Classifiers of Data Sharing Statements in Clinical Trial Records
This work addresses the challenge of efficiently locating reusable clinical trial data for researchers, but it is incremental as it applies existing NLP methods to a specific domain without major methodological breakthroughs.
The study tackled the problem of identifying available individual participant data (IPD) in clinical trials by evaluating classifiers based on domain-specific pre-trained language models to interpret textual data-sharing statements (DSS). The result showed that classifiers predicting manual annotations outperformed those using original availability categories, suggesting that textual DSS contain additional useful information for automatic IPD identification.
Digital individual participant data (IPD) from clinical trials are increasingly distributed for potential scientific reuse. The identification of available IPD, however, requires interpretations of textual data-sharing statements (DSS) in large databases. Recent advancements in computational linguistics include pre-trained language models that promise to simplify the implementation of effective classifiers based on textual inputs. In a subset of 5,000 textual DSS from ClinicalTrials.gov, we evaluate how well classifiers based on domain-specific pre-trained language models reproduce original availability categories as well as manually annotated labels. Typical metrics indicate that classifiers that predicted manual annotations outperformed those that learned to output the original availability categories. This suggests that the textual DSS descriptions contain applicable information that the availability categories do not, and that such classifiers could thus aid the automatic identification of available IPD in large trial databases.