Reliable extraction of clinical-trial evidence with provenance, verification, and targeted review
Najpande, G.; Titiya, P.; Khan, M. A.; Khakwani, K. Z. R.; Sonbol, M. B.; Riaz, I. B.; Gupta, V.
Show abstract
Reliable extraction of trial characteristics and outcomes is essential for systematic reviews, yet incorrect values can alter evidence synthesis and are difficult to detect without clear source evidence. We evaluate EviSearch, a clinical evidence-curation system that links extracted values to source passages, independently verifies cited evidence, and prioritizes higher-risk cells for review. Using ten trial publications, a 133-column schema, reference annotations, and consistent scoring across model families, we assess answer quality, inter-reading agreement, evidence reproduction, targeted review, and evidence modality. In the Qwen evaluation, EviSearch achieved 91.70% accuracy, cited 100.0% of admitted values, and reproduced 98.9% independently. Reviewing 15.6% of cells increased accuracy to 95.22%.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Trials that turn from retrospectively registered to prospectively registered: A cohort study of ‘retroactively prospective’ clinical trial registration using history data 94%
- Supporting Reanalysis and Reuse of Clinical Trial Data: A Case Study 92%
- Development of a consensus extension of the estimands framework for cluster randomised trials (CRT-estimands): results from an international Delphi study 92%
Similar papers in this journal
- Exploring scalable assessment methods for terminated trials in ClinicalTrials.gov: A cohort analysis of German and Californian trials 96%
- Analysis of clinical trial registry entry histories using the novel R package cthist 94%
- How Informative Were Early SARS-CoV-2 Treatment and Prevention Trials? A longitudinal cohort analysis of trials registered on clinicaltrials.gov 93%
Similar papers in this journal
- Exploring the potential of Claude 2 for risk of bias assessment: Using a large language model to assess randomized controlled trials with RoB 2 94%
- Machine learning for identifying relevant publications in updates of systematic reviews of diagnostic test studies 93%
- Evaluation of the sensitivity, accuracy and currency of the Cochrane COVID-19 Study Register for supporting rapid evidence synthesis production 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.