{"id":{"repo_id":"queens","oai_identifier":"oai:queensu.scholaris.ca:1974/5293"},"canonical_url":"https://search.dev.ndltd.org/etd/queens/oai:queensu.scholaris.ca:1974/5293","repository":{"repo_id":"queens","name":"Queens University","base_url":"https://qspace.library.queensu.ca/server/oai/request"},"display":{"title":"Recognition of Severe Congestive Heart Failure using Parallel Cascade Identification","abstract":"In previous studies on heartbeat series, it has been proposed that the healthy heartbeat pattern represents complex nonlinear dynamics, and such cardiac nonlinearity may be used as a clinical indicator for the diagnosis of certain types of heart disease. However, it is still not quite clear whether there is any difference among the heartbeat series of patients with congestive heart failure (CHF), or whether cardiac nonlinearity represents a severe heart disease situation. In the present study, parallel cascade identification (PCI), which frequently requires only short stretches of data to obtain highly promising results, is used to distinguish severe congestive heart failure, a clinical situation associated with a high-risk of sudden death, from low-risk CHF. Parallel cascade identification is an accurate and robust method for identifying dynamic nonlinear systems. The PCI algorithm combined with a specified statistical test may be used as a severe congestive heart failure marker by comparing a nonlinear model with a “linear” model (more precisely, a first-order Volterra series). In this thesis, PCI is applied to distinguish R-R wave intervals of CHF patients who died from those of patients who survived in a 5-year study. The detection accuracy of the PCI detector is evaluated over a first set of 49 patients, and then over a larger set of a further 352 patients, and consistent results are obtained between the two sets. Over the larger set, Matthews' correlation coefficient of nonlinearity with unfavorable outcome (death) is , sensitivity for predicting unfavorable outcome is , while the specificity is . The R-R wave interval exhibits nonlinearity in patients who died during the 5-year study. However, typically nonlinearity cannot be detected in patients who survived during the study. These findings show that for patients with congestive heart failure, nonlinearity is associated with unfavorable outcome (death), while patients for whom nonlinearity cannot be detected overwhelmingly have good outcomes. This is significant for clinical diagnosis and prognosis of severe congestive heart failure.","abstract_html":"In previous studies on heartbeat series, it has been proposed that the healthy heartbeat pattern represents complex nonlinear dynamics, and such cardiac nonlinearity may be used as a clinical indicator for the diagnosis of certain types of heart disease. However, it is still not quite clear whether there is any difference among the heartbeat series of patients with congestive heart failure (CHF), or whether cardiac nonlinearity represents a severe heart disease situation. In the present study, parallel cascade identification (PCI), which frequently requires only short stretches of data to obtain highly promising results, is used to distinguish severe congestive heart failure, a clinical situation associated with a high-risk of sudden death, from low-risk CHF. Parallel cascade identification is an accurate and robust method for identifying dynamic nonlinear systems. The PCI algorithm combined with a specified statistical test may be used as a severe congestive heart failure marker by comparing a nonlinear model with a “linear” model (more precisely, a first-order Volterra series). In this thesis, PCI is applied to distinguish R-R wave intervals of CHF patients who died from those of patients who survived in a 5-year study. The detection accuracy of the PCI detector is evaluated over a first set of 49 patients, and then over a larger set of a further 352 patients, and consistent results are obtained between the two sets. Over the larger set, Matthews' correlation coefficient of nonlinearity with unfavorable outcome (death) is , sensitivity for predicting unfavorable outcome is , while the specificity is . The R-R wave interval exhibits nonlinearity in patients who died during the 5-year study. However, typically nonlinearity cannot be detected in patients who survived during the study. These findings show that for patients with congestive heart failure, nonlinearity is associated with unfavorable outcome (death), while patients for whom nonlinearity cannot be detected overwhelmingly have good outcomes. This is significant for clinical diagnosis and prognosis of severe congestive heart failure.","abstract_has_math":false,"creators":["Wu, Yi"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Korenberg, Michael J."],"committee_chairs":[],"committee_members":[],"year":2009,"date_issued":"2009-10-27T14:27:10Z","date_published":"2009-10-27T14:27:10Z","updated_at":"2026-07-27T20:35:23Z","subjects":["Congestive Heart Failure","Parallel Cascade Identification"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1974/5293","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:contributor.supervisor","label":"Supervisor","values":["Korenberg, Michael J."]