Presentation is loading. Please wait.

Presentation is loading. Please wait.

Copyright © 2010 Accenture All Rights Reserved. Accenture, its logo, and High Performance Delivered are trademarks of Accenture. Multiple Ontologies in.

Similar presentations


Presentation on theme: "Copyright © 2010 Accenture All Rights Reserved. Accenture, its logo, and High Performance Delivered are trademarks of Accenture. Multiple Ontologies in."— Presentation transcript:

1 Copyright © 2010 Accenture All Rights Reserved. Accenture, its logo, and High Performance Delivered are trademarks of Accenture. Multiple Ontologies in Healthcare Information Technology: Motivations and Recommendation for Ontology Mapping and Alignment Colin Puri 1, Karthik Gomadam 1, Prateek Jain 2, Peter Yeh 1, Kunal Verma 1 1 Accenture Technology Labs, San Jose, CA 2 Kno.e.sis Center Wright State University, Dayton, OH

2 Outline Introduction Current Approaches Ontology Mappings Our Point of View & Recommendation: BLOOMS Questions 2 ©Accenture 2011 Proprietary and Confidential

3 Introduction Key Issues –No single ontology can meet the growing needs of healthcare –Heterogeneous landscape –Existing ontologies must be integrated to support data analysis Integration of patient data and health sources allows for mining and answering of key questions –What treatments were administered to other patients with similar health conditions? –What was the efficacy of such treatments when administered to patients with a given physiological profile? –What medications are currently being prescribed to the patient and how do they constrain available treatment options? –How can one meaningfully find and and utilize the vast amounts of medical knowledge, such as codified medical vocabularies, scientific publications, and findings from clinical trials, available in the public domain? –How can the health and wellness information stored by a patient in PHRs and other PHR-based applications be used to improve the quality of care? 3 ©Accenture 2011 Proprietary and Confidential

4 Outline Introduction Current Approaches Ontology Mappings Our Point of View & Recommendation: BLOOMS Questions 4 ©Accenture 2011 Proprietary and Confidential

5 Current Efforts & Approaches A patient's medical record captures multiple aspects of his/her health Information can come from multiple sources (e.g. EMR systems, PHR applications, etc.). Integration into a coherent view requires combining multiple ontologies such as: –SnoMed –Gene Ontology Examples Current efforts: –UMLS Existing Challenges –Syntactic differences between ontologies –Deep semantic differences –Generation of mappings 5 ©Accenture 2011 Proprietary and Confidential

6 Outline Introduction Current Approaches Ontology Mappings Our Point of View & Recommendation: BLOOMS Questions 6 ©Accenture 2011 Proprietary and Confidential

7 Ontology Mapping Ontology Mapping and Alignment Strategies Include: –Machine Learning –Rule Based Mapping –Logic Driven Frameworks Categories of Ontology Mapping –Global ontology view to local ontology view –Semantic mappings between local and target entities –Mappings for enablement of ontology reuse by integration and alignment 7 ©Accenture 2011 Proprietary and Confidential

8 Outline Introduction Current Approaches Ontology Mappings Our Point of View & Recommendation: BLOOMS Questions 8 ©Accenture 2011 Proprietary and Confidential

9 BLOOMS Approach For each concept name in the ontology –Identify article in Wikipedia corresponding to the concept. –Each article related to the concept indicates a sense of the usage of the word. For each article found in the previous step –Identify the Wikipedia category to which it belongs. –For each category found, find its parent categories till level 4. Once the “BLOOMS tree” for each of the sense of the source concept is created (T i ), utilize it for comparison with the “BLOOMS tree” of the target concepts (T j ). –BLOOMS trees are created for individual senses of the concepts.

10 BLOOMS 10 ©Accenture 2011 Proprietary and Confidential Available for download at: http://wiki.knoesis.org/index.php/BLOOMS

11 BLOOMS

12 Conclusion We have presented a system called BLOOMS for performing ontology alignment using contextual information. BLOOMS can be extended to utilize datasource of choice such as UMLS. To the best of our knowledge, BLOOMS is the only system which utilizes contextual information present in ontology and Wikipedia category hierarchy for ontology matching. BLOOMS significantly outperforms state of the art solutions for the task of ontology alignment [1,2].

13 References ① Prateek Jain,Peter Z. Yeh, Kunal Verma, Reymonrod Vasquez, Mariana Damova, Pascal Hitzler and Amit P. Sheth, “Contextual Ontology Alignment of LOD with an Upper Ontology: A Case Study with Proton”.In Proceedings of the 8th Extended Semantic Web Conference 2011, volume 6643 of Lecture Notes in Computer Science, Heidelberg, 2011. Springer Berlin. ② Prateek Jain, Pascal Hitzler, Amit P. Sheth, Kunal Verma and Peter Z. Yeh, “Ontology Alignment for Linked Open Data”. In Proceedings of the 9th International Semantic Web Conference 2010, Shanghai, China, November 7th-11th, 2010,volume 6496 of Lecture Notes in Computer Science, pages 402-417, Heidelberg, 2010. Springer Berlin. 13 ©Accenture 2011 Proprietary and Confidential

14 Questions Any Questions? 14 ©Accenture 2011 Proprietary and Confidential


Download ppt "Copyright © 2010 Accenture All Rights Reserved. Accenture, its logo, and High Performance Delivered are trademarks of Accenture. Multiple Ontologies in."

Similar presentations


Ads by Google