Overview
John Pestian, PhD, is an associate professor of pediatrics and biomedical informatics at Cincinnati Children's Hospital Medical Center and the University of Cincinnati. He is the director of the Computational Medicine Center, a collaborative medical research initiative between Cincinnati Children's and the University of Cincinnati Medical Center that uses data and computational systems to make disease more preventable, illness more predictive and treatment more personalized. He also holds an adjunct appointment as an associate professor of biomedical informatics at The Ohio State University.
Dr. Pestian's research lab focuses on using natural language processing (NLP) to analyze clinical free-text, with the goal of enhancing clinical processes and outcomes.
Free-text usually refers to data from some type of language. This free-text can be discharge summaries, radiology reports or text books. While free-text is data, it is different from structured data, which have forced choices -- for example, zip codes, states, specific diagnostics or therapeutics. The lab's research primarily focuses on how to process free-text using specific algorithms. This effort is often referred to as natural language processing.
There are many methods for natural language processing. Rule-based inference and neurocognitive computing are two methods that have captured the lab's attention for now. Lab members and collaborators are applying these methods to anonymize clinical free-text, cluster text into categories, develop corpora, develop visual languages and, most recently, develop artifical experts (the lab's work here is in a very early stage).
Open Position
We are accepting applications for a visiting research scientist/post-doctoral fellow. Research efforts will focus on the development, application and evaluation of novel linguisitc methods in both the clinical and administrative settings. For more information, download the position description.
Resources
Following are some resources developed by the lab. Note that open-source resources can be downloaded from the Computational Medicine Center's catalog.
- Encryption Broker - a tool that anonymizes and disambiguates clinical text without corrupting its meaning
- Pediatric Corpus - a collection of 600,000 words of HIPAA-anonymized clinical data approved for release by the Institutional Review Board of Cincinnati Children's Hospital Medical Center
- Christine for Personalized Medicine Drug Selection
- Christine's Expert Opinion System - for gathering expert opinion about personalized medicine drug selection
- Graphs of Consistent Concepts - a spreading activation graph system
- Radiology Negation System - NLP system for getting consensus on radiology negation data
Contact Us
For more information about NLP research at Cincinnati Children's, contact John Pestian, PhD.
