51
CDSS-1 CSE 300 Clinical Decision Support Clinical Decision Support Systems Systems Mohammed Saleem Mohammed Saleem

CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

  • View
    220

  • Download
    2

Embed Size (px)

Citation preview

Page 1: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-1

CSE 300

Clinical Decision Support Systems Clinical Decision Support Systems

Mohammed Saleem Mohammed Saleem

Page 2: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-2

CSE 300

OverviewOverview

Scope of Clinical Decision Support SystemsScope of Clinical Decision Support Systems Issues for success or failureIssues for success or failure Evaluation of Clinical Decision Support Evaluation of Clinical Decision Support

SystemsSystems Computing techniques used to create DSSComputing techniques used to create DSS Design Cycle for the development of DSSDesign Cycle for the development of DSS Early AI/Decision Support Systems. Early AI/Decision Support Systems. Open source Example Open source Example

Page 3: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-3

CSE 300

Scope of Clinical Decision Support SystemsScope of Clinical Decision Support Systems

DefinitionDefinition Categories of CDSSCategories of CDSS System Architecture System Architecture Advantages / Need for CDSSAdvantages / Need for CDSS Applications AreasApplications Areas DisadvantagesDisadvantages

Page 4: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-4

CSE 300

DefinitionDefinition

A A clinical decision-support systemclinical decision-support system is any is any computer program designed to help health computer program designed to help health professionals make clinical decisions.professionals make clinical decisions.

In a sense, In a sense, anyany computer system that deals computer system that deals with clinical data or medical knowledge is with clinical data or medical knowledge is intended to provide decision support.intended to provide decision support.

Three types of decision-support function, Three types of decision-support function, ranging from generalized to patient specific.ranging from generalized to patient specific.

Page 5: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-5

CSE 300

CategoriesCategories

Generating alerts and remindersGenerating alerts and reminders Diagnostic assistanceDiagnostic assistance Therapy critiquing and planningTherapy critiquing and planning Image recognition and interpretationImage recognition and interpretation

Page 6: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-6

CSE 300

Inference Engine

ClinicalData

Repository(CDR)

User

Knowledge Base

Event Monitor

NotifierRecipient(s)

Page 7: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-7

CSE 300

Tools for Information ManagementTools for Information Management

Examples:Examples: Hospital information systems Bibliographic retrieval systems (PubMed) Specialized knowledge-management workstations

(e.g. electronic textbooks, …) These tools provide the data and knowledge These tools provide the data and knowledge

needed, but they do not help to needed, but they do not help to applyapply that that information to a particular decision task information to a particular decision task (particular patient)(particular patient)

Page 8: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-8

CSE 300

Tools for Focusing AttentionTools for Focusing Attention

Examples:Examples: Clinical laboratory systems that flag abnormal

values or that provide lists of possible explanations for those abnormalities.

Pharmacy systems that alert providers to possible drug interactions or incorrect drug dosages

Are designed to remind the physician of Are designed to remind the physician of diagnoses or problems that might be diagnoses or problems that might be overlooked.overlooked.

Page 9: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-9

CSE 300

Tools for Patient-Specific ConsultationTools for Patient-Specific Consultation

Provide customized assessments or advice Provide customized assessments or advice based on sets of patient-specific data:based on sets of patient-specific data: Suggest differential diagnoses Advice about additional tests and examinations Treatment advice (therapy, surgery, …)

Page 10: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-10

CSE 300

Alternative (more specific) DefinitionAlternative (more specific) Definition

Clinical decision support systems are Clinical decision support systems are active active knowledge systems knowledge systems which use two or more which use two or more items of patient data to generate case-specific items of patient data to generate case-specific advice.advice.

