@inproceedings{0b8c12b01cee4b819804ec129554bf2e,
title = "EvidenceOutcomes: A Dataset of Clinical Trial Publications with Clinically Meaningful Outcomes",
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.",
keywords = "Biomedical Literature Research, NLP, PICO Outcomes, RCT",
author = "Yiliang Zhou and Newbury, \{Abigail M.\} and Gongbo Zhang and Idnay, \{Betina Ross\} and Hao Liu and Chunhua Weng and Yifan Peng",
note = "Publisher Copyright: {\textcopyright} 2025 The Authors.; 20th World Congress on Medical and Health Informatics, MEDINFO 2025 ; Conference date: 09-08-2025 Through 13-08-2025",
year = "2025",
month = aug,
day = "7",
doi = "10.3233/SHTI250935",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press BV",
pages = "723--727",
editor = "Househ, \{Mowafa S.\} and Househ, \{Mowafa S.\} and Tariq, \{Zain Ul Abideen\} and Mahmood Al-Zubaidi and Uzair Shah and Elaine Huesing",
booktitle = "MEDINFO 2025 - Healthcare Smart x Medicine Deep",
}