1 / 40

C urrent status of O ntologies in B iomedical and C linical I nformatics.

C urrent status of O ntologies in B iomedical and C linical I nformatics. By Rishi Kanth Saripalle. Biomedical Informatics, University of Connecticut, Storrs. Overview. Aim of the Presentation. Ontology Definition and Description. Example. Present Biomedical Ontology

ekram
Download Presentation

C urrent status of O ntologies in B iomedical and C linical I nformatics.

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Current status of Ontologies in Biomedical and Clinical Informatics. By Rishi Kanth Saripalle Biomedical Informatics, University of Connecticut, Storrs

  2. Overview • Aim of the Presentation. • Ontology • Definition and Description. • Example. • Present Biomedical Ontology • Need for Integration • Application of Biomedical Ontology • Clinical Trials • OASIS: Integration Technique • Clinical Decision Support System • Summary BioMedical Informatics

  3. Goal To study about ontologies, their advantages and applications in the field of Biomedical and Clinical informatics. BioMedical Informatics

  4. Ontology Definition(From Philosophy) : According to Philosophy, Ontology is study of being or existence and forms the basic subject matter of metaphysics. It seeks to describe the basic categories and relationships of being or existence to define entities and types of entities within its framework. BioMedical Informatics

  5. Ontology Definition(From Computer Science) : In Computer science , Ontology means “specification of a conceptualization” .It means “A data model that represents a set of concepts within a domain and the relationships between those concepts”. BioMedical Informatics

  6. Advantages of Ontology • Semantic way of representing knowledge of the • domain. • Intelligent system can provide reasoning • Systems to make inferences within the Ontology.  To Share the common structure of information.  To reuse the similar domain Ontology. BioMedical Informatics

  7. Development of Ontology • Determine the domain and Scope ( Range ) of the knowledge.  Look for already existing ontology in the similar domain  Listing all the terminologies or Concepts of the domain • List all the classes and instances to be created in the • ontology. • Create the properties which will relate these concepts in the • ontology. BioMedical Informatics

  8. Example of Ontology Wine Australian Yellow Tail Class Individual Grape Properties Maker Color Flavor Property Values German Yellow Delicate Australia BioMedical Informatics

  9. Disease Ontology Sub-Classes of Cardiology Diseases Instances of Mitral_Valve_Disorders Hierarchical organization of Cardiology Diseases BioMedical Informatics

  10. Disease Ontology Property Defined Representation of “Mitral_Valve_Prolapse”knowledge using properties and instances BioMedical Informatics

  11. Implemented Ontology in OWL Format ………….. <Congenital_Heart_Diseaserdf:ID="Atrial_septal_defect"> <Complications> <Cardiac_Arrhythmiasrdf:ID="Arrhythmia"> <Has_Interventionrdf:datatype="http://www.w3.org/2001/XMLSchema#string" >defibrillation</Has_Intervention> <Have_Symptoms> <Cardiology_Symptomsrdf:ID="Dyspnea"/> </Have_Symptoms> <Has_Diagnosis_Test> <Cardiology_Diagnosis_Testrdf:ID="Coronary_Angiography"> <Has_Synonymsrdf:datatype="http://www.w3.org/2001/XMLSchema#string" >coronary catheterization </Has_Synonyms> ……………….. BioMedical Informatics

  12. Bio-Medical Ontologies • OpenCyc • WordNet • Galen • UMLS • SNOMED – CT • FMA • Gene Ontology BioMedical Informatics

  13. Open Cyc • Open Cyc is an Upper level ontology developed by Cycorp Inc. • Open Cyc has 60,000 hand coded assertions that • capture “common sense language”, so that AI • algorithms can perform human like reasoning and • contains 6,000 concepts BioMedical Informatics

