HARVEST: Longitudinal Patient Record Summarization

harvest As more and more raw data observations are recorded about patients in their record, providers are face with an overwhelming amount of complex data points, with little time for making sense of them all. This phenomenon of information overload has been observed in several care settings, from outpatient clinics and primary care, to hospital admissions, and the emergency room. With the advant of health information exchange, reviewing of patient data will only become more complex and time consuming for clinicians. One of the promises of the electronic health record is to support clinicians at the point of care. Clinical information systems, unfortunately, seldom provide effective cognitive support - i.e., they do not present information in an optimal format to clinicians when and where it is needed.

HARVEST is an interactive, problem-oriented patient record summarization system. The summarizer differs from previous work in three critical ways: (i) it extracts content from the patient notes, where key clinical information resides; (ii) it aggregates and presents information from multiple care settings, including inpatient, ambulatory, and emergency department encounters; and (iii) it is integrated into the clinical information review system iNYP at New York Presbyterian Hospital, and is available for all patients in our institution, not just a curated dataset or for specific patient cohorts.

People - HARVEST
  • Noémie Elhadad
  • Sharon Lipsky Gorman, MS
  • Danish Ghazali
  • Rebekah Kim
  • Benjamin Bloxham, MD (alumn)
  • Jamie Hirsch, MD, MA (alumn)
  • Connie Liu, BS (alumn)
  • Cristel Oropesa (alumn)
  • Daniel Reichert, MA (alumn)
  • Rimma Pivovarov, PhD (alumn)
  • Jessica Tanenbaum, MD (alumn)
  • Rebecca Tisdale, MD (alumn)
People - NewYork-Presbyterian Hospital
  • Marc Sturm
  • David Vawdrey
  • Karthik Natarajan
Patient record summarization papers

Work for HARVEST is funded by the National Library of Medicine (R01 LM010027) and the National Science Foundation (#1344668).


Last Updated: 7/2016
noemie.elhadad @ columbia.edu