The datasheets in this repo document structured (or tabular) data used by the Pathology Data Mining team. The data encompasses modalities listed in the Datasets section below. template.md describes the schema of each datasheet. The template has been designed to give a sense of completeness to the documentation behind a dataset, for ease of use, and for ease of maintenance. This template should be used as a guide for the creation and maintenace of these datasheets.
Clinical Data Mining (CDM) - Datasets generated from abstracting data elements from clinical reports
IMPACT - MSK IMPACT genomic datasets
HoBBit - Pathology slide inventory datasets
Pathology Data Mining (PDM) - Datasets generated from abstracting data elements from pathology slides