BlackfordMiddleton,MD,MPH,MSc,FACP,FACMI,FHIMSSChairman,CenterforInformationTechnologyLeadership
CorporateDirector,ClinicalInformaticsResearch&DevelopmentPartnersHealthcareSystemHarvardMedicalSchool
HarvardSchoolofPublicHealth
WhatisClinicalDecisionSupport? TheEvidenceForandAgainstCDS CurrentexamplesandR&DProjectsfromPartners TheClinicalDecisionSupportConsortium
“Whatinformationconsumesisratherobvious:itconsumestheattentionofitsrecipients. Henceawealthofinformationcreatesapovertyofattention,andaneedtoallocatethatattentionefficientlyamongtheoverabundanceofinformationsourcesthatmightconsumeit.”
Changingclinicianroles: FromOmniscientOracle…toKnowledgeBroker.
compiled
analyzed
acted upon
After B Blum, 1984
Medicalliteraturedoublingevery19years Doublesevery22monthsforAIDScare
2Millionfactsneededtopractice CovellstudyofLAInternists:
2unansweredclinicalquestionsforevery3pts• 40%weredescribedasquestionsoffact,• 44%werequestionsofmedicalopinion,• 16%werequestionsofnon‐medicalinformation.
Covell DG, Uman GC, Manning PR. Ann Intern Med. 1985 Oct;103(4):596-9
Generally,withdirectobservation,orinterviewimmediatelyafterclinicalencounters,physicianshaveapproximatelyonequestionforevery1‐2patients Independentestimates:0.6,and0.62Q/pt HoldsacrossPCPandspecialtycare Holdsacrossurbanandrural
Gorman, 1995 Gorman and Helfand 1995
An objective measure of the amount of literature generated by medical scientists annually
Publication
Bibliographicdatabases
Submission
Reviews,guidelines,textbook
Negativeresults
variable
0.3year
6.013.0years50%
46%
18%
35%
0.6year
0.5year
9.3years
Dickersin,1987
Koren,1989
Balas,1995
Poynard,1985
Kumar,1992
Kumar,1992
Poyer,1982
Antman,1992
Negativeresults
Lackofnumbers
Inconsistentindexing
17:14
Originalresearch
Acceptance
PatientCare
17 years to apply 14% of research knowledge
to patient care!
BalasYearbookMedicalInformatics2000gtre4,courtesyMOverhage
AbrahamFlexner,MedicalEducationintheUnitedStatesandCanada.
Boston:MerrymountPress,1910
"...The curse of medical education is the excessive number of schools. The situation can improve only as weaker and superfluous schools are extinguished." “Society reaps at this moment but a small fraction of the advantage which current knowledge has the power to confer.”
“Insteadofteachingdoctorstobeintelligentmapreaders,wehavetriedtoteacheveryonetobeacartographer.”
“Wepracticehealthcareasifweneverwroteanythingdown.Itisaspectacleoffragmentedintention.”
LarryWeed,M.D. (fatherof“S.O.A.P.”note)
Pronetoerror Lotsofinformationbutnodata Limiteddecisionsupport,orqualitymeasurement DoesnotintegratewitheHealthcare Willnottransformhealthcare
Medicalerror,patientsafety,andqualityissues 98,000deathsrelatedtomedicalerror 40%ofoutpatientprescriptionsunnecessary Patientsreceiveonly54.9%ofrecommendedcare
Fracturedhealthcaredeliverysystem Medicarebeneficiariessee1.3–13.8uniqueprovidersannually,onaverage6.4differentproviders/yr
Patient’smultiplerecordsdonotinteroperate An‘unwired’system
90%ofthe30BhealthcaretransactionsintheUSeveryyearareconductedviamail,fax,orphone
http://tr.im/sVLA
“…driven primarily by local norms that tend towards heavier use of discretionary services – such as diagnostic testing and surgical versus less invasive interventions – for which there are no clear clinical guidelines.” Peter Orszag, OMB Blog http://www.whitehouse.gov/omb/blog/
El Paso
McAllen
TEXAS
790 mi., 1271 km
“Aknowledge‐basedsystemisanAIprogramwhoseperformancedependsmoreontheexplicitpresenceofalargebodyofknowledgethanonthepresenceofingeniouscomputationalprocedures…”
Duda RO, Shortliffe EH. Expert systems research. Science. 1983 Apr 15;220(4594):261-8.
Algorithmic Statistical PatternMatching Rule‐based(Heuristic) Meta‐heuristic Fuzzysets Neuralnets Bayesian
Knowledge Base
Inference Engine
A B
BloisMS.Clinicaljudgmentandcomputers.
NEnglJMed.1980Jul24;303(4):192‐7.