},{"key":"dc:creator","label":"Author","values":["Wu, Yi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2007-09-28 11:54:57.695"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2009-10-27T14:27:10Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2009-10-27T14:27:10Z"]},{"key":"dc:date.issued","label":"Date","values":["2009-10-27T14:27:10Z"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Congestive Heart Failure","Parallel Cascade Identification"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1974/5293"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Master, Electrical & Computer Engineering) -- Queen's University, 2007-09-28 11:54:57.695"]},{"key":"dc:description.abstract","label":"Abstract","values":["In previous studies on heartbeat series, it has been proposed that the healthy heartbeat pattern represents complex nonlinear dynamics, and such cardiac nonlinearity may be used as a clinical indicator for the diagnosis of certain types of heart disease. However, it is still not quite clear whether there is any difference among the heartbeat series of patients with congestive heart failure (CHF), or whether cardiac nonlinearity represents a severe heart disease situation. In the present study, parallel cascade identification (PCI), which frequently requires only short stretches of data to obtain highly promising results, is used to distinguish severe congestive heart failure, a clinical situation associated with a high-risk of sudden death, from low-risk CHF. Parallel cascade identification is an accurate and robust method for identifying dynamic nonlinear systems. The PCI algorithm combined with a specified statistical test may be used as a severe congestive heart failure marker by comparing a nonlinear model with a “linear” model (more precisely, a first-order Volterra series). In this thesis, PCI is applied to distinguish R-R wave intervals of CHF patients who died from those of patients who survived in a 5-year study. The detection accuracy of the PCI detector is evaluated over a first set of 49 patients, and then over a larger set of a further 352 patients, and consistent results are obtained between the two sets. Over the larger set, Matthews' correlation coefficient of nonlinearity with unfavorable outcome (death) is , sensitivity for predicting unfavorable outcome is , while the specificity is . The R-R wave interval exhibits nonlinearity in patients who died during the 5-year study. However, typically nonlinearity cannot be detected in patients who survived during the study. These findings show that for patients with congestive heart failure, nonlinearity is associated with unfavorable outcome (death), while patients for whom nonlinearity cannot be detected overwhelmingly have good outcomes. This is significant for clinical diagnosis and prognosis of severe congestive heart failure."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Sc."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Recognition of Severe Congestive Heart Failure using Parallel Cascade Identification"]}]}],"canonical_facts":{"dc:contributor.department":["Electrical and Computer Engineering"],"dc:contributor.supervisor":["Korenberg, Michael J."],"dc:creator":["Wu, Yi"],"dc:date":["2007-09-28 11:54:57.695"],"dc:date.accessioned":["2009-10-27T14:27:10Z"],"dc:date.available":["2009-10-27T14:27:10Z"],"dc:date.issued":["2009-10-27T14:27:10Z"],"dc:description":["Thesis (Master, Electrical & Computer Engineering) -- Queen's University, 2007-09-28 11:54:57.695"],"dc:description.abstract":["In previous studies on heartbeat series, it has been proposed that the healthy heartbeat pattern represents complex nonlinear dynamics, and such cardiac nonlinearity may be used as a clinical indicator for the diagnosis of certain types of heart disease. However, it is still not quite clear whether there is any difference among the heartbeat series of patients with congestive heart failure (CHF), or whether cardiac nonlinearity represents a severe heart disease situation. In the present study, parallel cascade identification (PCI), which frequently requires only short stretches of data to obtain highly promising results, is used to distinguish severe congestive heart failure, a clinical situation associated with a high-risk of sudden death, from low-risk CHF. Parallel cascade identification is an accurate and robust method for identifying dynamic nonlinear systems. The PCI algorithm combined with a specified statistical test may be used as a severe congestive heart failure marker by comparing a nonlinear model with a “linear” model (more precisely, a first-order Volterra series). In this thesis, PCI is applied to distinguish R-R wave intervals of CHF patients who died from those of patients who survived in a 5-year study. The detection accuracy of the PCI detector is evaluated over a first set of 49 patients, and then over a larger set of a further 352 patients, and consistent results are obtained between the two sets. Over the larger set, Matthews' correlation coefficient of nonlinearity with unfavorable outcome (death) is , sensitivity for predicting unfavorable outcome is , while the specificity is . The R-R wave interval exhibits nonlinearity in patients who died during the 5-year study. However, typically nonlinearity cannot be detected in patients who survived during the study. These findings show that for patients with congestive heart failure, nonlinearity is associated with unfavorable outcome (death), while patients for whom nonlinearity cannot be detected overwhelmingly have good outcomes. This is significant for clinical diagnosis and prognosis of severe congestive heart failure."],"dc:description.degree":["M.Sc."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["http://hdl.handle.net/1974/5293"],"dc:language.iso":["eng"],"dc:subject":["Congestive Heart Failure","Parallel Cascade Identification"],"dc:title":["Recognition of Severe Congestive Heart Failure using Parallel Cascade Identification"],"dc:type":["thesis"]},"updated_at":"2026-07-27T20:35:23Z"}