Leveraging Clinical Narrative Text at Scale: Applying Natural Language Processing to Understand the Patient Care Experience
Recent advances in biomedical informatics, such as the application of machine learning and natural language processing (NLP) to Electronic Health Record (EHR) data, have resulted in breakthroughs in the ability to identify, classify, and predict aspects of patient care, symptoms, and communication in the clinical record. These new tools that allow researchers and clinicians to generate and examine new research questions examining patient care quality and health-related quality of life.
This webinar presents four research studies highlighting different NLP applications in EHR free text. Topics include (1) phenotyping for treatment-related side effects and system severity, (2) cancer treatment-related side-effects, (3) non-adherence to cancer therapy and recurrence, and (4) documentation of patient care goals.
Presenters discuss how these methodologies support the capture and use of real-world data for precision oncology care, population health management, and how to scale-up applications within and across health care systems.
Extramural investigators at junior, mid, and senior levels. Basic familiarity with data science methods may be helpful, but not required.
Julian Hong, MD, MS
Healthcare Delivery Research Program
Department of Radiation Oncology
UCSF Medical Center
Charlotta Lindvall, MD, PhD
Instructor, Medicine, Harvard Medical School
Physician, Department of Psychosocial Oncology and Palliative Care
Dana-Farber Cancer Institute
Tina Hernandez-Boussard, PhD
Stanford University School of Medicine
Imon Banerjee, PhD
Department of Biomedical Informatics
Emory University School of Medicine
For more information, please contact Roxanne Jensen.
This webinar will be archived on the HDRP Events webpage.