{"id":{"repo_id":"csusb","oai_identifier":"oai:scholarworks.lib.csusb.edu:etd-3438"},"canonical_url":"https://search.ndltd.org/etd/csusb/oai:scholarworks.lib.csusb.edu:etd-3438","repository":{"repo_id":"csusb","name":"CSUniversity San Bernardino","base_url":"https://scholarworks.lib.csusb.edu/do/oai/"},"display":{"title":"EXPLAINABLE AI (XAI) FOR A MACHINE LEARNING HEART DISEASE PREDICTION MODEL","abstract":"Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, decision trees, support vector machines (SVM) (Cortes & Vapnik, 1995), and deep learning models (LeCun et al., 2015) have demonstrated high predictive accuracy, their adoption in clinical practice is hindered by their black-box nature (Rudin, 2019). Explainable AI (XAI) techniques, including SHapley Additive Explanations (SHAP) (Lundberg & Lee, 2017), Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro et al., 2016), and feature importance analysis aim to bridge this gap by improving model transparency and interpretability (Doshi-Velez & Kim, 2017). This study explores the effectiveness of various ML algorithms for heart disease prediction and examines how XAI techniques enhance their interpretability. Furthermore, it investigates the role of model transparency in influencing clinician trust and adoption of AI-based diagnostics. Research indicates that interpretable AI models foster greater trust among healthcare professionals, as they align with established medical knowledge and facilitate informed decision-making. Despite these benefits, challenges such as computational complexity, trade-offs between accuracy and interpretability, and ethical concerns regarding patient data privacy persist. The findings highlight the necessity of integrating XAI techniques into ML models to ensure high accuracy and transparency in heart disease prediction. By addressing existing challenges, AI-driven diagnostics can be effectively incorporated into clinical workflows, ultimately improving patient outcomes and supporting evidence-based medical decision-making.","abstract_html":"Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, decision trees, support vector machines (SVM) (Cortes &amp; Vapnik, 1995), and deep learning models (LeCun et al., 2015) have demonstrated high predictive accuracy, their adoption in clinical practice is hindered by their black-box nature (Rudin, 2019). Explainable AI (XAI) techniques, including SHapley Additive Explanations (SHAP) (Lundberg &amp; Lee, 2017), Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro et al., 2016), and feature importance analysis aim to bridge this gap by improving model transparency and interpretability (Doshi-Velez &amp; Kim, 2017). This study explores the effectiveness of various ML algorithms for heart disease prediction and examines how XAI techniques enhance their interpretability. Furthermore, it investigates the role of model transparency in influencing clinician trust and adoption of AI-based diagnostics. Research indicates that interpretable AI models foster greater trust among healthcare professionals, as they align with established medical knowledge and facilitate informed decision-making. Despite these benefits, challenges such as computational complexity, trade-offs between accuracy and interpretability, and ethical concerns regarding patient data privacy persist. The findings highlight the necessity of integrating XAI techniques into ML models to ensure high accuracy and transparency in heart disease prediction. By addressing existing challenges, AI-driven diagnostics can be effectively incorporated into clinical workflows, ultimately improving patient outcomes and supporting evidence-based medical decision-making.","abstract_has_math":false,"creators":["Sanchula, Sai Abhishek"],"institution":null,"degree_name":"Master of Science in Information Systems and Technology","degree_level":"Thesis","degree_discipline":"Information and Decision Sciences","degree_department":null,"school":null,"contributors":["Dr. Conrad Shayo"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:10:04Z","subjects":["Heart Disease Prediction","Explainable AI (XAI)","Machine Learning","Cardiovascular Diseases","Data Science","Health Information Technology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://scholarworks.lib.csusb.edu/etd/2241","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://scholarworks.lib.csusb.edu/etd/2241","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://scholarworks.lib.csusb.