Clinical Text Datasets


Lung and colorectal cancer data:

The dataset will be a subset of the Cancer Enterprise Data Warehouse, which contains only patients with lung and colorectal cancer. It includes each patient’s health history, demographics, vitals, diagnoses, medications, laboratory results, hospital utilization and more. The dataset will be linked with tumor registry data (including cancer identification, stage, TNM stage, treatment, prognostic factors, recurrence,etc) and all de-identified clinical notes (including radiology reports,etc).

Clinical NLP