  14. Word Net • WordNet is an electronic lexical database developed at • Princeton University that serves as a resource for • applications in natural language processing and • information retrieval. cancer, malignant neoplastic disease: any malignant growth or tumor caused by abnormal and uncontrolled cell division; it may spread to other parts of the body through the lymphatic system or the blood stream Cancer, Crab: (astrology) a person who is born while the sun is in Cancer Cancer: a small zodiacal constellation in the northern hemisphere; between Leo and Gemini Cancer, Cancer the Crab, Crab: the fourth sign of the zodiac; the sun is in this sign from about June 21 to July 22 Cancer, genus Cancer: type genus of the family Cancridae BioMedical Informatics

  15. Galen • GALEN stands for Generalised Architecture for • Languages, Encyclopedia and Nomenclature in Medicine. • It is a European project developed for reuse of terminology • in clinical systems. BioMedical Informatics

  16. UMLS • UMLS acronym for Unifies Medical Language System • was developed for National Library of Medicine. Disease is semantic type with around 392 relations (109 semantic relations and 22 other relations). Pneumonia categorized under one semantic type Disease, but has hundreds of relations. BioMedical Informatics

  17. SNOMED-CT • SNOMED stands for Systemized Nomenclature • Of Medicine Clinical Terms. SNOMED-CT is the • result of merging two ontologies: SNOMED-RT • and Clinical Terms. BioMedical Informatics

  18. Need for Integration • All the ontologies developed have a common aim, • describing the domain knowledge • Integration of ontologies is becoming very critical as • applications tend to use multiple ontologies and concepts in • the various ontology overlap or same concept is described in • multiple ways. • For example, the concept “Blood” is described differently • in above discussed ontologies. One describes it as “Fluid”, • another as “substance” and another as “semi- solid • substance” etc. BioMedical Informatics

  19. Ontology B Ontology A • Semantics vs Structural Integration ? • Difficulties of integration arise with similar, same and • complementary ontology integration. BioMedical Informatics

  20. OASIS OASIS: Ontology Mapping and Integration framework BioMedical Informatics

  21. Terms in the OBO ( Open Biomedical Ontology) are • arranged in Directed Acyclic Graph. This allows each • children to have multiple parents. The arc between the • concepts can be IS-A or PART-OF relations. • IOMG – Interactive schema matching algorithm. The first • step in this algorithm is to find Similarity Metrics. • Linguistic Similarity • Definition Similarity • Neighbor Similarity BioMedical Informatics

  22. Applications of Ontology • Randomized Clinical Trials (RCT) • Patient Records based on Clinical Trials. • Clinical Decision Systems. • ………….. BioMedical Informatics

  23. Randomized Clinical Trials (RCT) • Randomized Clinical Trails: one of the least biased • sources of clinical research evidence, and are therefore a • critical resource for the practice of evidence-based medicine • Scientific community is trying to encode the finding • in computer process able language. • However, for evidence to be put in practice one has to • analysis the data. The canonical practice for trial • interpretation is call System Reviewing. • Source for Data Specification: • Trial Reports • Trial Databases. BioMedical Informatics

  24. Life Cycle of Clinical Trials Ontology Specifications BioMedical Informatics

  25. RCT ontology specifications are obtained from: • Trial Reports • Trial Databases - ClinicalTrials.gov, PDQ etc. • The ontology is created by dividing the task into Sub- • Tasks and Methods. This recursive process is called • Competency Decomposition. • RCT decomposition methods combined Generic Tasks • and Competency Question. BioMedical Informatics

  26. RCT Schema Intervention -ARM ……. ……. • - Frames • 601 - Slots ……. ……. Administrative Concept TRAIL Outcome- Concept Excluded Population Population Analyzed Population Recruited Population BioMedical Informatics

  27. Matching Patient Records to Clinical Trials • Low participation in Clinical Trials is the major problem in • Clinical and translational research area. • Matching the patient records to clinical trials is presently a • manual procedure and its tedious. • Need a Semantic Bridge between Clinical Ontologies • (SNOMED CT, etc ..) and raw patient data for retrieving • matching patient records, clinical guidelines and clinical • decision support systems ( CDSS). BioMedical Informatics

