Text-based electronic health records contain useful information about the disease progression and treatment plans of patients, and provide an important resource to better understand the associations between complex disease processes and patient outcomes. This project aims to apply natural language processing, machine learning, and statistical analysis to automatically identify clinical concepts from large-scale textbased patient medical records of a large Intensive Care Unit (ICU) database for patient prognosis, disease correlation studies, and cohort stratifications.

I am a 6-3 senior, and my SuperUROP project aims to apply natural language processing, machine learning, and statistical analysis to automatically identify clinical concepts from text-based patient ICU medical records. I hope to learn more about critical care informatics, and I am excited to study whether text-based patient medical records can be used to better predict patient outcomes.