.0 26 March 2026 [Subsequent amendments will be tracked by version number, date, and a summary of changes.] 1.4 FundingOpen Philanthropy, grant title "From Manual to Machine: Validating and Scaling LLM-Based CONSORT Compliance Assessment for Evidence-Based Medicine Publishing" Participating journals provide in-kind editorial resources (staff time, system access) to facilitate trial conduct. 1.5 Roles and ResponsibilitiesO_ST_ABSProtocol contributorsC_ST_ABSAuden Nordberg Krauska (University of Wisconsin-Madison; krauska@wisc.edu): conceived the study design, wrote the initial protocol draft Karl Rohe (University of Wisconsin-Madison): primary investigator, co-developed the LLM-based CONSORT and RoB 2 systems Gary Collins (University of Birmingham): senior methodologist, contributed to trial design and statistical analysis plan Sara Schroter (British Medical Journal): research editor, contributed to trial design and implementation plans Hyunseung Kang (University of Wisconsin-Madison): aided in statistical analysis plan Trial sponsorUniversity of Wisconsin-Madison, Department of Statistics, 1300 University Avenue, Madison, WI 53706. Role of sponsor and fundersThe research team leads trial design, data collection, analysis, interpretation, and reporting. The sponsor and funders have no role in data collection, management, analysis, interpretation of data, writing of the report, or the decision to submit the report for publication. The funder provides financial support only. Participating journal editorial teams are consulted for feasibility and operational feedback but do not have authority over data analysis or reporting. Trial oversight groupsThe trial will be coordinated by Karl Rohe and Auden Nordberg Krauska (University of Wisconsin-Madison), with methodological input from Gary Collins (University of Birmingham). Day-to-day operations, including manuscript tracking, diff file preparation, and data management will be carried out by Auden Nordberg Krauska and trained undergraduate research assistants at UW-Madison. Sara Schroter, Research Editor at The BMJ, will facilitate integration with the journals editorial workflow and monitor recruitment progress. This group will meet as needed to review trial progress and resolve operational issues.