DeepPhe: A Natural Language Processing System for Extracting Cancer Phenotypes from Clinical Records
On Wednesday, October 23, Dr. Guergana Savova and Dr. Harry Hochheiser will present "DeepPhe - A Natural Language Processing System for Extracting Cancer Phenotypes from Clinical Records."
In this talk, Dr. Savova and Dr. Hochheiser will describe the DeepPhe system for extracting rich cancer phenotypes and its visual analytics platform. Electronic medical records offer a potential wealth of information about cancer patients; most automated extraction efforts have focused on single document types or data elements. DeepPhe differs from prior efforts, moving beyond entity mention recognition to summaries over the entire set of patient’s records, and longitudinally from primary tumor to regional recurrence or metastasis. DeepPhe is funded through NCI’s Informatics Technology for Cancer Research (ITCR) program (5U24CA184407-06).
The Data Science Seminar Series presents talks from innovators in the research and informatics communities both within and outside of NCI.
Dr. Guergana Savova is an associate professor at the Boston Children's Hospital Computational Health Informatics Program (CHIP) and Harvard Medical School. Her research interests are in Natural Language Processing, a sub-field of Artificial Intelligence that has witnessed astounding developments in the last several years. The mission of Dr. Savova’s lab is processing all health-related language with the goal to advance biomedicine. Dr. Savova and her lab have been part of many high-impact federally funded projects. They have contributed to the open-source community Apache Clinical Text Analysis and Knowledge Extraction System (cTAKES) and Deep Phenotyping for Cancer (DeepPhe), which have been widely used. The Apache Software Foundation recognized cTAKES as one of its top 20 most influential projects. Dr. Guergana Savova holds a doctorate in linguistics with a minor in cognitive science and a master's degree in computer science from University of Minnesota. Before joining Boston Children’s Hospital and Harvard Medical School in 2010, Dr. Savova was a technical staff and faculty member at the Biomedical Statistics and Informatics Department at the Mayo Clinic from 2002 to 2010.
Dr. Harry Hochheiser is an associate professor in the Department of Biomedical Informatics and the Intelligent Systems Program at the University of Pittsburgh. He is also director of the University of Pittsburgh Biomedical Informatics Training Program. His research interests are in the understanding of user needs and the development and evaluation of advanced user interfaces capable providing clinicians and researchers with easier and more flexible access to rich biomedical data. Recent projects include Deep Phenotyping for Cancer (DeepPhe), information displays for the Learning Electronic Medical Record (LEMR), and visualization designs for clinical predictive models. Dr. Hochheiser has a doctorate in computer science from the University of Maryland and bachelor's and master's degrees from the Massachusetts Institute of Technology. He is co-author of Research Methods in Human-Computer Interaction (Morgan Kaufmann, 2017).
- Clinical Proteomic Tumor Analysis Consortium Scientific SymposiumOctober 16, 2019DeepPhe: A Natural Language Processing System for Extracting Cancer Phenotypes from Clinical RecordsOctober 23, 2019ATOM Fellowship Virtual Information Session 2October 28, 2019Identifying Research Gaps and Setting a Research AgendaOctober 29, 2019Office of Cancer Clinical Proteomics Research (OCCPR) Proteomic Data Commons WebinarNovember 13, 2019Informatics for Genomics-informed Surveillance of RNA VirusesNovember 13, 2019Genomic Data Commons (GDC) Data Submission WebinarNovember 25, 2019The HemOnc Chemotherapy Regimen VocabularyDecember 18, 2019