Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/30043
DC FieldValueLanguage
dc.contributor.authorPrentzas, Nicoletta-
dc.contributor.authorPitsiali, Marios-
dc.contributor.authorKyriacou, Efthyvoulos C.-
dc.contributor.authorNicolaides, Andrew N.-
dc.contributor.authorKakas, Antonis-
dc.contributor.authorPattichis, Constantinos S.-
dc.date.accessioned2023-08-03T06:04:50Z-
dc.date.available2023-08-03T06:04:50Z-
dc.date.issued2021-10-25-
dc.identifier.citation21st IEEE International Conference on BioInformatics and BioEngineering, BIBE 2021, Kragujevac, 25 - 27 October 2021en_US
dc.identifier.isbn9781665442619-
dc.identifier.urihttps://hdl.handle.net/20.500.14279/30043-
dc.description.abstractThe current adoption of Medical Artificial Intelligence (AI) solutions in clinical practice suggest that despite its undeniable potential AI is not achieving this potential. A major barrier to its adoption is the lack of transparency and interpretability, and the inability of the system to explain its results. Explainable AI (XAI) is an emerging field in AI that aims to address these barriers, with the development of new or modified algorithms to enable transparency, provide explanations in a way that humans can understand and foster trust. Numerous XAI techniques have been proposed in the literature, commonly classified as model-agnostic or model-specific. In this study, we examine the application of four model-agnostic XAI techniques (LIME, SHAP, ANCHORS, inTrees) to an XGBoost classifier trained on real-life medical data for the prediction of high-risk asymptomatic carotid plaques based on ultrasound image analysis. We present and compare local explanations for selected observations in the test set. We also present global explanations generated from these techniques that explain the behavior of the entire model. Additionally, we assess the quality of the explanations, using suggested properties in the literature. Finally, we discuss the results of this comparative study and suggest directions for future work.en_US
dc.language.isoenen_US
dc.rights© IEEEen_US
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectANCHORsen_US
dc.subjectexplainable AIen_US
dc.subjectinTreesen_US
dc.subjectLIMEen_US
dc.subjectmodel-agnostic explain abilityen_US
dc.subjectSHAPen_US
dc.titleModel Agnostic Explainability Techniques in Ultrasound Image Analysisen_US
dc.typeConference Papersen_US
dc.collaborationUniversity of Cyprusen_US
dc.collaborationFrederick Universityen_US
dc.collaborationVascular Screening and Diagnostic Centreen_US
dc.subject.categoryElectrical Engineering - Electronic Engineering - Information Engineeringen_US
dc.countryCyprusen_US
dc.subject.fieldEngineering and Technologyen_US
dc.relation.conferenceBIBE 2021 - 21st IEEE International Conference on BioInformatics and BioEngineeringen_US
dc.identifier.doi10.1109/BIBE52308.2021.9635199en_US
dc.identifier.scopus2-s2.0-85123720821-
dc.identifier.urlhttps://api.elsevier.com/content/abstract/scopus_id/85123720821-
cut.common.academicyear2021-2022en_US
item.fulltextNo Fulltext-
item.languageiso639-1en-
item.grantfulltextnone-
item.openairecristypehttp://purl.org/coar/resource_type/c_c94f-
item.cerifentitytypePublications-
item.openairetypeconferenceObject-
crisitem.author.deptDepartment of Electrical Engineering, Computer Engineering and Informatics-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.orcid0000-0002-4589-519X-
crisitem.author.parentorgFaculty of Engineering and Technology-
Appears in Collections:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation
CORE Recommender
Show simple item record

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons