Medicine

Authoring and Management of Transparent Research Integrity Assessments of Randomised Clinical Trial Publications Using LLM-assisted Tools and Provenance Knowledge Graphs

Milan Markovic, Goutham Indukuri, Somayajulu Sripada, Colby J. Vorland, Jack Wilkinson, Clare Robertson, Mark Bolland, Andrew Grey, Miriam Brazzelli, Alison Avenell

Featured August 11, 2026

Original Paper

AI-generated analysis — This is SciGrove's AI interpretation of the paper, not peer-reviewed content. Always refer to the original paper.

Simply

A new AI tool helps scientists quickly check if medical studies are trustworthy, then records every step of that check in a digital family tree so everyone can see exactly how decisions were made, making research more transparent.

In depth

The paper introduces a novel end-to-end pipeline, INSPECT-AI, that leverages Large Language Models (LLMs) to semi-automate the integrity assessment of Randomised Controlled Trials (RCTs). It also establishes the Research Integrity Provenance and Evidence Ontology (RIPE-O) and Knowledge Graph (RIPE-KG) to transparently document and share the provenance of these assessments, addressing the subjectivity and manual effort of current methods.

Key Takeaways

1
The INSPECT-AI tool significantly enhances the efficiency of human reviewers by using LLMs to extract evidence and suggest outcomes for RCT integrity checks.
2
The RIPE-O ontology provides a standardized semantic framework for documenting the complete provenance of research integrity assessments, ensuring transparency and reproducibility.
3
The RIPE-KG knowledge graph aggregates and publishes these provenance traces, enabling advanced analysis of assessment disagreements and author networks, and facilitating integration with other scholarly data.

Conceptual Flow

HIGH LEVEL

Automating Trustworthiness Checks

A smart computer program helps people quickly check if medical studies are honest, making the process faster and more consistent.

Medical Study Paper

AI Helps Check

Trustworthiness Report

Transparent Decision Tracking

Every step of how a study's honesty was checked is written down like a detailed story, so anyone can understand why decisions were made.

Check Steps

Decisions Made

Record Everything

Clear Decision History

This breakdown was generated by SciGrove. Get the same analysis — intuition, storyboard, peer review, a runnable prototype and a glossary — on any paper you upload or paste a DOI for.