System Interoperability & Machine Learning: Multi-site Evidence-based Best Practice Discovery.

Eva K Lee
When: January 20, 2016 @ 12:00am - 12:00am
Location: TBD
Audiences: Everyone Is Invited

ABSTRACT

This study establishes interoperability among electronic medical records from 737 healthcare sites and performs machine learning for best practice discovery. A mapping algorithm is designed to disambiguate free text entries and to provide a unique and unified way to link content to structured medical concepts despite the extreme variations that can occur during clinical diagnosis documentation. Redundancy is reduced through concept mapping. A SNOMED-CT graph database is created to allow for rapid data access and queries. These integrated data can be accessed through a secured web-based portal. A classification model ((DAMIP) is then designed to uncover discriminatory characteristics that can predict the quality of treatment outcome. We demonstrate system usability by analyzing Type II diabetic patients. DAMIP establishes a classification rule on a training set which results in greater than 80% blind predictive accuracy on an independent set of patients. By including features obtained from structured concept mapping, the predictive accuracy is improved to over 88%. The results facilitate evidence-based treatment and optimization of site performance through best practice dissemination and knowledge transfer. This project receives the 2016 NSF Health Organization Transformation award.

BIO

Dr. Lee is a Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology, and Director of the Center for Operations Research in Medicine and HealthCare, a center established through funds from the National Science Foundation and the Whitaker Foundation. The center focuses on biomedicine, public health, and defense, advancing domains from basic science to translational medical research; intelligent, quality, and cost-effective delivery; and medical preparedness and protection of critical infrastructures. She is a Distinguished Scholar in Health Systems, Health System Institute at Georgia Tech and Emory University. She is also the Co-Director of the Center for Health Organization Transformation, an NSF Industry/University Cooperative Research Center. Lee partners with hospital leaders to develop novel transformational strategies in delivery, quality, safety, operations efficiency, information management, change management and organizational learning. Lee’s research focuses on mathematical programming, information technology, and computational algorithms for risk assessment, decision making, predictive analytics and knowledge discovery, and systems optimization. She has made major contributions in advances to medical care and procedures, emergency response and medical preparedness, healthcare operations, and business operations transformation. Dr. Lee serves on the National Preparedness and Response Science Board. She is the principle investigator of an online interoperable information exchange and decision support system for mass dispensing, emergency response, and casualty mitigation. The system integrates disease spread modeling with response processes and human behavior; and offers efficiency and quality assurance in operations and logistics performance. It currently has over 9500+ public health site users. Lee has also performed field work within the U.S. on mass dispensing design and evaluation, and has worked with local emergency responders and affected populations after Hurricane Katrina, the Haiti earthquake, the Fukushima Japan radiological disaster, and Hurricane Sandy. Lee has received multiple analytics and practice excellence awards including INFORMS Franz Edelman award, Daniel H Wagner prize for novel cancer therapeutics, bioterrorism emergency response dispensing for mass casualty mitigation, optimizing and transforming clinical workflow and patient care, vaccine immunity prediction, and reducing hospital acquired conditions. Dr. Lee is an INFORMS Fellow. She has received seven patents on innovative medical systems and devices.

CONTACT US
Share this
Become a CAIS partner through community projects, funding, volunteering, or research collaboration.