Formatting Resultsreview,“pocketrounds”reports
Interpreting EKG,PFTs,Pap,ABG
Consulting QMR,DxPlain,Iliad,Meditel,AbdPain,MIrisk
Monitoring Alerts:Criticallabs,ABx/Surgery,ADEs
Critiquing Ventmgmt,anesthesiamgmt,HTNRx,Radiologytestselection,Bloodproductsordering
Kuperman GJ et al. J Hlth Info Mgmt (13)2, pg 81-96
CDSyieldsincreasedadherencetoguideline‐basedcare,enhancedsurveillanceandmonitoring,anddecreasedmedicationerrors (Chaudhryetal.,2006)
CDS,atthetimeoforderentryinacomputerizedproviderorderentrysystemcanhelpeliminateoveruse,underuse,andmisuse. (Batesetal.,2003;Austinetal.,1994;Linder,BatesandLee,2005;Tierneyetal.,2003)
Forexpensiveradiologictestsandproceduresthisguidanceatthepointoforderingcanguidephysicianstowardorderingthemostappropriateandcosteffective,radiologictests. (Batesetal.,2003;Khorasanietal.,2003)
Showingthecumulativechargedisplayforalltestsordered,remindingaboutredundanttestsordered,providingcounter‐detailingduringorderentry,andremindingaboutconsequentorcorollaryordersmayalsoimpactresourceutilization (BatesandGawande,2003;Bates,2004;McDonaldetal.,2004).
Savingspotential:$44billion reducedmedication,radiology,laboratory,andADE‐relatedexpenses
AdvancedCDSsystems SavingspotentialonlywithadvancedCDS costfivetimesasmuchasbasicCDS generate12timesgreaterfinancialreturn
Apotentialreductionofmorethan2millionadversedrugevents(ADEs)annually
Johnston et al., 2003 http://www.citl.org
HanYY(Pediatrics116:6,Dec2005) Analyzeddata13prior,and5monthspost,implementationofCPOEincriticalcare
PreCPOEmortalityrate2.8%,Post6.57% 3.28Oddsratioaftermultivariateanalysisadjustingforcovariates
Conclusion Orderdelayduetolackofpre‐register Upfronttimecosttoenterorders Nursesawayfrombedside,atcomputer AlteredinteractionsbetweenICUteammembers Delayedpharmacyadministration Problemswithordertiming(subsequentdoses)
InformationErrors Assumeddose Medd/cfailure Procedure‐linkedmederror Givenow,andprnd/cerror Antibioticrenewal Diluentoptionerror Allergydisplay Conflictorduplicatemed
HCI/WorkflowErrors Patientselection Medselection Unclearlogon/off Medsaftersurgery Postsurgerysuspendedmeds Time/datalosswhenCPOEdown
Meddeliveryerror Timingerrors Delayednursingdocumentation
Rigidsystemdesign
Koppel R et al. JAMA 293:10, Mar 2005
During the Clinical Encounter
History and Physical End of Visit
After the Encounter
Results Arrive
Proactive Reminders Warnings/
Feedback Templates/Order Sets
Alerts Guidelines
Relevant Info Display
Consequent Actions
Communication Time-Based Checks
Adapted from Osherorff JA, Pifer EA, Sittig DF, Jenders RA, and Teich JM. Clinical Decision Support Implementers' Workbook. 2004.
Before the Encounter Patient Prepares
for the Visit
Scheduling Record Review & Update
Patient Reminders
Health Information
Bates et. al. JAMA 1998.
Secure Messaging
Task Management Population Management
Clinical Alerts
Schedule
Patient Lists
Knowledge Links
Information Access Knowledge Linking
KnowledgeLink in the Workflow
Patient Disease Management
SmartView:DataDisplay
SmartAssessment,Orders,andPlan
Assessmentandrecommendationsgeneratedfromrulesengine
SmartDocumentation
• Lipids• Anti‐platelettherapy• Bloodpressure• Glucosecontrol• Microalbuminuria• Immunizations• Smoking• Weight• Eyeandfootexaminations
MedicationOrders
LabOrders
Referrals
Handouts/Education
0% 10% 20% 30% 40% 50% 60% 70% 80%
UptodateBPresult
ChangeinBPtherapyifabovegoal
Uptodateheightandweight
ChangeintherapyifA1Cabovegoal
Uptodatefootexamdocumented
Uptodateeyeexamdocumented
#ofdeficienciesaddressed
SmartFormUsed Control
<0.001
<0.001
<0.001
<0.001
<0.001
0.05
0.004
0.006
Targetsare90thpercentileforHEDISorforPartnersproviders
Zerodefectcare:• Aspirin• Beta‐blockers• Bloodpressure• Lipids
Red,yellow,andgreenindicatorsshowadherencewithtargets
Discrepancy
Details
Grant RW et al. Practice-linked Online Personal Health Records for Type 2 Diabetes: A Randomized Controlled Trial. Arch Intern Med. 2008 Sep 8;168(16):1776-82. .