Main components:Main components: Medical knowledge Patient data Case-specific advice

Page 11: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-11

CSE 300

Characterizing Decision-Support SystemsCharacterizing Decision-Support Systems

SystemSystem functionfunction Determining what is true about a patient (e.g.

correct diagnosis) Determining what to do (what test to order, to

treat or not, what therapy plan …) The mode for giving adviceThe mode for giving advice

Passive role (physician uses the system when advice needed)

Active role (the system gives advice automatically under certain conditions)

Page 12: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-12

CSE 300

Passive SystemsPassive Systems

The user has total control:The user has total control: Requires advice Analyses the advice Accepts/Rejects the advice

Domain of use:Domain of use: Wide domain like internal medicine

Examples: QMR, DXPLAIN Narrow domain

Acute abdominal pain Analysis of ECG

Page 13: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-13

CSE 300

Passive Systems (cont.)Passive Systems (cont.)

Characteristics:Characteristics: Stand-alone Data entry:

System initiative User initiative

Consultation style Consulting model Critiquing model

Page 14: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-14

CSE 300

Active SystemsActive Systems

The user has partial controlThe user has partial control System gives advice User evaluates the advice The user accepts/rejects the advice

Domain of useDomain of use Limited domain

Drug interactions Protocol conformance control Laboratory results warnings Medical devices control

Page 15: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-15

CSE 300

Active Systems (cont.)Active Systems (cont.)

CharacteristicsCharacteristics Built-in/integrated with other system (e.g. laboratory

information system, or pharmacy system) Data entryData entry

By the user Related to the main application

Consultation styleConsultation style Critiquing model

Examples:Examples: HELP (advices and reminders, therapy) CARE (reminders)

Page 16: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-16

CSE 300

Need for CDSSNeed for CDSS

Limited resources - increased demandLimited resources - increased demandPhysicians are overwhelmed.Physicians are overwhelmed. Insufficient time available for diagnosis and

treatment. Need for systems that can improve health care Need for systems that can improve health care

processes and their outcomes in this scenarioprocesses and their outcomes in this scenario

Page 17: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-17

CSE 300

Application AreasApplication Areas

Page 18: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-18

CSE 300

Possible Disadvantages of CDSSPossible Disadvantages of CDSS

Changing relation between patient and the Changing relation between patient and the physicianphysician

Limiting professionals’ possibilities for Limiting professionals’ possibilities for independent problem solvingindependent problem solving

Legal implications - with whom does the onus Legal implications - with whom does the onus of responsibility lie?of responsibility lie?

Page 19: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-19

CSE 300

Issues for success or failureIssues for success or failure

Evaluation of User NeedsEvaluation of User Needs Top management supportTop management support Commitment of expertCommitment of expert Integration IssuesIntegration Issues Human Computer InterfaceHuman Computer Interface Incorporation of domain knowledgeIncorporation of domain knowledge Consideration of social and organisational Consideration of social and organisational

context of the CDSScontext of the CDSS

Page 20: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-20

CSE 300

Evaluation of Clinical Decision Support SystemsEvaluation of Clinical Decision Support Systems

Criteria for success of CDSSCriteria for success of CDSS Aspects for consideration during evaluationAspects for consideration during evaluation

Page 21: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-21

CSE 300

Criteria for a clinically useful DSSCriteria for a clinically useful DSS

Knowledge based on best evidenceKnowledge based on best evidence Knowledge fully covers problemKnowledge fully covers problem Knowledge can be updatedKnowledge can be updated Data actively used drawn from existing Data actively used drawn from existing

sources sources Performance validated rigorouslyPerformance validated rigorously

Page 22: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-22

CSE 300

Criteria for a clinically useful DSS (cont.)Criteria for a clinically useful DSS (cont.)

