A clinical decision support system prototype for cardiovascular intensive care.

F Lau
Author Information
  1. F Lau: Department of Accounting and Management Information Systems, Faculty of Business, University of Alberta, Canada.

Abstract

This paper describes the development and validation of a decision-support system prototype that can help manage hypovolemic hypotension in the Cardiovascular Intensive Care Unit (CVICU). The prototype uses physiologic pattern-matching, therapeutic protocols, computational drug-dosage response modeling and expert reasoning heuristics in its selection of intervention strategies and choices. As part of model testing, the prototype simulated real-time operation by processing historical physiologic and intervention data on a patient sequentially, generating alerts on questionable data, critiques of interventions instituted and recommendations on preferred interventions. Bench-testing with 399 interventions from 13 historical cases showed therapies for bleeding and fluid replacement proposed by the prototype were significantly more consistent (p < 0.0001) than those instituted by the staff when compared against expert critiques (80% versus 44%). This study has demonstrated the feasibility of formalizing hemodynamic management of CVICU patients in a manner that may be implemented and evaluated in a clinical setting.

MeSH Term

Alberta
Blood Volume
Clinical Protocols
Coronary Care Units
Cost Control
Decision Support Techniques
Decision Trees
Dose-Response Relationship, Drug
Evaluation Studies as Topic
Expert Systems
Fluid Therapy
Hemodynamics
Humans
Hypotension
Length of Stay
Monitoring, Physiologic
Therapy, Computer-Assisted

Word Cloud

Created with Highcharts 10.0.0prototypeinterventionssystemCVICUphysiologicexpertinterventionhistoricaldatacritiquesinstitutedclinicalpaperdescribesdevelopmentvalidationdecision-supportcanhelpmanagehypovolemichypotensionCardiovascularIntensiveCareUnitusespattern-matchingtherapeuticprotocolscomputationaldrug-dosageresponsemodelingreasoningheuristicsselectionstrategieschoicespartmodeltestingsimulatedreal-timeoperationprocessingpatientsequentiallygeneratingalertsquestionablerecommendationspreferredBench-testing39913casesshowedtherapiesbleedingfluidreplacementproposedsignificantlyconsistentp<00001staffcompared80%versus44%studydemonstratedfeasibilityformalizinghemodynamicmanagementpatientsmannermayimplementedevaluatedsettingdecisionsupportcardiovascularintensivecare

Similar Articles

Cited By