dc.contributor.author | Nair, Aditi | |
dc.date.accessioned | 2020-08-26T17:11:55Z | |
dc.date.available | 2020-08-26T17:11:55Z | |
dc.date.issued | 2020-08-26T17:11:55Z | |
dc.identifier.uri | http://hdl.handle.net/10222/79722 | |
dc.description.abstract | Cognitive Behavioural Therapy (CBT) is an action-oriented psychotherapy that uses a combination of cognitive and behavioural techniques—i.e. guided discovery and behavioural activation—as a psychosocial treatment for depression. CBT intervention is considered complex since it includes multiple components that need to be personalized to the patient’s beliefs, barriers, lifestyle and expected outcomes. CBT has been computerized to assist therapists develop CBT action plans for mild to moderate depression. However, most computerized CBT initiatives do not include a patient-centered and evidence-based CBT personalization component.
In this thesis, we take a knowledge management approach to semantically model the core CBT concepts and their relationships in terms of an ontological CBT knowledge model that can be reasoned over, with patient data, to generate personalized action plans for treating mild depression. We synthesized and computerized CBT knowledge from multiple sources in terms of the CBT ontology that was validated by a domain expert. We have developed an OWL based CBT ontology and a number of logic-based action plan personalization rules using Semantic Web Rule Language (SWRL). Using the CBT ontology and logical rules, we operationalized the guided discovery process such that a therapist working with a patient can systematically identify the negative thought processes that lead to depression, and can then apply behavioural activation principles to recommend personalized CBT action plans to alleviate mild depression. We developed a two-tiered personalized CBT action planning approach using logical reasoning to personalize a CBT action plan, whereby at the first level we infer the relevant patient profile attributes and at the second level we infer the most effective action plans for a specific patient. We performed a formative evaluation of the CBT ontology in terms of its completeness, consistency, and conciseness. Case-studies are presented to demonstrate the working of our personalized CBT action planning for treating mild depression. | en_US |
dc.language.iso | en | en_US |
dc.subject | ontology | en_US |
dc.subject | knowledge modelling | en_US |
dc.subject | ontological reasoning | en_US |
dc.subject | cognitive behavioural therapy | en_US |
dc.title | SEMANTIC WEB-BASED REPRESENTATION OF COGNITIVE BEHAVIOURAL THERAPY: APPLYING ONTOLOGICAL KNOWLEDGE MODELLING AND REASONING TO GENERATE PERSONALIZED BEHAVIOURAL PLANS FOR THE TREATMENT OF MILD DEPRESSION | en_US |
dc.date.defence | 2020-08-04 | |
dc.contributor.department | Faculty of Computer Science | en_US |
dc.contributor.degree | Master of Computer Science | en_US |
dc.contributor.external-examiner | n/a | en_US |
dc.contributor.graduate-coordinator | Dr. Michael McAllister | en_US |
dc.contributor.thesis-reader | Dr. Nur Zincir-Heywood | en_US |
dc.contributor.thesis-reader | Dr. William Van Woensel | en_US |
dc.contributor.thesis-supervisor | Dr. Samina Abidi | en_US |
dc.contributor.thesis-supervisor | Dr. Syed Sibte Raza Abidi | en_US |
dc.contributor.ethics-approval | Not Applicable | en_US |
dc.contributor.manuscripts | Not Applicable | en_US |
dc.contributor.copyright-release | Not Applicable | en_US |