Testing Pediatric Rheumatology Diagnostic Decision Support in Clinical Use

This research aims to ease the critical shortage of pediatric rheumatologists by using decision support software to improve the ability of generalist physicians to make rheumatologic diagnosesIn our SBIREmpowering Physicians with Evidence Based Decision Support for Pediatric Rheumatologyrheumatology information was added to the SimulConsult diagnostic decision support toolTesting using pediatric rheumatology case vignettes showed that all groups of clinicians were more effective in diagnosis after using the toolDiagnostic error was reducedwith error defined as the absence of the correct diagnosis or its category in the differential diagnosisError fell fromtorelative reductionwith largest reductions among junior physiciansrelative reductionand Emergency Medicine physiciansrelative reductionThis SBIRproposal extends the SBIRresearch to actual clinical practiceafter improving the diagnostic tool in ways suggested by the SBIRWe hypothesize improvements in actual practice similar to those using case vignettesWide use of such capabilities would ease the critical shortage of pediatric rheumatologistsand reduce instances of bad outcomes from delay or mistreatmentAimis to improve the decision support in ways suggested by a case based quality improvement methodology developed using thecases tested in the SBIRThat methodology will be formalized to guide further improvementusingadditional casesImprovements already surfaced using this methodology will be implementedincluding a new dimension to specifying timespeed of emergence of a diseaseOther improvements will be resources to assist non specialists in identification of key findingsbundlesof several results of one test that can be combined to better represent the usefulness of obtaining that testaddition of further findings often not mentioned in narrative resources such as responses to particular treatmentsadding exclusionary findingsand adding further diseases in the differential diagnosis of rheumatologic conditionsAimis a trial of effectiveness in clinical careThis will be done in the emergency department of Boston Children s Hospitalwithpatients overmonthsand in rheumatology clinic at the hospitalwithpatientsfor a total ofcasesCases will be randomized to a Control conditionin which the tester may use all usual resources such as textbooks or web searchesor an Intervention conditionin which the diagnostic tool is used and the same usual resources may be usedas wellTrainees will record their differential diagnosis and planned workup before and after the trialThese lists will be compared to thegold standarddiagnosis and workupbased on assessments of senior rheumatologistslab testing and follow up in subsequent monthsErrorrelevancecomprehensivenessand cost impactwill be analyzedDemonstrating that non rheumatologists and trainees improve their diagnoses in pediatric rheumatology and save costs will enable the diagnostic decision support to be commercialized to hospitals and pediatricians