EviSearch is evaluated, a clinical evidence-curation system that links extracted values to source passages, independently verifies cited evidence, and prioritizes higher-risk cells for review, and evidence modality.
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%.
Background: Systematic reviews are critical for informing evidence-based medicine, policy, and future research. However, conducting a systematic review is labour- and cost-intensive and error-prone. Elicit is an AI tool that claims to replicate the systematic review process. Methods: Our study investigated Elicit's abi...
I. Wei, J. Shah, A. Miah et al.· medRxiv· 0 citations
Evidence-based clinical practice is grounded in research and interpretation of findings. Individual studies capture only part of the evidence relevant to a clinical question, making synthesis important for evaluating consistency and precision. Systematic reviews bring relevant studies together, and meta-analyses use st...
T. Fernandes, Natanael A. Santos· Journal of Evaluation In Cli...· 0 citations
The synthesis is shifted from plausible report generation to clinically interpretable effectiveness, safety, and workflow effects, and the evidence remains too heterogeneous, biased, and sparse on case-level end points to support a pooled meta-analysis or autonomous clinical-readiness claims.
Jie-Li Huang, Ji-Qing Zhu, Xiao-Guang Ni· Journal of Medical Internet...· 0 citations
Systematic reviews of clinical prediction models demonstrate inadequate reporting and significant risk of bias and Optimizing research design, enforcing stricter reporting guidelines, promoting protocol pre-registration, and enhancing journal review processes to boost reliability and transparency are warranted.
Mei Zhang, Yun-Hui Xia, Hang-Feng Mo et al.· Epidemiologic Reviews· 0 citations
BACKGROUND
Detecting discrepancies between registered and published trial outcomes currently requires manual expert review, limiting surveillance to small samples. No scalable automated system exists for continuous monitoring of outcome reporting integrity across the clinical trial literature. We aimed to develop and v...
Clinical prediction models are increasingly deployed to support diagnostic and prognostic decisions, making reproducibility essential for assessing their reliability and generalizability. Analytical code supports independent assessment of these processes, yet its availability in the literature remains limited. This sco...
Thomas Sounack, Raffaele Giancotti, Catherine A. Gao et al.· Nature Medicine· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
