Precision Medicine Symposium 2022: Tickets are open and event is free to Register.Register
Precision Medicine Symposium 2022: Tickets are open and event is free to Register.Register
Epic
Electronic Medical Records, including patient demographics, encounters, notes, labs, flowsheets, and more
REDCap
Research registries
Custom data
sources
Research Access databases spreadsheets
Vendor
Neutral
Archives
Radiology imaging
Physiological monitors
Including critical care units
Note: Additional sources can be requested and added
The Data Commons is a repository that collects patient data from all across Johns Hopkins Medicine. You can think of it as an enterprise data warehouse or data lake.
It currently pulls data from our Electronic Medical Record system, Vendor Neutral Archives (radiology), Hospital Physiological Monitoring, and several research databases (REDcap, Access, SQL and others). We plan to add other sources over time. The data from all those sources is cross-linked and joined into a very wide patient-focused data set.
Subsets of data from the Data Commons can be extracted for your use in research or in patient quality and safety improvement. You can use the Data Catalog to look for tables an * of data you can request.
If you have an approved IRB protocol, you can request a subset of data from the Data Commons. That subset is delivered to you in a Data Projection. Your Data Projection will include a read-only database that houses your IRB-approved data, and a writeable database.
You can access your Data Projection as well as a suite of Analytical Tools through the SAFE Desktop.
You can access your data and the Data Catalog through the SAFE Desktop.
The SAFE Desktop comes installed with several tools for exploration and analysis.
You can try it out for free now, via the SAFE Desktop following these steps:
When you're ready to use the PMAP for an IRB-approved study:
OMOP
The Observational Medical Outcomes Partnership (OMOP) brings a global data standard to Johns Hopkins, enabling researchers to accelerate outcomes research.
Installed for exploration and analysis, including:
Microsoft SQL Server
Database management system
sas
Statistical analysis
Stata
Statistical software
R
Statistical Computing
R Studio
Integrated Development Environment
Python
Programming language
Access several tools that can handle more computationally intensive workloads
and modern machine learning tools.
crunchr
Collaboration, Jupyter Notebooks
Provides access to Jupyter Notebooks to write and run analytical code right in your browser. You can work on your code with co-investigators.
Data Catalog
Explore Available Data Sets
Data Catalog uses tags to assist with catalog searching, so that users do not need to know exact table and field names in order to find entries of interest. Example tags include: Demographics. Labs, Medication, Vital, Biospecimen.
Computing resources to work with PMAP data. (These resources may have their own cost)
Phoenix
Hopkins High Performance Computing
Micosoft Azure Databricks
Apache Spark-base analytics
Note: our data and computational resources exist in a HIPAA-compliant, IRB- and Data Trust-approved environment.
We use reusable visualizations and data modules to build clinical decision support tools, patient education tools, and more, and make them available within Epic if appropriate.
Learn about Active Care, a Delivery Application helping Prostate Cancer patients and doctors make decisions.
Contact us for a consult and pricing.