FirsthandHealth
medRxiv PreprintsInternational19 November 2026

Prospective prediction of clinical trial outcomes from public evidence

This is an official announcement record

Firsthand records what medRxiv Preprints announced and links to the original. The wording below is theirs, not ours.

Predicting clinical trial outcomes requires interpreting biological and clinical evidence in the context of a specific intervention, population and study design. Here we test whether a general-purpose large language model (LLM) can predict trial outcomes from publicly available evidence. We introduce TrialDossier, which assembles standardized evidence dossiers, and TrialOutlook, which uses these dossiers with GPT-5 to estimate the probability that a trial meets its prespecified primary endpoint. Among 694 ongoing trials with results expected within six months of cohort assembly, 69 outcomes fi
Source: medRxiv Preprints
Read the official announcement

Opens www.medrxiv.org

More from medRxiv Preprints

This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program: especially if you are pregnant, nursing, taking medication, or managing a health condition.