@inproceedings{780001ac890040a9b051af9178fb114a,
title = "A Sample Size Extractor for RCT Reports",
abstract = "Sample size is an important indicator of the power of randomized controlled trials (RCTs). In this paper, we designed a total sample size extractor using a combination of syntactic and machine learning methods, and evaluated it on 300 Covid-19 abstracts (Covid-Set) and 100 generic RCT abstracts (General-Set). To improve the performance, we applied transfer learning from a large public corpus of annotated abstracts. We achieved an average F1 score of 0.73 on the Covid-Set testing set, and 0.60 on the General-Set using exact matches. The F1 scores for loose matches on both datasets were over 0.74. Compared with the state-of-the-art tool, our extractor reports total sample sizes directly and improved F1 scores by at least 4\% without transfer learning. We demonstrated that transfer learning improved the sample size extraction accuracy and minimized human labor on annotations.",
keywords = "Natural Language Processing, Randomized Controlled Trial, Sample Size",
author = "Fengyang Lin and Hao Liu and Paul Moon and Chunhua Weng",
note = "Publisher Copyright: {\textcopyright} 2022 International Medical Informatics Association (IMIA) and IOS Press.; 18th World Congress on Medical and Health Informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021 ; Conference date: 02-10-2021 Through 04-10-2021",
year = "2022",
month = jun,
day = "6",
doi = "10.3233/SHTI220151",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press BV",
pages = "617--621",
editor = "Paula Otero and Philip Scott and Martin, \{Susan Z.\} and Elaine Huesing",
booktitle = "MEDINFO 2021",
}