Deep Learning and Natural Language Processing Methods for Mining Electronic Medical Records
Overview:
Without access to unstructured free-text clinical notes, many types of clinical data such as symptoms, severity, history of illness, and events at other institutions remain inaccessible. In this talk, Masoud Rouhizadeh discusses his work at the Johns Hopkins Precision Medicine Analytics Platform, including clinical concept extraction, identifying social and behavioral determinants of health, and extracting COVID-19 symptoms from hospital admission notes.
Speaker:
Masoud Rouhizadeh, PhD, MSc, MA, is an assistant professor in the University of Florida College of Pharmacy, Department of Pharmaceutical Outcomes, under the AI in the Health Sciences Initiative. The primary focus of Rouhizadeh’s research involves applying machine learning and natural language processing methods for identifying clinical concepts from unstructured text and converting them into structured data. Another major part of his research has been developing clinical ontologies and lexical resources, as well as computational models for identifying social and behavioral determinants of health. Before joining the UF, Rouhizadeh was a faculty instructor at Biomedical Informatics and Data Science and the Natural Language Processing lead at the Institute for Clinical and Translational Research at the Johns Hopkins University School of Medicine. Prior to JHU, he was a postdoctoral fellow at the University of Pennsylvania’s World Well-Being Project and then at the Penn Institute for Biomedical Informatics. He obtained his Master’s and PhD in Computer Science and Engineering from Oregon Health and Science University and his master's degree in Human Language Technology from the University of Trento, Italy.
Originally recorded on Wednesday, November 30, 2021, as part of CHOIR's
Overview:
Without access to unstructured free-text clinical notes, many types of clinical data such as symptoms, severity, history of illness, and events at other institutions remain inaccessible. In this talk, Masoud Rouhizadeh discusses his work at the Johns Hopkins Precision Medicine Analytics Platform, including clinical concept extraction, identifying social and behavioral determinants of health, and extracting COVID-19 symptoms from hospital admission notes.
Speaker:
Masoud Rouhizadeh, PhD, MSc, MA, is an assistant professor in the University of Florida College of Pharmacy, Department of Pharmaceutical Outcomes, under the AI in the Health Sciences Initiative. The primary focus of Rouhizadeh’s research involves applying machine learning and natural language processing methods for identifying clinical concepts from unstructured text and converting them into structured data. Another major part of his research has been developing clinical ontologies and lexical resources, as well as computational models for identifying social and behavioral determinants of health. Before joining the UF, Rouhizadeh was a faculty instructor at Biomedical Informatics and Data Science and the Natural Language Processing lead at the Institute for Clinical and Translational Research at the Johns Hopkins University School of Medicine. Prior to JHU, he was a postdoctoral fellow at the University of Pennsylvania’s World Well-Being Project and then at the Penn Institute for Biomedical Informatics. He obtained his Master’s and PhD in Computer Science and Engineering from Oregon Health and Science University and his master's degree in Human Language Technology from the University of Trento, Italy.