informatics institute logo Infromatics Institute UMDNJ logo


 


 

-----

Projects

-----

HGML

We have been developing the Hypertext Guideline Markup Language (HGML), the key component of a guideline delivery and evaluation system. HGML is an XML/XHTML specification for the identification of condition and recommendation elements within text guidelines. This markup process results in "machine operable" versions of text-based clinical practice guidelines, to automatically generate relevant recommendations given a particular case, and it allows clinicians to access the guideline using multiple views.

To ease the process of marking up guidelines we created a guideline markup editor that uses a point-and-click interface similar to the interface commonly used by word processors and HTML editors. We have also developed a Guideline Evaluation Engine that allows us to collect information about a patient (either from an Electronic Medical Record system, or directly from a clinician through a web-based interface), and return relevant recommendations to a web browser. The output from the system is linked to the related text in the original guideline, and to supporting evidence including references, related text, and survival curves from models evaluated by Decision Maker, a companion project developed and maintained by members of this Group.

Our most recent work includes

  • Continued development of a markup editor to facilitate the streamlined encoding of guidelines. Our latest editor is based on the Mozilla/Firefox Annozilla Extension!
  • Refinement of the HGML elements for increased flexibility and scope, making it easier it identify critical guideline components and their relationships
  • Implementation of a guideline server, integrated with a prototype point-of-care delivery system, in which guideline recommendations relevant to a specific patient can be delivered (integrated with our current medical record system, Logician).
  • Exploration of Semi-Automatic means for encoding clinical guidelines, using UMLS/MetaMap to identify clinical terms in the guidelines and infer possible encodings to assist in the markup process.

For more information, please see...

  • HGML2.2 Elements Specification Overview
  • Hagerty CG, Pickens D, Kulikowski CA, and Sonnenberg FA. HGML: A Hypertext Guideline Markup Language. Proceedings Annual Meeting of the AMIA 2000 Fall Symposium, American Medical Informatics Association, 2000:325-9. [Download PDF]
  • A slide presentation [Download Powerpoint File]
  • Hagerty CG, Chang J, Pickens DS, Kulikowski CA, and Sonnenberg FA. Semi-Automated Encoding of Guidelines. Medinfo. 2004;2004(CD):1625.
  • The Medinfo 2004 Poster [Download PDF]
-----

SimPal /
Decision
Maker

Decision Maker is an application for building and evaluating decision analytic models, or "decision [analytic] trees". Originally developed for DOS, a perpetual beta-test version of the application WinDM is now available for the Windows platform. We have also been developing a cross-platform evaluator, SimPal, currently for Monte Carlo evaluation of Markov models.

Web-based Model Presentation

We have also been developing an architecture that allows the presentation and custom evaluation of [strict and semi-] Markov models through a web-based interface. The interface allows parameters to be specified for the models, in "decision tree" format, which may then be evaluated to result in graphically displayed results. Prototype applications include the Stroke Prevention Policy Model and the Interactive Contraceptive Choice Model (restricted access).

UMaker

UMaker is a utility assessment tool that allows health states to be compared from the perspectives of Categorical-Scales, Time-Tradeoff and Reference-Lottery. It is also available as perpetual beta-test software. We've also been developing an exciting new browser-based version, that makes use of the Scalable Vector Graphics features built into the latest versions of the Mozilla/Firefox web browser. (Ask if interested)
-----

People

-----
 
Frank Sonnenberg   (sonnenbe@umdnj.edu)
Medical Director of Clinical Information Systems
Professor of Medicine
UMDNJ Robert Wood Johnson Medical School
C. Greg Hagerty (cgreg@cgreg.com)
Assistant Professor of Medicine
...among other things
UMDNJ Robert Wood Johnson Medical School
 
Casimir Kulikowski   (kulikows@cs.rutgers.edu)
Board of Governors Professor of Computer Science
Department of Computer Science
Rutgers University
David Pickens (dsp@rci.rutgers.edu)
Assistant Dean, Graduate School-New Brunswick
Rutgers University
 
John Chuo MD, MS (chuojo@umdnj.edu) Assistant Professor of Pediatrics
Department of Pediatrics
Division of Neonatology
University of Medicine and Dentistry of New Jersey
Bristol-Myers Squibb Children's Hospital at Robert Wood Johnson University Hospital
Kennedy Ganti, MD (gantike@umdnj.edu)
Resident
Department of Family Medicine
UMDNJ-RWJMS

Alumni:

Janaki Acharya (janaki_acharya@hotmail.com)
UMDNJ Alumni, Volunteer

Jaime Chang (changj02@yahoo.com)
Harvard-MIT Division of Health Sciences and Technology
Massachusetts Institute of Technology
 
Smita Namboodiri (smitapsn@yahoo.com)
Gainfully Employed!
 
-----