Abstract: Leveraging clinical narratives to classify patients based on phenotype requires layers of annotations. Representation of the knowledge described in the reports is critical to accurate extraction of that information. In this talk, Dr. Chapman will describe application ontologies her lab has developed for modeling annotations of information described in clinical reports. She will illustrate the usefulness of the formalism with several use cases and describe a vision of how the ontologies can potentially support collaborative knowledge authoring and NLP customization.
Bio: Dr. Chapman earned her Bachelor's degree in Linguistics and her PhD in Medical Informatics from the University of Utah in 2000. From 2000-2010 she was a National Library of Medicine postdoctoral fellow and then a faculty member at the University of Pittsburgh. She joined the Division of Biomedical Informatics at the University of California, San Diego in 2010. In 2013, Dr. Chapman became the chair of the University of Utah, Department of Biomedical Informatics.
Dr. Chapman’s research focuses on developing and disseminating resources for modeling and understanding information described in narrative clinical reports. She is interested not only in better algorithms for extracting information out of clinical text through natural language processing (NLP) but also in generating resources for improving the NLP development process (such as shareable annotations and open source toolkits) and in developing user applications to help non-NLP experts apply NLP in informatics-based tasks like clinical research and decision support.
Abstract: The Human Phenotype Ontology (HPO) was developed to describe phenotypic abnormalities, aka, “deep phenotyping”, whereby symptoms and characteristic phenotypic findings (a phenotypic profile) are captured. The HPO has been utilized to great success for assisting computational phenotype comparison against known diseases, other patients, and model organisms to support diagnosis of rare disease patients. Clinicians and geneticists create phenotypic profiles based on clinical evaluation, but this is time consuming and can miss important phenotypic features. Patients are sometimes the best source of information about their symptoms that might otherwise be missed in a clinical encounter. However, HPO primarily use medical terminology, which can be difficult for patients and their families to understand. To make the HPO accessible to patients, we systematically added non-expert terminology (i.e., layperson terms) synonyms. Using semantic similarity, patient-recorded phenotypic profiles can be evaluated against those created clinically for undiagnosed patients to determine the improvement gained from the patient-driven phenotyping, as well as how much the patient phenotyping narrows the diagnosis. This patient-centric HPO can be utilized by all: in patient-centered rare disease websites, in patient community platforms and registries, or even to post one’s hard-to-diagnosed phenotypic profile on the Web.
Bio: Dr. Haendel is an Associate Professor in the Library and the Department of Medical Informatics & Clinical Epidemiology at the Oregon Health & Science University (OHSU), where she directs the Ontology Development Group. She is the principal investigator of the Monarch Initiative and is an active researcher in ontologies and data standards. Melissa is known for her work on biomedical resource discovery, open science and reproducibility, and for her work on anatomy, cell, and phenotype ontologies such as Uberon and the Human Phenotype Ontology. She holds a Ph.D. Neuroscience from the University of Wisconsin and completed postdoctoral training at the University of Oregon and Oregon State University.
Abstract: The explosion of biomedical big data and information in the past decade or so has created new opportunities for discoveries to improve the treatment and prevention of human diseases. But the large body of knowledge—mostly exists as free text in journal articles for humans to read—presents a grand new challenge: individual scientists around the world are increasingly finding themselves overwhelmed by the sheer volume of research literature and are struggling to keep up to date and to make sense of this wealth of textual information. Our research aims to break down this barrier and to empower scientists towards accelerated knowledge discovery. We will discuss our work on developing large-scale text-mining tools as well as their uses in real-world applications such as extracting genotype-phenotype associations from PubMed articles for precision medicine and computer-assisted database curation.
Bio: Dr. Lu is Earl Stadtman investigator at NCBI, part of the National Library of Medicine/National Institutes of Health, where he directs the text mining research and oversees the development and operation of PubMed search to enhance information access to the biomedical literature. Dr. Lu is an Associate Editor for BMC Bioinformatics and serves on the editorial board for the Journal Database. He is an organizer of the international BioCreative challenge and has authored over 120 publications.