BioSift: A Dataset for Filtering Biomedical Abstracts for Drug Repurposing and Clinical Meta-Analysis

Abstract

This work presents a new, original document classification dataset, , to expedite the initial selection and labeling of studies for drug repurposing. The dataset consists of 10,000 human-annotated abstracts from scientific articles in PubMed. Each abstract is labeled with up to eight attributes necessary to perform meta-analysis utilizing the popular patient-intervention-comparator-outcome (PICO) method: has human subjects, is clinical trial/cohort, has population size, has target disease, has study drug, has comparator group, has a quantitative outcome, and an “aggregate” label. Each abstract was annotated by 3 different annotators (i.e., biomedical students) and randomly sampled abstracts were reviewed by senior annotators to ensure quality. Data statistics such as reviewer agreement, label co-occurrence, and confidence are shown. Robust benchmark results illustrate neither PubMed advanced filters nor state-of-the-art document classification schemes (e.g., active learning, weak supervision, full supervision) can efficiently replace human annotation. In short, is a pivotal but challenging document classification task to expedite drug repurposing. The full annotated dataset is publicly available and enables research development of algorithms for document classification that enhance drug repurposing.

An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia

“… Use of transfer learning—Transfer learning, which applies knowledge gained from a larger distribution or dataset to a smaller one, could be added as a module to the proposed general framework for specific research use cases [ 80 ] However, in general, transfer learning would not be as generally suited to all rare disease, particularly heterogeneous rare diseases, because their sample distributions may not be well represented by the larger aggregate or average model distribution. Use of large language models—Large language models like ChatGPT may enable the aggregation and extraction of multiple published rare disease datasets in order to increase the available sample sizes for standard collected features [ 81 ]. While large language models excel in producing tabular data from unstructured data, most are currently not specifically suited for the generation of predictions using small-sample-size tabular data.…”

“…Use of large language models—Large language models like ChatGPT may enable the aggregation and extraction of multiple published rare disease datasets in order to increase the available sample sizes for standard collected features [ 81 ]. While large language models excel in producing tabular data from unstructured data, most are currently not specifically suited for the generation of predictions using small-sample-size tabular data.…”