This work constitutes six projects. In the first project, a newly inaugurated research database for 12-lead electrocardiogram signals was created under the auspices of Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine). This database aims to enable the scientific community in conducting new studies on arrhythmia and other cardiovascular conditions. In the second project, we created a new 12-lead ECG database under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University that aims to provide high quality data enabling detection of the distinctions between idiopathic ventricular arrhythmia from right ventricular outflow tract to left ventricular outflow tract. In the third project, Principle Component Analysis (PCA) application in classification problem was studied. PCA is a commonly used technique to reduce dimensions of the data through analyzing correlation structure of the original variables. This reduction is achieved by considering only the first few principal components for a subsequent analysis. We conclude that the exclusion of any principal components should be carefully investigated. In the fourth project, we have jointly optimized the entire multi-stage arrhythmia classification scheme based on 12-lead surface ECGs that attains the accuracy performance level of professional cardiologists. Our results show that the optimal approach achieved an F_1-Score of 0.988 on patients without additional cardiac conditions. In the fifth project, we trained a multi-stage artificial intelligence algorithm to classify right ventricular outflow tract or left ventricular outflow tract origins ventricular tachycardia. Under 100-time cross-validation, the proposed approach achieved an average F1-Score 0.97, accuracy 0.97, and area under curve 0.99, and predicted a right ventricular outflow tract origin with sensitivity 0.96, specificity 0.97, positive predictive value 0.99, and negative predictive value 0.89 respectively. In the sixth project, we designed four classification schemes responding to different hierarchical levels of the possible idiopathic ventricular arrhythmia (VA) origins. Our pioneering study designs and implements an artificial intelligence-based ECG algorithm to predict 21 possible sites of idiopathic ventricular arrhythmia origin with an accuracy of 98.24% on a testing cohort.
","abstract_html":"<p>This work constitutes six projects. In the first project, a newly inaugurated research database for 12-lead electrocardiogram signals was created under the auspices of Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine). This database aims to enable the scientific community in conducting new studies on arrhythmia and other cardiovascular conditions. In the second project, we created a new 12-lead ECG database under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University that aims to provide high quality data enabling detection of the distinctions between idiopathic ventricular arrhythmia from right ventricular outflow tract to left ventricular outflow tract. In the third project, Principle Component Analysis (PCA) application in classification problem was studied. PCA is a commonly used technique to reduce dimensions of the data through analyzing correlation structure of the original variables. This reduction is achieved by considering only the first few principal components for a subsequent analysis. We conclude that the exclusion of any principal components should be carefully investigated. In the fourth project, we have jointly optimized the entire multi-stage arrhythmia classification scheme based on 12-lead surface ECGs that attains the accuracy performance level of professional cardiologists. Our results show that the optimal approach achieved an F_1-Score of 0.988 on patients without additional cardiac conditions. In the fifth project, we trained a multi-stage artificial intelligence algorithm to classify right ventricular outflow tract or left ventricular outflow tract origins ventricular tachycardia. Under 100-time cross-validation, the proposed approach achieved an average F1-Score 0.97, accuracy 0.97, and area under curve 0.99, and predicted a right ventricular outflow tract origin with sensitivity 0.96, specificity 0.97, positive predictive value 0.99, and negative predictive value 0.89 respectively. In the sixth project, we designed four classification schemes responding to different hierarchical levels of the possible idiopathic ventricular arrhythmia (VA) origins. Our pioneering study designs and implements an artificial intelligence-based ECG algorithm to predict 21 possible sites of idiopathic ventricular arrhythmia origin with an accuracy of 98.24% on a testing cohort.</p>","abstract_has_math":false,"creators":["Zheng, Jianwei"],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computational and Data Sciences","degree_department":null,"school":null,"contributors":["Cyril Rakovski","Daniele Struppa","Islam Abudayyeh","Magdi Yacoub, Hesham El-Askary"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-05-01T07:00:00Z","date_published":"2021-05-01T07:00:00Z","updated_at":"2026-07-24T01:38:16Z","subjects":["Arrhythmia","ECG","Machine Learning","Ventricular Arrhythmia Origins","Artificial Intelligence","PCA","Biomedical Engineering and Bioengineering","Cardiovascular Diseases","Data Science","Diagnosis","Investigative Techniques","Numerical Analysis and Computation"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.chapman.edu/cads_dissertations/21","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Cyril Rakovski","Daniele Struppa","Islam Abudayyeh","Magdi Yacoub, Hesham El-Askary"]},{"key":"dc:creator","label":"Author","values":["Zheng, Jianwei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2023-05-17T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computational and Data Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Arrhythmia","ECG","Machine Learning","Ventricular Arrhythmia Origins","Artificial Intelligence","PCA","Biomedical Engineering and Bioengineering","Cardiovascular Diseases","Data Science","Diagnosis","Investigative Techniques","Numerical Analysis and Computation"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.chapman.edu/cads_dissertations/21"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This