System improves clinical practiceSystem improves clinical practice Clinician is in controlClinician is in control The system is easy to useThe system is easy to use The decisions made are transparentThe decisions made are transparent

Page 23: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-23

CSE 300

Aspects for Evaluation of a CDSSAspects for Evaluation of a CDSS

The process used to develop the systemThe process used to develop the system The systems essential structureThe systems essential structure Evidence of accuracy, generality and clinical Evidence of accuracy, generality and clinical

effectivenesseffectiveness The impact of the resource on patients and The impact of the resource on patients and

other aspects of the health care environmentother aspects of the health care environment

Page 24: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-24

CSE 300

Computing techniques used to create DSSComputing techniques used to create DSS

Machine Learning and Adaptive ComputingMachine Learning and Adaptive Computing Inductive Tree Methods Case Based Reasoning Artificial Neural Networks

Expert Systems - Knowledge based MethodsExpert Systems - Knowledge based Methods Rule based Systems

Page 25: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-25

CSE 300

Design Cycle for the development of a CDSSDesign Cycle for the development of a CDSS

Planning PhasePlanning Phase Research PhaseResearch Phase System Analysis and conceptual phaseSystem Analysis and conceptual phase Design Phase Design Phase Construction phaseConstruction phase Further Development phaseFurther Development phase Maintenance, documentation and adaptationMaintenance, documentation and adaptation

Page 26: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-26

CSE 300

Early AI/Decision Support Systems. Early AI/Decision Support Systems.

De Dombal's system for acute abdominal De Dombal's system for acute abdominal pain (1972) pain (1972) developed at Leeds University decision making was based on the naive

Bayesian approach automated reasoning under uncertainty designed to support the diagnosis of acute

abdominal pain

Page 27: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-27

CSE 300

Early AI/Decision Support Systems. Early AI/Decision Support Systems.

INTERNIST-I (1974) INTERNIST-I (1974) rule-based expert system designed at the

University of Pittsburgh diagnosis of complex problems in general

internal medicine It uses patient observations to deduce a list of

compatible disease states used as a basis for successor systems including

CADUCEUS and Quick Medical Reference (QMR)

Page 28: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-28

CSE 300

Example: Decision TreeExample: Decision Tree 1 1

Page 29: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-29

CSE 300

Example: Decision Tree 2Example: Decision Tree 2

Page 30: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-30

CSE 300

MYCIN (1976) MYCIN (1976) rule-based expert system designed to diagnose

and recommend treatment for certain blood infections (extended to handle other infectious diseases)

Clinical knowledge in MYCIN is represented as a set of IF-THEN rules with certainty factors attached to diagnoses

Page 31: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-31

CSE 300

Example: Decision Rule 1Example: Decision Rule 1

Page 32: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-32

CSE 300

System MYCIN – a Decision RuleSystem MYCIN – a Decision Rule

Page 33: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-33

CSE 300

System MYCIN – Explanation ExampleSystem MYCIN – Explanation Example

Page 34: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-34

CSE 300

System HELP – MLM ExampleSystem HELP – MLM Example

Page 35: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-35

CSE 300

System ONCOCIN – Cancer-Treatment Protocol ExampleSystem ONCOCIN – Cancer-Treatment Protocol Example

Page 36: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-36

CSE 300

Successful CDS Systems Successful CDS Systems

DXplain DXplain uses a set of clinical findings (signs, symptoms,

laboratory data) to produce a ranked list of diagnosis

DXplain includes 2,200 diseases and 5,000 symptoms in its knowledge base.

provides justification for why each of these diseases might be considered, suggests what further clinical information would be useful to collect for each disease.

Page 37: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-37

CSE 300

Successful CDS Systems (cont.)Successful CDS Systems (cont.)

