Related Experiment Video
Updated: Aug 10, 2026

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
The consensus-based CINEX guideline for reporting clinical information extraction studies
Daniel Reichenpfader1,2, Jamil Zaghir3,4, Elsa Cécilia-Joseph5,6
1School of Life Sciences, Faculty of Medicine, University of Geneva, Geneva, 1206, Switzerland.
A new guideline, CINEX, was developed to standardize reporting for clinical information extraction (IE) studies. This framework enhances transparency and reproducibility in AI research for better clinical translation.
Area of Science:
- Natural Language Processing
- Clinical Informatics
- Artificial Intelligence
Background:
- Information extraction (IE) from clinical texts has advanced due to large language models (LLMs).
- Inconsistent reporting of methodologies hinders reproducibility and clinical translation of IE studies.
- A need exists for standardized reporting guidelines specific to clinical IE.
Purpose of the Study:
- To develop a consensus-based reporting guideline tailored for clinical information extraction (IE) studies.
- To enhance transparency, reproducibility, and interpretability in clinical IE research.
Main Methods:
- The Clinical Information Extraction Reporting Guideline (CINEX) was developed using a multi-phase approach.
- A scoping review informed an initial set of items, refined through a 3-round electronic Delphi study with 20 international experts.
- The guideline was finalized in a consensus meeting, with items iteratively refined based on expert feedback and predefined criteria.
Main Results:
- The CINEX guideline consists of 29 checklist items across 5 domains: information model, architecture, data, annotation, and outcomes.
- Consensus for inclusion was reached on all items through the Delphi process.
- The guideline development involved 20 experts across 3 rounds of electronic Delphi study.
Conclusions:
- CINEX offers a structured framework to improve transparency and reproducibility in clinical IE.
- Standardizing reporting of data provenance, annotation, and evaluation facilitates study comparison.
- CINEX complements existing AI reporting standards by addressing clinical IE-specific challenges, supporting safer clinical implementation.
Related Concept Videos
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Clinical Trials
There are four phases in a clinical trial. A phase one...
Clinically Relevant Drug Product Specifications: Methods of Establishment
Clinical Trials: Overview
