Associate Professors Halil Kilicoglu and Jodi Schneider are part of a team of researchers who have received a three-year, $947,925 grant from the National Institutes of Health/National Library of Medicine (NIH/NLM) to improve upon a tool that clinicians, researchers, and systematic reviewers use to retrieve biomedical articles from bibliographic databases. Kilicoglu and Schneider will work with Affiliate Professor Neil Smalheiser, professor of psychiatry at the University of Illinois Chicago, on the project, "Automated Indexing for Publication Types and Study Designs."
Schneider previously received a subaward for her work on the original Multi-Tagger tool, which was designed by Smalheiser and Aaron Cohen, professor in the Oregon Health and Science University's Department of Medical Informatics and Clinical Epidemiology. Through this work, she found that the tool's automated publication type filtering could make systematic reviews more efficient.
More than 3 million searches currently are conducted on PubMed, the NLM's widely used bibliographic search engine. Multi-Tagger 2.0 will include additional publication types and study designs; state-of-the-art, explainable neural models; and better alignment with user needs.
"The new Multi-Tagger 2.0 models will be incorporated into the Anne O'Tate tool, a publicly available text mining-augmented search engine for biomedical literature. The tool will enable more fine-grained publication type and study design searches than are currently possible in PubMed," said Kilicoglu.
"Identifying what publication types people need to find, that PubMed is missing, will be a key part of the project," added Schneider.
Schneider will work with stakeholders such as medical librarians, health services researchers, and informaticians to consider performance and use cases to evaluate the models. Kilicoglu will develop datasets and natural language processing models and their validation.
Schneider studies the science of science through the lens of arguments, evidence, and persuasion. Her long-term research agenda analyzes controversies applying science to public policy; how knowledge brokers influence citizens; and whether controversies are sustained by citizens' disparate interpretations of scientific evidence and its quality. She holds a PhD in informatics from the National University of Ireland, Galway, and master's degrees in library and information science from the University of Illinois and mathematics from the University of Texas at Austin.
Kilicoglu's research interests include biomedical informatics, natural language processing, knowledge representation, scholarly communication, and scientific reproducibility. He holds a PhD in computer science from Concordia University.