Clinical Research Informatics Core

Overview of Services

The Institute for Biomedical Informatics (IBI) Clinical Research Informatics Core (CIC) provides data brokering and analytics services of clinical data for clinical and translational research in which the goal is to learn actionable healthcare knowledge and develop impactful solutions for improving patient care. We specialize in data de-identification, extraction, integration, standardization, and analytics of clinical data from the electronic health record (EHR) as well as research databases including PennG&P | TriNetX, Epic Cosmos, Epic Clarity, and the IQVIA Medical Record Database using artificial intelligence, natural language processing (NLP), ontologies, machine learning, and visual analytics. We also provide translation of research products into healthcare operations through coordination of projects with Penn Medicine Corporate Information Services, Penn Medicine BioBank, Penn Data and Analytics Center of Excellence, Penn RADAR, and the Center for Applied Health Informatics. The IBI CIC is a member of the Penn-sponsored Honest Broker program.

Consultation services:

— Generate aggregate counts as prep for research
— Assess project feasibility, study design, and computational approaches
— Advise data management, security, privacy, compliance
— Assist with writing grant proposals and NIH Data Management Plans
— Provide guidance for preparing institute review board (IRB) protocols
— Advise coordination across other cores and centers sponsored through Penn’s Honest Brokering program including the Penn Medicine BioBank, Abramson Cancer Center Electronic Phenotyping Resource

Technical services:

— Broker clinical data from PennChart EHR, PennG&P, Penn COVID-19 i2b2 database, and the IQVIA Medical Record Database
— Define study variables, clinical phenotypes, and patient health outcomes
— Extract, transform, and load data into REDCap; develop and deploy infrastructure, e.g, chart reviewers for clinical research
— De-identify, extract, encode, and classify information from structured and unstructured (clinical notes) electronic health record data 
— Standardize clinical data using biomedical and biological vocabularies, ontologies, and common data models
— Facilitate authorizations and data linkage with external data sources, e.g., national death index, claims data, geographical surveys, etc.
— Generate case/control datasets for clinical and translational research
— Develop and validate predictive models, machine/deep learning, and visual analytic solutions for health data (e.g., EHR, device, etc.)
— Translate research products into healthcare operations and assess their impact as part of the Penn Learning Health System
— Facilitate appropriate data sharing and execution of NIH Data Management Plans

Fee Structure:

Low Complexity Project (<2 hours): $250 flat project fee
Moderate Complexity Project (2-8 hours): $750 flat project fee
High Complexity Project (>8 hours): $750 flat project fee + $125/hr for each hour exceeding 8
Very high complexity or extended duration projects handled by custom quote or negotiated salary support as % effort

Research Resource Identifier (RRID)

Our RRID is: RRID:SCR_022409. Please cite us using this identifier when publishing your results. 

Leadership

Location and hours of operation

Links and Resources

1. Clinical Research Informatics Core
2. Institute for Biomedical Informatics

Contacts