EMERSE (coming soon)
EMERSE (Electronic Medical Record Search Engine) is a tool that allows researchers to query free text data from the WCM/NYP electronic health record. Users can search a wide variety of concepts, including diseases, drugs, symptoms and more, to identify which patients have these concepts mentioned in any free text document in their electronic health record.
Using EMERSE, you can answer questions like "How many patients have a mention of pleomorphic sarcoma in their clinical notes stored in Epic?" on your own, without the need for a data analyst, or any technical expertise. EMERSE is particularly useful in situations where a free text note is the only way to identify a concept of interest.
i2b2 enables researchers to determine counts of patients using data from EHR systems. Through a point-and-click interface, researchers can define cohorts of patients using de-identified data from both Epic and Allscripts without the need for IRB approval.
Once an investigator has defined the cohort of interest, s/he can, with IRB approval, obtain a list of MRNs for the patients in question.
Researchers can use i2b2 to answer questions like:
- “How many patients have a history of colon cancer using ICD-9 codes 153.* and 154.*?"
- “How many patients with colon cancer were younger than age 50 at the time of initial diagnosis?”
- “How many patients with colon cancer had a colectomy procedure performed and then were admitted to the hospital within 30 days?”
Interested in learning how to use i2b2?
In-person workshops are held on the last Thursday of every month at the Library Surface Hub from 11am to 12:30pm. More info is available at firstname.lastname@example.org.
TriNetX also enables researchers to determine counts of patients using data from EHR systems, similar to i2b2. The TriNetX user experience differs from i2b2 and some WCM-specific data points are not available (e.g. eye exam results, hospital sites and departments). However, TriNetX also allows users to query the TriNetX Research Network, which includes deidentified data from 100+ million patients.
Interested in learning how to use TriNetX?