work constitutes six projects. In the first project, a newly inaugurated research database for 12-lead electrocardiogram signals was created under the auspices of Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine). This database aims to enable the scientific community in conducting new studies on arrhythmia and other cardiovascular conditions. In the second project, we created a new 12-lead ECG database under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University that aims to provide high quality data enabling detection of the distinctions between idiopathic ventricular arrhythmia from right ventricular outflow tract to left ventricular outflow tract. In the third project, Principle Component Analysis (PCA) application in classification problem was studied. PCA is a commonly used technique to reduce dimensions of the data through analyzing correlation structure of the original variables. This reduction is achieved by considering only the first few principal components for a subsequent analysis. We conclude that the exclusion of any principal components should be carefully investigated. In the fourth project, we have jointly optimized the entire multi-stage arrhythmia classification scheme based on 12-lead surface ECGs that attains the accuracy performance level of professional cardiologists. Our results show that the optimal approach achieved an F_1-Score of 0.988 on patients without additional cardiac conditions. In the fifth project, we trained a multi-stage artificial intelligence algorithm to classify right ventricular outflow tract or left ventricular outflow tract origins ventricular tachycardia. Under 100-time cross-validation, the proposed approach achieved an average F1-Score 0.97, accuracy 0.97, and area under curve 0.99, and predicted a right ventricular outflow tract origin with sensitivity 0.96, specificity 0.97, positive predictive value 0.99, and negative predictive value 0.89 respectively. In the sixth project, we designed four classification schemes responding to different hierarchical levels of the possible idiopathic ventricular arrhythmia (VA) origins. Our pioneering study designs and implements an artificial intelligence-based ECG algorithm to predict 21 possible sites of idiopathic ventricular arrhythmia origin with an accuracy of 98.24% on a testing cohort.
"]},{"key":"dc:source","label":"Dc Source","values":["J. Zheng, \"Optimal analytical methods for high accuracy cardiac disease classification and treatment based on ECG data,\" Ph.D. dissertation, Chapman University, Orange, CA, 2021. https://doi.org/10.36837/chapman.000281"]},{"key":"dc:title","label":"Title","values":["Optimal Analytical Methods for High Accuracy Cardiac Disease Classification and Treatment Based on ECG Data"]}]}],"canonical_facts":{"dc:contributor":["Cyril Rakovski","Daniele Struppa","Islam Abudayyeh","Magdi Yacoub, Hesham El-Askary"],"dc:creator":["Zheng, Jianwei"],"dc:date.available":["2023-05-17T07:00:00Z"],"dc:description.abstract":["This work constitutes six projects. In the first project, a newly inaugurated research database for 12-lead electrocardiogram signals was created under the auspices of Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine). This database aims to enable the scientific community in conducting new studies on arrhythmia and other cardiovascular conditions. In the second project, we created a new 12-lead ECG database under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University that aims to provide high quality data enabling detection of the distinctions between idiopathic ventricular arrhythmia from right ventricular outflow tract to left ventricular outflow tract. In the third project, Principle Component Analysis (PCA) application in classification problem was studied. PCA is a commonly used technique to reduce dimensions of the data through analyzing correlation structure of the original variables. This reduction is achieved by considering only the first few principal components for a subsequent analysis. We conclude that the exclusion of any principal components should be carefully investigated. In the fourth project, we have jointly optimized the entire multi-stage arrhythmia classification scheme based on 12-lead surface ECGs that attains the accuracy performance level of professional cardiologists. Our results show that the optimal approach achieved an F_1-Score of 0.988 on patients without additional cardiac conditions. In the fifth project, we trained a multi-stage artificial intelligence algorithm to classify right ventricular outflow tract or left ventricular outflow tract origins ventricular tachycardia. Under 100-time cross-validation, the proposed approach achieved an average F1-Score 0.97, accuracy 0.97, and area under curve 0.99, and predicted a right ventricular outflow tract origin with sensitivity 0.96, specificity 0.97, positive predictive value 0.99, and negative predictive value 0.89 respectively. In the sixth project, we designed four classification schemes responding to different hierarchical levels of the possible idiopathic ventricular arrhythmia (VA) origins. Our pioneering study designs and implements an artificial intelligence-based ECG algorithm to predict 21 possible sites of idiopathic ventricular arrhythmia origin with an accuracy of 98.24% on a testing cohort.
"],"dc:identifier":["https://digitalcommons.chapman.edu/cads_dissertations/21"],"dc:source":["J. Zheng, \"Optimal analytical methods for high accuracy cardiac disease classification and treatment based on ECG data,\" Ph.D. dissertation, Chapman University, Orange, CA, 2021. https://doi.org/10.36837/chapman.000281"],"dc:subject":["Arrhythmia","ECG","Machine Learning","Ventricular Arrhythmia Origins","Artificial Intelligence","PCA","Biomedical Engineering and Bioengineering","Cardiovascular Diseases","Data Science","Diagnosis","Investigative Techniques","Numerical Analysis and Computation"],"dc:title":["Optimal Analytical Methods for High Accuracy Cardiac Disease Classification and Treatment Based on ECG Data"],"thesis:degree_discipline":["Computational and Data Sciences"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T01:38:16Z"}