The Toolkit

Penn Labs projects have access to a software development kit that includes a real-time API to read certain data from the UPHS electronic medical records. This is hosted on a linux server within the UPHS firewall.

Learn more about Sandbox and Clinstream

Other Resources (Datasets & APIs/SDKs)

Medicare Provider Utilization & Payment Data- information on services and procedures provided to Medicare beneficiaries by physicians and other healthcare professionals.

County Health Rankings - Various health metrics by county.

Hospital Quality Data (CMS) - Data on how well hospitals care for patients with certain conditions or procedures.

NPI Database

Medicare Databases

Health & Human Services Datasets - Over 1100 searchable datasets ranging from hospital-acquired infections to readmissions.

HHS Hospital Charge Data - include information comparing the charges for the 100 most common inpatient services and 30 common outpatient services.

National Cancer Institute SEER Database - Examine cancer data such as cancer stage at diagnosis by race/ethnicity, survival rate by stage, or trends and incidence rates of cancers at various sites over time. Requires 2 business days of lead time for approval.

Practice Fusion Insight Database - a real-time healthcare database based upon records of over 250K patients per day. You’ll be able to see information like disease trends over time and by patient, what diseases are being diagnosed, and real-time prescription drug market share.

FDA Databases

FDA Drugs@FDA Database

Behavioral Risk Factor Surveillance System (BRFSS) Data- uniform, state-specific data on preventive health practices and risk behaviors that are linked to chronic diseases, injuries, and preventable infectious diseases that affect the adult population.

Dartmouth Atlas of Health Care Data - Datasets on Medicare spending, variation in the care of surgical conditions, Medicare mortality rates, selected measures of primary care access and quality, Children’s health care in Northern New England, prescription drug use, selected hospital and physician capacity measures, geographic boundary files, end-of-life chronic illness care, and hospital and post-acute care.

Cancer Biomedical Informatics Grid (caBIG) Databases - Genomic/clinical data on glioblastoma multiforme and ovarian tumors; gene and chromosomal information, expression data, and clinical outcomes; mutation, copy number, and DNA methylation data; imaging databases; and protein and pathway information databases.

Unified Medical Language System Downloads - RxNorm, SNOMED, ICD–9 Diagnostic Codes, IDC–9 Procedure Codes

Insight Toolkit - an open-source, cross-platform system that provides developers with an extensive suite of software tools for image analysis.

Merge HL7 Toolkit - Develop and deploy HL7 interfaces using workflow enabled tools that provide stability and control.

Merge DICOM Toolkit - Develop DICOM interfaces that are highly optimized for a wide range of platforms with uncompromised stability and performance.

Postmates API - The Postmates API allows any developer to integrate fast and scalable local, on-demand delivery into their products, websites and apps. It also gives developers access to a delivery fleet of 6,000 drivers and riders in 18 U.S. markets. We’re giving $5,000 to the PennApps team who builds the best application on top of the Postmates API. Your application can be built using whatever platform you like. We’re also giving $250 in free delivery credits to any team who builds something on the Postmates API. Potential uses in health include better and faster access to prescriptions, delivery of goods to hospitals and doctors, and services that are designed for people who can’t leave the house and could be managed by dependents on their behalf.

Healthdata.gov Data API - APIs for the data in datasets in the Healthdata.gov catalog. This Data API provides application developers with search and query capabilities for data in API-enabled datasets.

Healthdata.gov Catalog API- used to provide software developers programmatic access to the contents of our data catalog. The API can be used to find recently added datasets, to search the catalog, to download the contents of the catalog for analysis, or to build a new data catalog tool.

Data.gov Healthcare Finder API - All of the data used on the Finder.HealthCare.gov web application is available through this API. There are multiple collections of data available through the API. (Public, individual, and group healthcare coverage options)

Validic API - designed to enable a simple, standardized connection between healthcare companies and mobile health and wellness apps and devices. Validic captures a user’s fitness activities and health measurements over time. Each activity and measurement contains a timestamp and a note about which integration was used to track the activity. A core aspect of the Validic API is to vastly increase the speed of integration between mHealth app developers and healthcare business.

Human API - The easiest way to integrate health data from anywhere. Enable your users to securely share their health data with you, regardless of how that data was recorded, processed, or stored. Human API integrates data directly from every device, app or system you can think of. If not, tell us and we’ll add it.

openFDA API - OpenFDA is an Elasticsearch-based API that serves public FDA data about drugs, devices, and foods.

OpenSlide - a C library that provides a simple interface to read whole-slide images (also known as virtual slides).

Gamuts - an API to aid developers in using the Radiology Gamuts Ontology information.

Radreport.org - an API to aid developers in accessing structured radiology report templates.

Adapted from PennApps Health - Resources