QMR Quick Medical ReferenceQMR Quick Medical Reference Based on Internist-1 A diagnostic decision-support system with a

knowledge base of diseases, diagnoses, findings, disease associations and lab information

medical literature on almost 700 diseases and more than 5,000 symptoms, signs, and labs.

frequency weight (FW) evoking strength (ES)

Page 38: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-38

CSE 300

Page 39: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-39

CSE 300

Open Source Medical Decision Open Source Medical Decision Support System Support System

Page 40: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-40

CSE 300

EMR/CIS/HIS (description of patient) + New Symptoms

Decision Support

Page 41: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-41

CSE 300

Existing Medical DSS SystemsExisting Medical DSS Systems

70 known proprietary DSS Systems.70 known proprietary DSS Systems. Only 10 of 70 geared towards General Practice. All require advanced technical knowledge. None allow source access to modify interface to

Clinical. Information Systems (CIS). Only one is correctable/updateable by end user. Developed with little consideration of end users

“..thus far the systems have failed to gain wide acceptance by physicians.”

Proprietary attempts to help physicians have Proprietary attempts to help physicians have failed.failed. Cost to generate useful database outside reach of one

company.

Page 42: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-42

CSE 300

Proposed SolutionProposed Solution

Clinical Decision Support System (DSS).Clinical Decision Support System (DSS). Instant recommendations from an “expert” Improved care and accuracy of diagnoses.

Reduce liability insurance premiums. Reduce the number of office visits to resolve

conditions. Reduce the number of treatments attempted

to resolve conditions.

Page 43: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-43

CSE 300 Clinical Decision Support System (DSS).Clinical Decision Support System (DSS).

Allows verification of data not easily available for proprietary solutions.

Allows updates in a timely and peer reviewable (e.g. Guideline International Network or NGC) manner.

Integration is possible with EMR/CIS/HIS for record keeping and more detailed diagnoses based on regional statistics and past history.

Reduction in the overall cost per man-hour.

Proposed SolutionProposed Solution

Page 44: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-44

CSE 300

Features of DSSFeatures of DSS

Describe Condition of Patient using StandardsDescribe Condition of Patient using Standards Standards approach eases interface with other

systems, including proprietary systems.

Page 45: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-45

CSE 300

Features of DSSFeatures of DSS Describe Clinical Guidelines and Diseases using Describe Clinical Guidelines and Diseases using

StandardsStandards Several standards being considered for

harmonization. GLIF3 has a lot of support.

Standards approach eases interface with other systems, including proprietary systems.

Page 46: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-46

CSE 300

Features of DSSFeatures of DSS

Simplified Graphical User Interface.Simplified Graphical User Interface. Do for medical decision support systems what web browsers

did for the internet, what GUI did for PC’s and PDA’s. Usable by anyone, including physicians, nurses and patients.

– Base on open-source info (e.g. visible human project.)

Page 47: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-47

CSE 300

IssuesIssues

Privacy concerns/laws.Privacy concerns/laws. No code shared with EMR/CIS/HIS. Patient identity not shared with DSS system.

Tremendous amount of data and rules Tremendous amount of data and rules must be incorporated into system.must be incorporated into system. National Health Information Technology

Coordinator created in 2004 to encourage/fund electronic health initiatives.

Resistance/job fears of cliniciansResistance/job fears of clinicians Goal is to assist clinicians, not replace them.

Page 48: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-48

CSE 300

Issues (cont.)Issues (cont.)

Clinical Trial Hurdles.Clinical Trial Hurdles. Make recommendations, not diagnoses. Disclaimers regarding use.

All past efforts have failed to achieve All past efforts have failed to achieve common usage.common usage. Include end users (physicians, nurses,

schedulers, IT departments) in the design decisions and testing.

Iterative design approach (i.e. modify based on feedback.)

Page 49: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-49

CSE 300

Existing Open Source ExampleExisting Open Source Example

EGADSS system:

• Interfaces with EMR/CIS only.

- No direct symptom inputs.

• Institutional support and funding.

Recommended Modifications:

• Add GUI for patient/physician direct access.

• Support development of Computer Interpretable Clinical Guidelines (CIG).

Page 50: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-50

CSE 300

Where do we go from here?Where do we go from here?

