|
Tool for augmenting patients' records with information from NLM resources |
Project Members:
Dina Demner-Fushman,
George Thoma
Collaborators:
NIH Clinical Center Nursing and Patient Care Services (NPCS):
Clare Hastings, Gwen Wallen, Cheryl Fisher
NIH Clinical Center Department of Clinical Research Informatics (DCRI)
Charlotte Seckman, Lincoln Farnum
The NLM InfoBot is a prototype system that enables a medical institution to automatically augment a patient's Electronic Medical Record (EMR) with pertinent patient-specific information from NLM's evidence-based resources and resources provided by the institution.
The prototype explores possibilities to automatically extract patients' problems and planned interventions from clinical notes and query evidence-based resources using the extracted terms. Our prototype implementation uses RIDeM services to extract clinical terms from free text, to find UMLS definition, to conduct MEDLINE® searches, and for article summarization.
Information provided to a medical institution is customized according to the institution's requirements. The requirements define the EMR fields that are provided to InfoBot and the knowledge sources to be mined for information provided by InfoBot. Each set of requirements for a specific clinical task and user group is called a Ruleset. Medical institutions can define as many rulesets as are needed to support their daily practice with evidence.

Figure 1 illustrates the InfoBot Evidence Dashboard for the ruleset defined by the NIH Clinical Center to support the Interdisciplinary Team care plan development.
Overview of Processes: text
Overview of Processes: table
Overview of Processes: slideshow
Process specifications: text and tables
Overview of Processes: diagram
The second version of the CRIS prototype was deployed for evaluation at the NIH Clinical Center in February 2011.
The first life EBP InfoBot prototype was deployed as the EBP-InfoBot tab in the NIH Clinical Center system CRIS in August 2009.
An offline protoype system was evaluated in 2008.
Using 4,335 de-identified interdisciplinary team notes for 525 patients, the system automatically
extracted biomedical terminology from 4,219 notes and linked resources to 260 patient records.
Sixty of those records (15 each for Pediatrics, Oncology & Hematology, Medical & Surgical,
and Behavioral Health units) have been evaluated by 16 Clinical Center nurses for quality of
automatically proactively delivered evidence and its usefulness in development of care plans.