Skip to main navigation Skip to search Skip to main content

EvidenceOutcomes: A Dataset of Clinical Trial Publications with Clinically Meaningful Outcomes

  • Yiliang Zhou
  • , Abigail M. Newbury
  • , Gongbo Zhang
  • , Betina Ross Idnay
  • , Hao Liu
  • , Chunhua Weng
  • , Yifan Peng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The fundamental process of evidence extraction in evidence-based medicine relies on identifying PICO elements, with Outcomes being the most complex and often overlooked. To address this, we introduce EvidenceOutcomes, a large annotated corpus of clinically meaningful outcomes. A robust annotation guideline was developed in collaboration with clinicians and NLP experts, and three annotators annotated the Results and Conclusions of 500 PubMed abstracts and 140 EBM-NLP abstracts, achieving an inter-rater agreement of 0.76. A fine-tuned PubMedBERT model achieved F1 scores of 0.69 (entity level) and 0.76 (token level). EvidenceOutcomes offers a benchmark for advancing machine learning algorithms in extracting clinically meaningful outcomes.

Original languageEnglish
Title of host publicationMEDINFO 2025 - Healthcare Smart x Medicine Deep
Subtitle of host publicationProceedings of the 20th World Congress on Medical and Health Informatics
EditorsMowafa S. Househ, Mowafa S. Househ, Zain Ul Abideen Tariq, Mahmood Al-Zubaidi, Uzair Shah, Elaine Huesing
PublisherIOS Press BV
Pages723-727
Number of pages5
ISBN (Electronic)9781643686080
DOIs
StatePublished - 7 Aug 2025
Event20th World Congress on Medical and Health Informatics, MEDINFO 2025 - Taipei, Taiwan, Province of China
Duration: 9 Aug 202513 Aug 2025

Publication series

NameStudies in Health Technology and Informatics
Volume329
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference20th World Congress on Medical and Health Informatics, MEDINFO 2025
Country/TerritoryTaiwan, Province of China
CityTaipei
Period9/08/2513/08/25

Keywords

  • Biomedical Literature Research
  • NLP
  • PICO Outcomes
  • RCT

Fingerprint

Dive into the research topics of 'EvidenceOutcomes: A Dataset of Clinical Trial Publications with Clinically Meaningful Outcomes'. Together they form a unique fingerprint.

Cite this