Promote open source Computer Interpretable clinical Promote open source Computer Interpretable clinical Guideline (CIG) knowledge base development at the federal Guideline (CIG) knowledge base development at the federal level with continuing maintenance from AHRQ.level with continuing maintenance from AHRQ. All 70+ proprietary efforts to develop knowledge bases have

failed. AHRQ already maintains written clinical guidelines AHRQ represents the U.S. for international vetting of clinical

guidelines. Funding opportunity in upcoming HIT legislation

Form IEEE study group on clinical interfaces and systems.Form IEEE study group on clinical interfaces and systems. Review past analyses of clinical interfaces. Work with doctors, nurses, hospitals, HMO’s, etc. to obtain

input and feedback. Perform human factors studies, if warranted. Develop needs statement or software specification for clinical

interfaces.

Page 51: CDSS-1 CSE 300 Clinical Decision Support Systems Mohammed Saleem

CDSS-51

CSE 300

SourcesSources Perreault L, Metzger J. A pragmatic framework for understanding clinical decision Perreault L, Metzger J. A pragmatic framework for understanding clinical decision

support. Journal of Healthcare Information Management. 1999;13(2):5-21.support. Journal of Healthcare Information Management. 1999;13(2):5-21. Musen MA. Stanford Medical Informatics: uncommon research, common goals. Musen MA. Stanford Medical Informatics: uncommon research, common goals.

MD Comput. 1999 Jan-Feb;16(1):47-8, 50. MD Comput. 1999 Jan-Feb;16(1):47-8, 50. E. Coiera. The Guide to Health Informatics (2nd Edition). Arnold, London, E. Coiera. The Guide to Health Informatics (2nd Edition). Arnold, London,

October 2003.October 2003. EGADSS: EGADSS: http://www.egadss.orghttp://www.egadss.org OpenClinical: http://www.openclinical.org/dss.htmlOpenClinical: http://www.openclinical.org/dss.html Whyatt and SpiegelhalterWhyatt and Spiegelhalter ( (http://http://www.computer.privateweb.at/judith/index.htmlwww.computer.privateweb.at/judith/index.html)) OpenClinical (OpenClinical (http://http://www.openclinical.org/home.htmlwww.openclinical.org/home.html)) de Dombal FT, Leaper DJ, Staniland JR, McCann AP, Horrocks JC. Computer-de Dombal FT, Leaper DJ, Staniland JR, McCann AP, Horrocks JC. Computer-

aided diagnosis of acute abdominal pain. Br Med J. 1972 Apr 1;2(5804):9-13. aided diagnosis of acute abdominal pain. Br Med J. 1972 Apr 1;2(5804):9-13. Solventus (Solventus (http://http://www.solventus.comwww.solventus.com/aquifer/aquifer)) Conversations with Dan Smith at ASTMConversations with Dan Smith at ASTM Agency for Healthcare, Research and Quality/AHRQ (Agency for Healthcare, Research and Quality/AHRQ (http://www.ahrq.gov/http://www.ahrq.gov/ and and

http://http://www.guideline.govwww.guideline.gov)) WebMD (WebMD (http://my.webmd.com/medical_information/check_symptomshttp://my.webmd.com/medical_information/check_symptoms)) http://www.cems.uwe.ac.uk/~pcalebso/UWEDMGroup/Documents/MDSS.ppthttp://www.cems.uwe.ac.uk/~pcalebso/UWEDMGroup/Documents/MDSS.ppt http://www.healthsystem.virginia.edu/internet/familymed/information_mastery/Clihttp://www.healthsystem.virginia.edu/internet/familymed/information_mastery/Cli

nical_Decision_Making_in_3_Minutes_or_Less.pptnical_Decision_Making_in_3_Minutes_or_Less.ppt http://www.phoenix.tc-ieee.org/016_Clinical_Care_Support_System/Open_CIG_9http://www.phoenix.tc-ieee.org/016_Clinical_Care_Support_System/Open_CIG_9

_19_sanitized.ppt_19_sanitized.ppt