SlideShare une entreprise Scribd logo
1  sur  16
Improving search efficiency
for economic evaluations in
major databases using
semantic technology
Julie Glanville, Carol Lefebvre, Pamela
Negosanti, Bill Porter
jmg1@york.ac.uk
Oct 2010
Overview
 Why are we interested in economic evaluations?
 Can economic evaluations be identified efficiently at
present?
 This research project
 Methods
 Results
 Discussion
 Next steps
Why are we interested in
economic evaluations?
 Systematic reviews and technology assessments frequently
consider cost-effectiveness as well as effectiveness outcomes
 This information is published in economic evaluations
 Cost-effectiveness analyses
 Cost-utility analyses
 Cost-benefit analyses
 Issues in identifying reports of economic evaluations
 Poor reporting
 abstracts may contain terms which signal an economic evaluation but not an
explicit term
 Economics is often mentioned in passing in abstracts
 Increases number of irrelevant records retrieved
Can economic evaluations be
identified efficiently?
 In healthcare databases
 Yes and No
 Specific economic evaluation databases are available (NHS
EED and HEED)
 BUT may need to carry out top up/supplementary searches
in large bibliographic databases
 Beyond healthcare
 Seem to be no economic evaluation databases
 Need to search large bibliographic databases such as ERIC
and Criminal Justice Abstracts
What about search filters?
Can search filters help?
 In healthcare databases
 Many search filters
 search filters to find economic evaluations in EMBASE and
MEDLINE achieve high sensitivity (100%) (1)
 BUT they have poor precision (less than 4%): very high proportion
of irrelevant studies are retrieved (1)
 Beyond health
 Few filters available
 Issues of precision likely to be similar to health
(1)Glanville J, Kaunelis D,Mensinkai S.How well do search filtersperform in identifying
economic evaluations in MEDLINE and EMBASE. Int J Tech Assess Hlth Care
2009;25:522-529
This research project
 How can we improve efficiency of retrieval of
economic evaluations in large bibliographic
databases?
 Traditional Boolean approaches don’t seem to be
helping
 Indexing isn’t very helpful at present
 Can semantic analysis software help?
 Collaboration with Expert System to explore potential
for identifying economic evaluations using their
Cogito software
Semantic Net
Semantic analysis
Analysis hat assigns a meaning, a sense, to a syntactic
structure and consequently to a linguistic unit, according
to the knowledge contained in the semantic network.
Methods
 Gold standard set of 1950 economic evaluation records
(published 2000, 2003, 2006)
 identified from NHS EED and then downloaded from MEDLINE.
 Comparator set of 4136 matching MEDLINE records for the 3
years (2000, 2003, 2006)
 not economic evaluations
 But identified using the NHS EED filter
 Loaded into Cogito
 Divided randomly into test sets and validation sets
 Used in-built semantic analysis and also created new rules to
categorise economic evaluations to categorise records as
economic evaluations or non-economic evaluations
Testing and validation
Results
Test set
(Gold Standard
records=975)
(Comparator records =
2068)
Validation set
(Gold Standard
records=975)
(Comparator records =
2068)
Number of gold standard (GS)
records retrieved 975 975
Number of comparator records
retrieved 203 385
Sensitivity
(number GS retrieved/number of
GS records) 100% 100%
Precision
(number of GS retrieved/number
of records retrieved) 82.77% 71.69%
Results, 2
 
Precision 
(combined Test and 
Validation sets)
Sensitivity 
(combined Test and 
Validation sets)
Using Cogito in-built 
semantic rules (no filter) 77.23% 100%
Using filter with records 
scoring 50
78% 
90%
Using filter with records 
scoring 100 80% 85%
Using filter with records 
scoring 200 81%  83%
Discussion
 Cogito performs as well as Boolean searching in terms of
sensitivity
 Cogito has a much improved precision score compared to
performance of Boolean filters
 Over 70% (Cogito) compared to under 10% (Glanville et al)
 Cogito performs well ‘out of the box’
 Although early training efforts did not improve precision, further
exploration might yield improved results
Next steps
 Identifying funding to carry out further exploration
 Exploring economic evaluation identification optimisation further
 Exploring the effects of importing results from a range of databases into
Cogito
 Exploring whether semantic analysis has potential to achieve
improvements in retrieval of other hard to find research where filters do
not perform well
 diagnostic test accuracy studies and quality of life research
 Exploring the potential of semantic analysis for analysing records
by study design obtained from a range of databases in healthcare,
social care, education and criminal justice contexts
 in-built rules are database independent.
For further information
Julie Glanville, York Health Economics
Consortium
jmg1@york.ac.uk
Bill Porter at Expert System
http://www.expertsystem.net/
bporter@expertsystem.net

Contenu connexe

Tendances

Coaching Action Plan for MSL - Investigator Initiated Trials
Coaching Action Plan for MSL - Investigator Initiated TrialsCoaching Action Plan for MSL - Investigator Initiated Trials
Coaching Action Plan for MSL - Investigator Initiated Trials
Marieke Jonkman PharmD
 
Innovation Centers and Health Care
Innovation Centers and Health CareInnovation Centers and Health Care
Innovation Centers and Health Care
The Commonwealth Fund
 

Tendances (13)

Real-World Evidence Database Studies
Real-World Evidence Database StudiesReal-World Evidence Database Studies
Real-World Evidence Database Studies
 
Chapter 020
Chapter 020Chapter 020
Chapter 020
 
Business Consulting Presentation
Business Consulting PresentationBusiness Consulting Presentation
Business Consulting Presentation
 
Perceptions of the Nursing Faculty Towards the Development of eTest Generator
Perceptions of the Nursing Faculty Towards the Development of eTest GeneratorPerceptions of the Nursing Faculty Towards the Development of eTest Generator
Perceptions of the Nursing Faculty Towards the Development of eTest Generator
 
Applied Statistics, with Emphasis on Risk Management in R&D, QA/QC, and Manuf...
Applied Statistics, with Emphasis on Risk Management in R&D, QA/QC, and Manuf...Applied Statistics, with Emphasis on Risk Management in R&D, QA/QC, and Manuf...
Applied Statistics, with Emphasis on Risk Management in R&D, QA/QC, and Manuf...
 
Coaching Action Plan for MSL - Investigator Initiated Trials
Coaching Action Plan for MSL - Investigator Initiated TrialsCoaching Action Plan for MSL - Investigator Initiated Trials
Coaching Action Plan for MSL - Investigator Initiated Trials
 
Innovation Centers and Health Care
Innovation Centers and Health CareInnovation Centers and Health Care
Innovation Centers and Health Care
 
Bdo Sr&Ed Presentation Silicon Halton March 23, 2010. Meetup 5.
Bdo Sr&Ed Presentation Silicon Halton March 23, 2010. Meetup 5.Bdo Sr&Ed Presentation Silicon Halton March 23, 2010. Meetup 5.
Bdo Sr&Ed Presentation Silicon Halton March 23, 2010. Meetup 5.
 
Towers Perrin's Health Care 360 Performance Study - Value for Your Organization
Towers Perrin's Health Care 360 Performance Study - Value for Your OrganizationTowers Perrin's Health Care 360 Performance Study - Value for Your Organization
Towers Perrin's Health Care 360 Performance Study - Value for Your Organization
 
A/B testing from basic concepts to advanced techniques
A/B testing  from basic concepts to advanced techniquesA/B testing  from basic concepts to advanced techniques
A/B testing from basic concepts to advanced techniques
 
The Perils of Clinical Trial Budgeting
The Perils of Clinical Trial BudgetingThe Perils of Clinical Trial Budgeting
The Perils of Clinical Trial Budgeting
 
Investigator initiated trials (ExL Conference April-2012)
Investigator initiated trials (ExL Conference April-2012)Investigator initiated trials (ExL Conference April-2012)
Investigator initiated trials (ExL Conference April-2012)
 
Laatsit - Towards a typology of innovation system practices
Laatsit - Towards a typology of innovation system practicesLaatsit - Towards a typology of innovation system practices
Laatsit - Towards a typology of innovation system practices
 

En vedette

Improving rapid access to reports of RCTs from EMBASE: innovative methods to...
Improving rapid access to reports of RCTs from EMBASE: innovative  methods to...Improving rapid access to reports of RCTs from EMBASE: innovative  methods to...
Improving rapid access to reports of RCTs from EMBASE: innovative methods to...
York Health Economics Consortium (YHEC)
 
Travel bandefo 2 B bandini de feudis
Travel bandefo 2 B bandini de feudisTravel bandefo 2 B bandini de feudis
Travel bandefo 2 B bandini de feudis
guestc93580
 
UGIF 12 2010 - migration v11 - Khaled Bentebal
UGIF 12 2010 - migration v11 - Khaled BentebalUGIF 12 2010 - migration v11 - Khaled Bentebal
UGIF 12 2010 - migration v11 - Khaled Bentebal
UGIF
 
Ugif 12 2011-ibm cap-seine
Ugif 12 2011-ibm cap-seineUgif 12 2011-ibm cap-seine
Ugif 12 2011-ibm cap-seine
UGIF
 
The Impact of Increased Survival in the Assessment of Interventions for Cancer
The Impact of Increased Survival in the Assessment of Interventions for CancerThe Impact of Increased Survival in the Assessment of Interventions for Cancer
The Impact of Increased Survival in the Assessment of Interventions for Cancer
York Health Economics Consortium (YHEC)
 

En vedette (9)

Improving rapid access to reports of RCTs from EMBASE: innovative methods to...
Improving rapid access to reports of RCTs from EMBASE: innovative  methods to...Improving rapid access to reports of RCTs from EMBASE: innovative  methods to...
Improving rapid access to reports of RCTs from EMBASE: innovative methods to...
 
Travel bandefo 2 B bandini de feudis
Travel bandefo 2 B bandini de feudisTravel bandefo 2 B bandini de feudis
Travel bandefo 2 B bandini de feudis
 
UGIF 12 2010 - migration v11 - Khaled Bentebal
UGIF 12 2010 - migration v11 - Khaled BentebalUGIF 12 2010 - migration v11 - Khaled Bentebal
UGIF 12 2010 - migration v11 - Khaled Bentebal
 
Twitter
TwitterTwitter
Twitter
 
Ugif 12 2011-ibm cap-seine
Ugif 12 2011-ibm cap-seineUgif 12 2011-ibm cap-seine
Ugif 12 2011-ibm cap-seine
 
Is it appropriate to limit searches to prospective trials registries? Resear...
Is it appropriate to limit searches to prospective trials registries? Resear...Is it appropriate to limit searches to prospective trials registries? Resear...
Is it appropriate to limit searches to prospective trials registries? Resear...
 
IEEE754-pourquoi_les_calculs_informatiques_sont_faux
IEEE754-pourquoi_les_calculs_informatiques_sont_fauxIEEE754-pourquoi_les_calculs_informatiques_sont_faux
IEEE754-pourquoi_les_calculs_informatiques_sont_faux
 
The Impact of Increased Survival in the Assessment of Interventions for Cancer
The Impact of Increased Survival in the Assessment of Interventions for CancerThe Impact of Increased Survival in the Assessment of Interventions for Cancer
The Impact of Increased Survival in the Assessment of Interventions for Cancer
 
NHS consultancy and outcomes research from YHEC
NHS consultancy and outcomes research from YHECNHS consultancy and outcomes research from YHEC
NHS consultancy and outcomes research from YHEC
 

Similaire à Improving search efficiency for economic evaluations in major databases using semantic technology

Continued Use Of IDAs And Knowledge Acquisition
Continued Use Of IDAs And Knowledge AcquisitionContinued Use Of IDAs And Knowledge Acquisition
Continued Use Of IDAs And Knowledge Acquisition
Micheal Axelsen
 
The High Quality Data Gathering System Essay
The High Quality Data Gathering System EssayThe High Quality Data Gathering System Essay
The High Quality Data Gathering System Essay
Divya Watson
 
LASA 2—Company Analysis Report RubricNOTE If a componen.docx
LASA 2—Company Analysis Report RubricNOTE If a componen.docxLASA 2—Company Analysis Report RubricNOTE If a componen.docx
LASA 2—Company Analysis Report RubricNOTE If a componen.docx
DIPESH30
 
Cost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docx
Cost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docxCost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docx
Cost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docx
bobbywlane695641
 
Chapter 14 certificationsIT Framework standards
Chapter 14 certificationsIT Framework standardsChapter 14 certificationsIT Framework standards
Chapter 14 certificationsIT Framework standards
EstelaJeffery653
 
Highlights from ExL Pharma's Proactive GCP Compliance
Highlights from ExL Pharma's Proactive GCP ComplianceHighlights from ExL Pharma's Proactive GCP Compliance
Highlights from ExL Pharma's Proactive GCP Compliance
ExL Pharma
 
Healthcare quality improvement for meaningful use
Healthcare quality improvement for meaningful useHealthcare quality improvement for meaningful use
Healthcare quality improvement for meaningful use
Samantha Haas
 
Term Paper OutlineTopic Benefits of data analytics for extern.docx
Term Paper OutlineTopic Benefits of data analytics for extern.docxTerm Paper OutlineTopic Benefits of data analytics for extern.docx
Term Paper OutlineTopic Benefits of data analytics for extern.docx
jacqueliner9
 

Similaire à Improving search efficiency for economic evaluations in major databases using semantic technology (20)

Continued Use Of IDAs And Knowledge Acquisition
Continued Use Of IDAs And Knowledge AcquisitionContinued Use Of IDAs And Knowledge Acquisition
Continued Use Of IDAs And Knowledge Acquisition
 
The High Quality Data Gathering System Essay
The High Quality Data Gathering System EssayThe High Quality Data Gathering System Essay
The High Quality Data Gathering System Essay
 
Can systematic reviews help identify what works and why?
Can systematic reviews help identify what works and why?Can systematic reviews help identify what works and why?
Can systematic reviews help identify what works and why?
 
first-batch-me-training.pptx
first-batch-me-training.pptxfirst-batch-me-training.pptx
first-batch-me-training.pptx
 
LASA 2—Company Analysis Report RubricNOTE If a componen.docx
LASA 2—Company Analysis Report RubricNOTE If a componen.docxLASA 2—Company Analysis Report RubricNOTE If a componen.docx
LASA 2—Company Analysis Report RubricNOTE If a componen.docx
 
ISPMS Background, Purpose and Approach
ISPMS Background, Purpose and ApproachISPMS Background, Purpose and Approach
ISPMS Background, Purpose and Approach
 
Principles for good metrics: theory to practice
Principles for good metrics: theory to practicePrinciples for good metrics: theory to practice
Principles for good metrics: theory to practice
 
How to Implement Quality in Health Care Organizations.
How to Implement Quality in Health Care Organizations.How to Implement Quality in Health Care Organizations.
How to Implement Quality in Health Care Organizations.
 
Cost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docx
Cost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docxCost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docx
Cost-Benefit AnalysisCost-Benefit Analysis WorksheetThis cell left.docx
 
Chapter 14 certificationsIT Framework standards
Chapter 14 certificationsIT Framework standardsChapter 14 certificationsIT Framework standards
Chapter 14 certificationsIT Framework standards
 
An empirical performance evaluation of relational keyword search systems
An empirical performance evaluation of relational keyword search systemsAn empirical performance evaluation of relational keyword search systems
An empirical performance evaluation of relational keyword search systems
 
Highlights from ExL Pharma's Proactive GCP Compliance
Highlights from ExL Pharma's Proactive GCP ComplianceHighlights from ExL Pharma's Proactive GCP Compliance
Highlights from ExL Pharma's Proactive GCP Compliance
 
Healthcare quality improvement for meaningful use
Healthcare quality improvement for meaningful useHealthcare quality improvement for meaningful use
Healthcare quality improvement for meaningful use
 
Audit opinion & information asymmetry
Audit opinion & information asymmetryAudit opinion & information asymmetry
Audit opinion & information asymmetry
 
NURS 6052 Week 4 Paper Walden.docx
NURS 6052 Week 4 Paper Walden.docxNURS 6052 Week 4 Paper Walden.docx
NURS 6052 Week 4 Paper Walden.docx
 
Term Paper OutlineTopic Benefits of data analytics for extern.docx
Term Paper OutlineTopic Benefits of data analytics for extern.docxTerm Paper OutlineTopic Benefits of data analytics for extern.docx
Term Paper OutlineTopic Benefits of data analytics for extern.docx
 
Effects of factor analysis on the questionnaire of strategic marketing mix on...
Effects of factor analysis on the questionnaire of strategic marketing mix on...Effects of factor analysis on the questionnaire of strategic marketing mix on...
Effects of factor analysis on the questionnaire of strategic marketing mix on...
 
Denise Rousseau's Generic EBMgt Class 4
Denise Rousseau's Generic EBMgt Class 4Denise Rousseau's Generic EBMgt Class 4
Denise Rousseau's Generic EBMgt Class 4
 
Demonstrating Research Impact: Measuring Return on Investment with an Impact ...
Demonstrating Research Impact: Measuring Return on Investment with an Impact ...Demonstrating Research Impact: Measuring Return on Investment with an Impact ...
Demonstrating Research Impact: Measuring Return on Investment with an Impact ...
 
Using CATs and REAs to inform decision-making
Using CATs and REAs to inform decision-makingUsing CATs and REAs to inform decision-making
Using CATs and REAs to inform decision-making
 

Dernier

Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
Areesha Ahmad
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Sérgio Sacani
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
levieagacer
 
Human genetics..........................pptx
Human genetics..........................pptxHuman genetics..........................pptx
Human genetics..........................pptx
Silpa
 

Dernier (20)

PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 
Selaginella: features, morphology ,anatomy and reproduction.
Selaginella: features, morphology ,anatomy and reproduction.Selaginella: features, morphology ,anatomy and reproduction.
Selaginella: features, morphology ,anatomy and reproduction.
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICEPATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
 
Introduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxIntroduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptx
 
Zoology 5th semester notes( Sumit_yadav).pdf
Zoology 5th semester notes( Sumit_yadav).pdfZoology 5th semester notes( Sumit_yadav).pdf
Zoology 5th semester notes( Sumit_yadav).pdf
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
 
Velocity and Acceleration PowerPoint.ppt
Velocity and Acceleration PowerPoint.pptVelocity and Acceleration PowerPoint.ppt
Velocity and Acceleration PowerPoint.ppt
 
An introduction on sequence tagged site mapping
An introduction on sequence tagged site mappingAn introduction on sequence tagged site mapping
An introduction on sequence tagged site mapping
 
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
 
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIACURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
Use of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxUse of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptx
 
Human genetics..........................pptx
Human genetics..........................pptxHuman genetics..........................pptx
Human genetics..........................pptx
 
300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx
 

Improving search efficiency for economic evaluations in major databases using semantic technology

  • 1. Improving search efficiency for economic evaluations in major databases using semantic technology Julie Glanville, Carol Lefebvre, Pamela Negosanti, Bill Porter jmg1@york.ac.uk Oct 2010
  • 2. Overview  Why are we interested in economic evaluations?  Can economic evaluations be identified efficiently at present?  This research project  Methods  Results  Discussion  Next steps
  • 3. Why are we interested in economic evaluations?  Systematic reviews and technology assessments frequently consider cost-effectiveness as well as effectiveness outcomes  This information is published in economic evaluations  Cost-effectiveness analyses  Cost-utility analyses  Cost-benefit analyses  Issues in identifying reports of economic evaluations  Poor reporting  abstracts may contain terms which signal an economic evaluation but not an explicit term  Economics is often mentioned in passing in abstracts  Increases number of irrelevant records retrieved
  • 4. Can economic evaluations be identified efficiently?  In healthcare databases  Yes and No  Specific economic evaluation databases are available (NHS EED and HEED)  BUT may need to carry out top up/supplementary searches in large bibliographic databases  Beyond healthcare  Seem to be no economic evaluation databases  Need to search large bibliographic databases such as ERIC and Criminal Justice Abstracts
  • 5. What about search filters?
  • 6. Can search filters help?  In healthcare databases  Many search filters  search filters to find economic evaluations in EMBASE and MEDLINE achieve high sensitivity (100%) (1)  BUT they have poor precision (less than 4%): very high proportion of irrelevant studies are retrieved (1)  Beyond health  Few filters available  Issues of precision likely to be similar to health (1)Glanville J, Kaunelis D,Mensinkai S.How well do search filtersperform in identifying economic evaluations in MEDLINE and EMBASE. Int J Tech Assess Hlth Care 2009;25:522-529
  • 7. This research project  How can we improve efficiency of retrieval of economic evaluations in large bibliographic databases?  Traditional Boolean approaches don’t seem to be helping  Indexing isn’t very helpful at present  Can semantic analysis software help?  Collaboration with Expert System to explore potential for identifying economic evaluations using their Cogito software
  • 9. Semantic analysis Analysis hat assigns a meaning, a sense, to a syntactic structure and consequently to a linguistic unit, according to the knowledge contained in the semantic network.
  • 10. Methods  Gold standard set of 1950 economic evaluation records (published 2000, 2003, 2006)  identified from NHS EED and then downloaded from MEDLINE.  Comparator set of 4136 matching MEDLINE records for the 3 years (2000, 2003, 2006)  not economic evaluations  But identified using the NHS EED filter  Loaded into Cogito  Divided randomly into test sets and validation sets  Used in-built semantic analysis and also created new rules to categorise economic evaluations to categorise records as economic evaluations or non-economic evaluations
  • 12. Results Test set (Gold Standard records=975) (Comparator records = 2068) Validation set (Gold Standard records=975) (Comparator records = 2068) Number of gold standard (GS) records retrieved 975 975 Number of comparator records retrieved 203 385 Sensitivity (number GS retrieved/number of GS records) 100% 100% Precision (number of GS retrieved/number of records retrieved) 82.77% 71.69%
  • 13. Results, 2   Precision  (combined Test and  Validation sets) Sensitivity  (combined Test and  Validation sets) Using Cogito in-built  semantic rules (no filter) 77.23% 100% Using filter with records  scoring 50 78%  90% Using filter with records  scoring 100 80% 85% Using filter with records  scoring 200 81%  83%
  • 14. Discussion  Cogito performs as well as Boolean searching in terms of sensitivity  Cogito has a much improved precision score compared to performance of Boolean filters  Over 70% (Cogito) compared to under 10% (Glanville et al)  Cogito performs well ‘out of the box’  Although early training efforts did not improve precision, further exploration might yield improved results
  • 15. Next steps  Identifying funding to carry out further exploration  Exploring economic evaluation identification optimisation further  Exploring the effects of importing results from a range of databases into Cogito  Exploring whether semantic analysis has potential to achieve improvements in retrieval of other hard to find research where filters do not perform well  diagnostic test accuracy studies and quality of life research  Exploring the potential of semantic analysis for analysing records by study design obtained from a range of databases in healthcare, social care, education and criminal justice contexts  in-built rules are database independent.
  • 16. For further information Julie Glanville, York Health Economics Consortium jmg1@york.ac.uk Bill Porter at Expert System http://www.expertsystem.net/ bporter@expertsystem.net

Notes de l'éditeur

  1. Improving search efficiency for economic evaluations in major databases using semantic technology" by Glanville, Julie; Lefebvre, Carol; Porter, Bill; Negosanti, Pamela,