Research Interests & Projects:

"To condense fact from the vapor of nuance."  - Neal Stephenson, Snow Crash

I am a clinician-researcher interested in leveraging Healthcare IT to support Patient Safety.  I am engaged in developing next-generation provider documentation tools in electronic medical records. My main project, DETER-MINE (DETecting ERrors MIning Narrative Electronically), involves the development of informatics tools (using natural language processing) to detect adverse events and deviations in care from established clinical guidelines through automated processing of electronic provider notes.  On the operational side, as Associate Director of Quality Informatics at NewYork-Presbyterian Hospital, I am leading several healthcare information technology projects, including the implementation of automated clinical alerts and structured, electronic provider documentation. 

1. Clinical Documentation:

   eNote:

   1. Goal:

   2. Status:

   3. Collaborators:

   4. Screenshots:

   5. Publications & Links:

   DSUM Writer:

   1. Goal:

   2. Status:

   3. Collaborators:

   4. Screenshots:

   5. Publications & Links:

      AMIA Poster Session 2005 - Electronic Discharge Summaries

   Structured Documentation:

   1. Goal:

   2. Status:

   3. Collaborators:

   4. Screenshots:

   5. Publications & Links:

    

2. Patient Safety:

   DETER-MINE:

1. Abstract:  

   The long-term goal of this proposal is to use the electronic medical record, including narrative text, to understand and encode the process of care for individual patients in order to improve patient safety.  Achieving this goal has the potential to help detect adverse events, and to differentiate medical errors from appropriately tailored care.  The specific aims for this proposal are as follows: 

   1. To understand and encode the process of care for individual patients using data in the electronic medical record, including narrative text.

   2. To use a more detailed understanding of patients’ processes of care to improve automated adverse event detection. 

   3. To match processes of care for individual patients against accepted care pathways in order to identify discrepancies.

   We will capitalize on three core technologies that are in active use by clinicians and researchers in our busy clinical setting:  1) a Web-based clinical information system and its associated clinical data repository (WebCIS), 2) a full medical language parser (MedLEE), and 3) a semi-structured, electronic physician documentation system built by our team specifically to support this project (eNote).    

   Methods will include evaluating the performance (sensitivity, specificity and positive predictive value) of our system, DETER+MINE (DETecting ERrors MIning Narrative Electronically), to model the care process and detect adverse events and pathway deviations.  We will utilize explicit process criteria and manual, retrospective chart review as a gold standard.    

   This research is intended to provide proof of concept that combining natural language processing of clinical narrative with traditional sources of coded data is required for effective screening with automated detection systems.  This approach has the potential to impact significantly on our ability to detect and investigate medical errors, adverse medical events, and pathway deviations by reducing reliance on costly and slow manual chart reviews.

      

2. Status:

   Ongoing Support:
   1 K22-LM8805-01       October 2005 – September 2008
   National Library of Medicine
   

3. Collaborators:

   • Carol Friedman, PhD

   • George Hripcsak, MD, MS

   • Stephen Johnson, PhD

   • Steven Shea, MD, MS

    

4. Publications & Links:

Clinical Alerts:

1. Goal:

2. Status:

3. Collaborators:

4. Publications & Links:

Center for Quality and Safety Informatics:

1. CPOE:

2. Alerts:

3. Elective Opportunities:

home