More medication changes in visits after diabetes journal submission:
NewappreciationforpotentialunintendedconsequencesofCDS
Knowledge“hardwired”intoapplications Knowledge‐engineeringtoolsassumeauthorsknowwhattoputintothem
Proprietaryknowledgerepresentationstandards:notre‐usable,noteasilyshared
Lackofhealthcareleadershiporresourceinvestmentinprocessesforknowledgeacquisitionandmanagement
ARoadmapforNationalActiononClinicalDecisionSupport
“toensurethatoptimal,usableandeffectiveclinicaldecisionsupportiswidelyavailabletoproviders,
patients,andindividualswhereandwhentheyneedittomakehealthcaredecisions.” !
Osheroff JA, Teich JM, Middleton B, Steen EB, Wright A, Detmer DE. J. Am. Med. Inform. Assoc. 2007;14(2):141-145.
Toassess,define,demonstrate,andevaluatebestpracticesforknowledgemanagementandclinicaldecisionsupportinhealthcareinformationtechnologyatscale–acrossmultipleambulatorycaresettingsandEHRtechnologyplatforms.
www.partners.org/cird/cdsc
HowdoweimprovethetranslationofknowledgeinclinicalpracticeguidelinesintoactionableCDSinhealthcareinformationtechnology?
HowdoweoptimallyrepresentknowledgeanddatarequiredtomakeactionableCDScontentinbothhumanandmachinereadableform?
Howdowecollate,aggregate,andcurateknowledgecontentforCDSinaknowledgeportalusedbymembersoftheCDSConsortium?Howmayweusesuchatooltosupportknowledgemanagementandcollaborativeknowledgeengineeringforclinicaldecisionsupportatscale,acrossmultiplehealthcaredeliveryorganizations,andmultipledomainsofmedicine?
Howdowedemonstratebroadadoptionofevidence‐basedCDSatscaleinawidearrayofHITproductsusedindisparateambulatorycaredeliverysettings?
Further,howdowedeployclinicaldecisionsupportservicesinhealthcareinformationtechnologyinamannerthatimprovesCDSimpact?
Howdowetakethelearningsgarneredthroughthecourseoftheseinvestigationsandbroadlydisseminatethembroadlytokeystakeholders?
1980 1990 2000
ONCOCIN EON(T-Helper) GLIF2
Arden
MBTA
GEODE-CM
EON2
GLIF3
Asbru
Oxford System of Medicine DILEMMA PROforma
PRESTIGE
PRODIGY
Decision Tables GEM
PRODIGY3
P. L. Elkin, M. Peleg, R. Lacson, E. Bernstam, S. Tu, A. Boxwala, R. Greenes, & E. H. Shortliffe. Toward Standardization of Electronic Guidelines. MD Computing 17(6):39-44, 2000
Shahar Y, et al. JBI 2004
1. Knowledge Management Life Cycle
2. Knowledge Specification
3. Knowledge Portal and Repository
4. CDS Public Services and Dashboard
5. Evaluation Process for each CDS Assessment and Research Area
6. Dissemination Process for each Assessment and Research Area
Knowledgemanagementlifecycle Knowledgespecification KnowledgePortalandRepository CDSKnowledgeContentandPublicWebServices Evaluation Dissemination
NarrativeRecommendationlayer
Narrativetextoftherecommendationfromthepublishedguideline.Semi‐StructuredRecommendationlayer
Breaksdownthetextintovariousslotssuchasthoseforapplicableclinicalscenario,therecommendedintervention,andevidencebasisfortherecommendation
Standardvocabularycodesfordataandmoreprecisecriteria(pseudocode)
AbstractRepresentationlayer
StructurestherecommendationforuseinparticularkindsofCDStools
• Reminderandalertrules
• Ordersets
Arecommendationcouldhaveseveraldifferentartifactscreatedinthislayer,oneforeachkindofCDStool
MachineExecutablelayer
KnowledgeencodedinaformatthatcanberapidlyintegratedintoaCDStoolonaspecificHITplatform
E.g.,rulecouldbeencodedinArdenSyntax
Arecommendationcouldhaveseveraldifferentartifactscreatedinthislayer,oneforeachofthedifferentHITplatforms
NarrativeGuideline
SemistructuredRecommendationAbstractRepresentation
MachineExecution
ForeachknowledgerepresentationlayerinCDSstack: Datastandard(controlledmedicalterminology,conceptdefinitions,allowablevalues)
Logicspecification(statementofrulelogic) Functionalrequirement(specificationofITfeaturerequirementsforexpressionofrule,etc.)
Reportspecification(descriptionofmethodforCDSimpactmeasurementandassessment)
Collaboration eRoom for Adult Primary Care
51
1 Oct 08 9:55pm • How does everyone feel about this?
• Should we turn the reminder off for a shorter period of time if “Done Elsewhere” is chosen?
PersonalHealth
InformationNetwork
Community(”Crowd”)MedicalProfessional
ScienceRulebuilder
Knowledge
respository
Ruleengine
Clin.Inf.System
PetterK.RisøeHSPH HPM512 2009
Patient
“I conclude that though the individual physician is not perfectible, the system of care is, and that the computer will play a major part in the perfection of future care systems.”
Clem McDonald, MD NEJM 1976
Thank you! Blackford Middleton, MD [email protected] www.partners.org/cird www.citl.org