Fuchiang (Rich) Tsui, PhD

Room 437L
5607 Baum Blvd.
Admin Support: 

Primary Appointment: 

Associate Professor, Department of Biomedical Informatics
Associate Professor of Intelligent Systems
Associate Professor of Bioengineering
Associate Professor of Clinical and Translational Science
Associate Director, RODS Laboratory
Biomedical Informatics Training Program Core Faculty, University of Pittsburgh School of Medicine
Peer-reviewed Publications: 
Dr. Tsui's research interest includes Clinical informatics, public health informatics, biosurveillance, machine learning, (big) data mining, artificial intelligence, natural language processing, mobile healthcare, precision medicine, data warehouse, time series analysis, signal processing, and large real-time production systems. He has been working in medical informatics for more than 18 years. Dr. Tsui has produced over 100 peer-reviewed publications and his publications have been actively cited (Google h-index: 39). Dr. Tsui has extensive knowledge and experience building large informatics production systems. At the University of Pittsburgh, he received his PhD in Electrical Engineering, premed training, and postdoctoral training in medical informatics. He has built several large real-time informatics production systems: (1) Clinical Event Monitor System (CLEM) that serves as a decision support system and reports notifiable diseases at University of Pittsburgh Medical Center (UPMC) in real-time, (2) Realtime Outbreak and Disease Surveillance System (RODS) that collects and monitors emergency department visits at UPMC, and (3) National Retail Data Monitor (NRDM) that collects and monitors over-the-counter medication sales from over 32,000 retail stores across the nation. Recently, he has been working with Children's Hospital of Pittsburgh of UPMC to build his 4th production system SHARP, a realtime decision support system that helps clinicians and patient care teams identify and manage patients at high-risk for 30-day readmission.
Research/Scholarship Interests: 
Public Health Informatics; clinical informatics; Machine Learning; biosurveillance; artificial intelligence; natural language processing; (big) data mining; mobile healthcare; precision medicine; data warehouse; time series analysis; signal processing; large real-time production systems; Commerce; Thermometers
(Legend: Current Major/ Current Minor, Non-current Major/ Non-current Minor)
Honors & Awards: 
Innovation Award, University of Pittsburgh
Distinguished Poster Award in 2014 American Medical Informatics Association annual conference, Washington, DC (among 400+ posters)
Interviewed by Pittsburgh Business Times about my latest research work on hospital readmission reduction that could have strong impact to patient care and cost reduction (http://www.bizjournals.com/pittsburgh/print-edition/2013/11/22/analytic-tool-helps-docs-make-better.html)
Scientific achievement Award for Outstanding Research Articles in Biosurveillance, 2012 Annual International Society for Disease Surveillance: Expanding Collaborations to Chart a New Course in Public Health Surveillance (December 4-5, 2012, San Diego, California), International Society for Disease Surveillance
Invited meeting with the President of Taiwan (President Ma) at the Presidential Building; selected elites in public health surveillance field
Nomination for best paper, 2002 Annual Symposium for Computer Applications in Medical Care: Biomedical Informatics: One Discipline (November 9 - 13, San Antonio, TX), AMIA
Nomination for best paper, 1998 Annual Symp. for Computer Applications in Medical Care: A Paradigm Shift in Health Information Systems: Clinical Infrastructures for the 21st Century (Nov. 7-11), AMIA
Nomination for best paper, 1997Annual Symposium for Computer Applications in Medical Care: The Emergence of 'Internetable' Health Care. Systems That Really Work (October 25-29, Nashville, TN), AMIA
Grants & Contracts: 
09/2016 - 02/2018
Children's Hospital of Pittsburgh of UPMC Under agreement
C-WIN: Cardiac Intensive Care Unit Warning System
Role: PI (sole)
08/2016 - 07/2018
Richard King Mellon Foundation
Infant mortality prediction and intervention in Allegheny County
Role: PI (sole)
05/2015 - 04/2018
Local Foundation
System for Hospital Adaptive Readmission Prevention and Reduction (SHARP)
Role: PI (sole)
01/2015 - 01/2018
Coulter Foundation
Readmission technology development for Industrial applications
Role: PI (sole)
09/2014 - 08/2015
Pennsylvania Innovation Works
Post discharge monitoring through mobile application
Role: PI (sole)
07/2014 - 06/2016
NIH 5UL1 TR000005
University of Pittsburgh Clinical and Translational Science Institute
Role: Co-Investigator
02/2014 - 01/2015
First Gear, University of Pittsburgh N/A
Hospital Readmission Prediction
Role: PI (sole)
01/2014 - 06/2016
PaTH towards a Learning Health System for the Mid-Atlantic Region
Role: Co-Investigator
07/2013 - 06/2016
NIH/NLM 1 R01 LM011370
Probabilistic Disease Surveillance
Role: Co-Investigator
09/2008 - 09/2010
Centers for Disease Control and Prevention U38HK000063
PA-OH BIG: Building a Regional Biosurveillance Grid for Pennsylvania and Ohio
Role: Principal Investigator (sole)
05/2008 - 08/2009
Houston Department of Health and Human Services 460000897 (08-0672)
The Houston RODS System Expansion of Functionality
Role: Principal Investigator (sole)
01/2008 - 06/2011
Pennsylvania Department of Health SAP #40000012020
Pennsylvania (PA) Biosurveillance
Role: Co-Investigator
Teaching Activities: 
08/31/2015 - 12/19/2015 BIOINF - 2011 - 14178 FDS CLIN & PH INFORMATICS
08/31/2015 - 12/19/2015 BIOINF - 2120 - 19867 SYMBLC MTHS IN ARTFCL INTELGNC





