Cohort Explorer

Cohort Explorer is PennOmics’ self-service tool which grants researchers direct access to a fully de-identified dataset compiled from Penn’s patient population and complimented by genomic data from clinical labs and contributing researchers throughout the university and health system. The de-identified data set allows users to query Penn data without the need for an approved IRB protocol or Quality improvement project. 


Data Set

In order to de-identify the clinical data, all HIPAA identifiers have been stripped from the data set with the exception of dates. Dates are shifted by a random number of days between -5 and -25. Each patient’s days are shifted by the random number assigned to them. This means users are still able to find the exact number of patients who had a certain diagnosis X number of days before a procedure but not the number of procedures that occurred on a given date.

Data domains include:


Patient Demographics

Encounter/Visit Details

Coded Diagnosis

Coded Procedures

Administered Medications

Lab results


Vital Signs

Tumor Registry Dx, Stage, and Grade

Clinical Genetic results

Research Genetics

Clinical Trails


Users may request access by emailing Patrick Sullivan

Accounts are created after requestors complete a ~1hr training session and fill out a Data Use Agreement.

Those with accounts may log in at: