eevidence : information seeking support for evidence-based practice: an implementation case study
DESCRIPTION
eEvidence : Information Seeking Support for Evidence-based Practice: An Implementation Case Study. Jin Zhao, Min-Yen Kan, Paula M. Procter, Siti Zubaidah , Wai Kin Yip, Goh Mien Li. Evidence-based Practice (EBP). Advantages Reliable, extensive and updated. Intervention A. - PowerPoint PPT PresentationTRANSCRIPT
eEvidence: Information Seeking Support for Evidence-based Practice:
An Implementation Case StudyJin Zhao, Min-Yen Kan, Paula M. Procter,
Siti Zubaidah, Wai Kin Yip, Goh Mien Li
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Evidence-based Practice (EBP)
• Advantages– Reliable, extensive and updated
2 of 15WING, NUS
Intervention C
Intervention B
Intervention A
Intuition
Experience
Research Articles
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Two Stages of EBP• Stage 1: Search and Appraise
• Stage 2: Apply and Evaluate
3 of 15WING, NUS
InterventionsArticle Collections
Research Articles
Interventions
Crucial yet difficult!
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Issues in the Search & Appraise Stage• Accessibility problems
– Collection-specific specialized search engines– Subscription barrier
• Usability gap in Search Engines– Key information not displayed or searchable
Elements of well-form clinical questions• E.g., demographics of the patient, intervention and results
Strength of evidence• E.g., study design
• Different search patterns– Active v.s. passive
4 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
eEvidence System for EBP• Key features
– Harvesting EBP resources by periodic crawling Address accessibility issue and ensures up-to-date coverage
– Automated article classification and key information extraction Provides crucial information to assist search and appraisal
– Dual active/passive user interface Caters for different search patterns
5 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
System Architecture
6WING, NUS
EBP resources
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Harvesting EBP Resources by Periodic Crawling• Two stages
– Selection of EBP resources by experts– Periodic crawling using Nutch
• Advantages– Able to harvest from any type of EBP resources– Always up-to-date
7 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Automated Article Classification• Supervised machine learning pipeline
– Three categories: full text / abstract / others– Maximum entropy classifier – Text, webpage and formatting features
• Advantages– Filters out useless webpages– Allows users to zoom to subsets of articles
8 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Automated Key Information Extraction• Year of publication, article type, time added, URL
• Key sentence / keywords
• Advantages– Provides crucial information to assist search and appraisal
9 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Extraction of Key Sentences and Keywords• Cast as two-stage pipelined soft-classification
10 of 15WING, NUS
Sentences
Patient Sentences
Research Goal Sentences
ResultSentences
Intervention Sentences
Sentence Classification
Study Design Sentences
Sex Keywords
Condition Keywords
Age Keywords
Intervention Keywords
Study Design Keywords
Race Keywords
Keyword classification
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Extraction of Key Sentences and Keywords• 1-against-all MaxEnt classifiers for each
class based on various text features
• Key Sentences Extraction– Precise but much room for improvement in recall– Due to the variety of sentence structure and the
shortness of information– Acceptable in the context of Information Retrieval
• Keywords Extraction– Good performance in general– Difficult to extract keywords belonging to classes
with a diverse vocabulary or lexical variations
11 of 15WING, NUS
Performance for key sentences extraction
Performance for keywords extraction
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Dual Interface (Read)• Recommend relevant articles based on user profile
12 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Dual Interface (Search)• Allow users to search with complex query and filters
• Search history in place of profile
13 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Discussion• Iterative development methodology
– Interview users for requirements– Design and implement features– Gather user feedbacks of the system
• Current feedbacks– Able to find freely available full text articles – Search history useful for writing of search methodology– Collection size still limited for practical task
• Future work– Improve key information extraction– Extend collection and perform full-fledge evaluation– Discover user- and group- specific features
14 of 15WING, NUS
Zhao et al.
10/08/2010
eEvidence: Information Seeking Support for Evidence-based Practice: An Implementation Case Study
Conclusion• eEvidence: a literature retrieval system with novel
features to facilitate EBP– Harvesting EBP resources by periodic crawling– Automated article classification and key information
extraction– Dual active/passive user interface
15 of 15WING, NUS