Classifiers of Data Sharing Statements in Clinical Trial Records

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mamaghani, Saber Jelodari, Strantz, Cosima, Toddenroth, Dennis
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915157416869888
author Mamaghani, Saber Jelodari
Strantz, Cosima
Toddenroth, Dennis
author_facet Mamaghani, Saber Jelodari
Strantz, Cosima
Toddenroth, Dennis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12362
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Classifiers of Data Sharing Statements in Clinical Trial Records
Mamaghani, Saber Jelodari
Strantz, Cosima
Toddenroth, Dennis
Computation and Language
Artificial Intelligence
68T50
I.2.7; J.3
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.
title Classifiers of Data Sharing Statements in Clinical Trial Records
topic Computation and Language
Artificial Intelligence
68T50
I.2.7; J.3
url https://arxiv.org/abs/2502.12362