Colloquium - Halil Kilicoglu, "Enhancing Rigor and Integrity of Biomedical Research using Natural Language Processing"

Abstract: 
There has been much debate about rigor, transparency, and reproducibility of biomedical research in recent years. Ongoing efforts aim to address issues in research conduct and reporting by developing standards, guidelines, and recommendations. As biomedical research output increases exponentially, automated tools are needed to complement such efforts and assist the stakeholders (e.g., researchers, journals, peer reviewers, funders, policymakers) in assessing and improving research output efficiently.  In this talk, I will discuss how NLP methods can help improve rigor and transparency in biomedical communication, as reflected in textual artifacts such as protocols, manuscripts, and publications. I will then present two research projects that we have been pursuing in this area: a) evaluating the methodological and reporting quality of clinical trial publications, and b) assessing citation integrity in biomedical literature. Finally, I will highlight some of the key challenges for NLP in this application domain.

Bio:
Dr. Halil Kilicoglu is Associate Professor in the School of Information Sciences (iSchool) at the University of Illinois Urbana-Champaign. He specializes in natural language processing (NLP), artificial intelligence/machine learning (AI/ML), and knowledge representation with biomedical applications. His work aims to extract and organize knowledge buried in textual artifacts to benefit biomedical discovery and scholarship, and improve healthcare outcomes. His recent work includes development of automated methods to assess research rigor, transparency, and integrity of biomedical publications. Prior to joining the iSchool faculty in 2019, he was a research scientist at the U.S. National Library of Medicine, National Institutes of Health (NLM/NIH), where he led the Semantic Knowledge Representation project. His research has been funded by NIH, AHRQ, and HHS Office of Research Integrity.