Clinical care is complex and often fast paced. Preventable medical errors can and do occur, as has been well documented in recent years. Clinical guidelines and rule-based alerts provide clinical decision support that is intended to reduce medical errors. These methods are driven by expert knowledge. As such, they tend to focus on high impact areas in which medical errors are either prevalent, serious, or both. However, the coverage of such methods is relatively narrow.

We are investigating data-driven methods for helping avoid medical errors. Machine-learning methods are applied to electronic health record (EHR) data to derive computer-based probabilistic models of usual care. These models, which can be complex and time-oriented, represent the probability of various types of care being given for different types of medical conditions. The care of a current patient, as revealed by his or her EHR, is automatically compared to the model of usual care that has been constructed from past-patient cases. If some aspect of the care of the current patient has a low probability, then an alert is sent to the patient’s clinician that indicates the care is unusual.

Milos Hauskrecht, Ph.D., Gregory F. Cooper, M.D., Ph.D., Gilles Clermont, M.D., M.P.H., and Shyam Visweswaran, M.D., Ph.D. are faculty on a project that is investigating these methods in the area of critical care medicine. The project is currently developing and evaluating models and alerts in a laboratory setting. Once this approach is validated in the laboratory, the next stage will be to evaluate it in a limited clinical setting.

Sample of Related Publications:

Batal I, Sacchi L, Bellazzi R, Hauskrecht M. Multivariate time series classification with temporal abstractions. In: Proceedings of the International Florida AI Research Society Conference (FLAIRS) (2009).

Hauskrecht M, Valko M, Batal I, Clermont G, Visweswaran S, Cooper GF. Conditional outlier detection for clinical alerting. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov 2010).

Visweswaran S, Mezger J, Clermont G, Hauskrecht M, Cooper GF. Identifying deviations from usual medical care using a statistical approach. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov, 2010).

Batal I, Hauskrecht M. Mining clinical data using minimal predictive rules. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov, 2010).

Valko M, Hauskrecht M. Feature importance analysis for patient management decisions. In: Proceedings of the International Congress on Medical Informatics (MEDINFO), Cape Town, South Africa (2010)

Ruiz VM, Ye Y, Draper AJ, Tsui F.-C., The use of multiple emergency department reports per visit for improving the accuracy of influenza case detection, Conference Proceedings, American Medical Informatics Association, Washington DC, Nov. 2014

Funded by the CDC, which allows five participating members—Pennsylvania Department of Health, Ohio Department of Health, Center for Disease Control and Prevention (CDC), Allegheny County Health Department, and the University of Pittsburgh—to share data and detection algorithms.

Funded by the CDC, as a part of CDC Center of Excellence P01 grant.

Funded by PADOH as a sub-award, for public health researchers.

Allegheny County Health Department.

James Levin, MD, Chief Medical Information Officer (CMIO)

Ronald Voorhees, MD, Chief of Epidemiology and Biostatistics

Brian Fowler, MPH, Chief, Situational Monitoring and Event Detection Unit,

Center for Public Health Statistics and Informatics

Kirsten Waller, MD, MPH,

Bill Stephens, Manager, Southwest Center for Advanced Public Health Practice

Jamyia Clark, Epidemiologist

Carol Friedman, Ph.D., Professor