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ascholarworks.lib.csusb.edu%3Aetd-3438","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Conrad Shayo"]},{"key":"dc:creator","label":"Author","values":["Sanchula, Sai Abhishek"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-14T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-05-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Information and Decision Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Information Systems and Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Heart Disease Prediction","Explainable AI (XAI)","Machine Learning","Cardiovascular Diseases","Data Science","Health Information Technology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarworks.lib.csusb.edu/etd/2241"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, decision trees, support vector machines (SVM) (Cortes & Vapnik, 1995), and deep learning models (LeCun et al., 2015) have demonstrated high predictive accuracy, their adoption in clinical practice is hindered by their black-box nature (Rudin, 2019). Explainable AI (XAI) techniques, including SHapley Additive Explanations (SHAP) (Lundberg & Lee, 2017), Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro et al., 2016), and feature importance analysis aim to bridge this gap by improving model transparency and interpretability (Doshi-Velez & Kim, 2017). This study explores the effectiveness of various ML algorithms for heart disease prediction and examines how XAI techniques enhance their interpretability. Furthermore, it investigates the role of model transparency in influencing clinician trust and adoption of AI-based diagnostics. Research indicates that interpretable AI models foster greater trust among healthcare professionals, as they align with established medical knowledge and facilitate informed decision-making. Despite these benefits, challenges such as computational complexity, trade-offs between accuracy and interpretability, and ethical concerns regarding patient data privacy persist. The findings highlight the necessity of integrating XAI techniques into ML models to ensure high accuracy and transparency in heart disease prediction. By addressing existing challenges, AI-driven diagnostics can be effectively incorporated into clinical workflows, ultimately improving patient outcomes and supporting evidence-based medical decision-making."]},{"key":"dc:title","label":"Title","values":["EXPLAINABLE AI (XAI) FOR A MACHINE LEARNING HEART DISEASE PREDICTION MODEL"]}]}],"canonical_facts":{"dc:contributor":["Dr. Conrad Shayo"],"dc:creator":["Sanchula, Sai Abhishek"],"dc:date.available":["2025-04-14T07:00:00Z"],"dc:date.created":["2025-05-01T07:00:00Z"],"dc:description.abstract":["Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, decision trees, support vector machines (SVM) (Cortes & Vapnik, 1995), and deep learning models (LeCun et al., 2015) have demonstrated high predictive accuracy, their adoption in clinical practice is hindered by their black-box nature (Rudin, 2019). Explainable AI (XAI) techniques, including SHapley Additive Explanations (SHAP) (Lundberg & Lee, 2017), Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro et al., 2016), and feature importance analysis aim to bridge this gap by improving model transparency and interpretability (Doshi-Velez & Kim, 2017). This study explores the effectiveness of various ML algorithms for heart disease prediction and examines how XAI techniques enhance their interpretability. Furthermore, it investigates the role of model transparency in influencing clinician trust and adoption of AI-based diagnostics. Research indicates that interpretable AI models foster greater trust among healthcare professionals, as they align with established medical knowledge and facilitate informed decision-making. Despite these benefits, challenges such as computational complexity, trade-offs between accuracy and interpretability, and ethical concerns regarding patient data privacy persist. The findings highlight the necessity of integrating XAI techniques into ML models to ensure high accuracy and transparency in heart disease prediction. By addressing existing challenges, AI-driven diagnostics can be effectively incorporated into clinical workflows, ultimately improving patient outcomes and supporting evidence-based medical decision-making."],"dc:identifier":["https://scholarworks.lib.csusb.edu/etd/2241"],"dc:subject":["Heart Disease Prediction","Explainable AI (XAI)","Machine Learning","Cardiovascular Diseases","Data Science","Health Information Technology"],"dc:title":["EXPLAINABLE AI (XAI) FOR A MACHINE LEARNING HEART DISEASE PREDICTION MODEL"],"thesis:degree_discipline":["Information and Decision Sciences"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science in Information Systems and Technology"]},"updated_at":"2026-11-19T08:10:04Z"}