  28. Technical Challenges • Challenges to be faced during real time scenario: • Knowledge Engineering. • Scalability • Noisy or Incomplete Data • Knowledge Engineering • Clinical Ontology has the concept “Drug”, which describe various active composition of the various drugs. However, patient record contains name of vendor-specific drugs list. BioMedical Informatics

  29. Clinical Ontology describe the cause of the disorder. The • patient records only specify the presence or absence of the • disorder and where was the clinical test conducted. • Scalability • The size of the knowledge base and the patient data are • very large. Can the reasoner handle such massive data. • Noisy or Incomplete Data • Clinical data is very inconsistent. But logical reasoners • acts on this data assuming it to be complete. BioMedical Informatics

  30. SNOMED-CT Patient Data Query TBox ABox Ontology Reasoner Architecture Clinical Trials BioMedical Informatics

  31. Solutions to the Challenges • Mapping Patient Data Terminology to SNOMED-CT • Using UMLS as intermediate target. • NLP mapping techniques • Manual Mapping • Map the raw patient data to SNOMED-CT terminology. • Example: Cerner Drug: Lactulose Syrup 20G/30ml • SNOMED-CT: administeredSubstance. • Allow user to specify which terms in the definition to • be matched. BioMedical Informatics

  32. Example: • SNOMED-CT: Disease1 • hasAgent Virus007 • Infection due to Bacteria001 • Infection due to MicroBacteria007 • Patient Record: Disease1 Positive. • As there is not much information in the patient • record the query reasoner cannot find the records • with partial data. BioMedical Informatics

  33. Sample Examples of above architecture ЭassociatedObservation MRSA ЭassociatedObservation Pneumococcal Penumonia П ЭhasSpecimanSource BloodЦSputum BioMedical Informatics

  34. Clinical Decision Support System • ClinicalDecision Support Systems (CDSS) are • interactive computer programs, which are designed to • assist physicians and other health professionals with • decision making tasks. • Components of CDSS: • Knowledge Base • Rule Based Engine • Case Base • Business Models BioMedical Informatics

  35. IF “ RULE 1” &“RULE 2” &“RULE 3” ….. “Rule n” THEN “INTERVENTION 1 or Rule M” IF p.getGender() = “male” & p.getAge()=34 & p.getBP() <140 & p.getInsulinLevel()<20 THEN “ Asthma Intervention Level 2” Class Patinet HasGender “male” ПhasAge“34” ПhasBPMoreThan140ПhasInsulinLevelMoreThan20 BioMedical Informatics

  36. Nursing COmputerDecision Support • The goal of NCODES is to provide a decision support • system for novice nurses. Feed Back Wireless LAN Inference Engine Expert/ Knowledge Sources Rules K E Knowledge Acquisition Knowledge Utilization and Representation BioMedical Informatics

  37. Presentation Layer User End Server Side Server End BioMedical Informatics

  38. High Speed wireless LAN and Handheld devices like • PDA constitute NCodes hardware. • The communication between the server and the PALM’s • is through wireless network. • Trying to in cooperate semantic knowledge base besides • the present database. The present database has rule and • information for Respiratory system. • Use SPARQL queries to retrieve the knowledge from the • ontology. • PREFIX URI: <http://www.owl-ontologies.com/Cardiology.owl#> • PREFIX RDFS: <http://www.w3.org/2000/01/rdf-schema#> • PREFIX OWL: <http://www.w3.org/2002/07/owl#> • PREFIX XSD: <http://www.w3.org/2001/XMLSchema#> • PREFIX RDF: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> • SELECT DISTINCT ?x "WHERE{?x URI:Have_Symptoms }". BioMedical Informatics

  39. Summary • Ontology • Definition and Descriptions. • Example. • Biomedical Ontology • Open Cyc • WordNet • GALEN • SNOMED - CT • Integration of Ontologies • Application of Biomedical Ontology • Clinical Trials. • OASIS: Integration Technique. • Clinical Decision Support System. BioMedical Informatics

  40. ? Questions “ The important thing is not to stop questioning. Curiosity has its own reason for existing.” BioMedical Informatics

More Related