{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/132474"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/132474","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Machine learning enhancements for wearable device investigation of acute anxiety and cardiovascular diseases","abstract":"Promoting well-being and healthy ageing in young adults increasingly hinges on detecting and managing conditions that silently erode quality of life, chief among them cardiovascular health and anxiety-related disorders. This dissertation advances both fields by developing data-driven methods that move clinical assessment from infrequent clinic visits to continuous, patient-centred monitoring. We address two persistent challenges: (i) identifying early autonomic markers of cardiovascular health before life-threatening damage occurs; and (ii) recognising context-specific surges in anxiety that impair daily functioning yet often escape formal diagnosis. By integrating multimodal wearable signals with modern machine-learning techniques, the work demonstrates how artificial intelligence can support clinicians in forecasting cardiovascular risk, delivering just-in-time interventions for anxiety, and ultimately fostering healthier, more independent ageing. This work proposes new data-driven machine learning-based solutions utilizing health data from multiple modalities, such as electrocardiography (ECG), blood volume pulse (BVP), electrodermal activity (EDA) etc. signals, to improve early disease prediction and progression in physical and mental health disorders. We measure our ability to use these signals to classify anomalies in the cardiovascular health and physiological body reactions in persons with disorders. This thesis is a multidisciplinary effort that involves novel combinations of sensors, audio, machine learning, biomechanics, and dynamical analyses to better characterize physiological signals from the body. These studies on the integration of AI and health data may provide a viable patient-centric approach to aid clinicians in designing novel AI-based disease prediction strategies and monitoring disease progression. This may help providers to individualize or generalize treatment plans and design improved clinical trials; thus, help reduce the skyrocketing healthcare costs in the future. The focus of this dissertation is on the following three areas under the broad umbrella of AI for digital healthcare: 1) Feature transformation for ECG signals so that we can get information about the cardiovascular risk in an automated settings, 2) Understanding the lab data collection for the mental health research settings i.e., anxiety and multimodal data analysis for the detection of state anxiety, where we focus on early- stage disease detection and propose feature engineering settings with machine learning models to identify physiological reactions for state anxiety, and 3) Transforming what we learned from the lab (controlled environment settings) to the daily life settings (uncontrolled environment settings) through wearable devices.","abstract_html":"Promoting well-being and healthy ageing in young adults increasingly hinges on detecting and managing conditions that silently erode quality of life, chief among them cardiovascular health and anxiety-related disorders. This dissertation advances both fields by developing data-driven methods that move clinical assessment from infrequent clinic visits to continuous, patient-centred monitoring. We address two persistent challenges: (i) identifying early autonomic markers of cardiovascular health before life-threatening damage occurs; and (ii) recognising context-specific surges in anxiety that impair daily functioning yet often escape formal diagnosis. By integrating multimodal wearable signals with modern machine-learning techniques, the work demonstrates how artificial intelligence can support clinicians in forecasting cardiovascular risk, delivering just-in-time interventions for anxiety, and ultimately fostering healthier, more independent ageing. This work proposes new data-driven machine learning-based solutions utilizing health data from multiple modalities, such as electrocardiography (ECG), blood volume pulse (BVP), electrodermal activity (EDA) etc. signals, to improve early disease prediction and progression in physical and mental health disorders. We measure our ability to use these signals to classify anomalies in the cardiovascular health and physiological body reactions in persons with disorders. This thesis is a multidisciplinary effort that involves novel combinations of sensors, audio, machine learning, biomechanics, and dynamical analyses to better characterize physiological signals from the body. These studies on the integration of AI and health data may provide a viable patient-centric approach to aid clinicians in designing novel AI-based disease prediction strategies and monitoring disease progression. This may help providers to individualize or generalize treatment plans and design improved clinical trials; thus, help reduce the skyrocketing healthcare costs in the future. The focus of this dissertation is on the following three areas under the broad umbrella of AI for digital healthcare: 1) Feature transformation for ECG signals so that we can get information about the cardiovascular risk in an automated settings, 2) Understanding the lab data collection for the mental health research settings i.e., anxiety and multimodal data analysis for the detection of state anxiety, where we focus on early- stage disease detection and propose feature engineering settings with machine learning models to identify physiological reactions for state anxiety, and 3) Transforming what we learned from the lab (controlled environment settings) to the daily life settings (uncontrolled environment settings) through wearable devices.","abstract_has_math":false,"creators":["Dogan, Ayse"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Industrial Engineering","degree_department":null,"school":null,"contributors":["Sowers, Richard B.","Hernandez, Manuel E.","Cao, Caroline","Sreenivas, Ramavarapu S."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-22T22:25:07Z","subjects":["wearable devices, signal processing, digital phenotyping, label generation, ECG"],"languages":["en"],"rights":["Copyright 2025 Ayse Dogan"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/132474","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sowers, Richard B.","Hernandez, Manuel E.","Cao, Caroline","Sreenivas, Ramavarapu S."]},{"key":"dc:creator","label":"Author","values":["Dogan, Ayse"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12","2025-10-27"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Industrial Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["wearable devices, signal processing, digital phenotyping, label generation, ECG"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Ayse Dogan"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/132474"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Promoting well-being and healthy ageing in young adults increasingly hinges on detecting and managing conditions that silently erode quality of life, chief among them cardiovascular health and anxiety-related disorders. This dissertation advances both fields by developing data-driven methods that move clinical assessment from infrequent clinic visits to continuous, patient-centred monitoring. We address two persistent challenges: (i) identifying early autonomic markers of cardiovascular health before life-threatening damage occurs; and (ii) recognising context-specific surges in anxiety that impair daily functioning yet often escape formal diagnosis. By integrating multimodal wearable signals with modern machine-learning techniques, the work demonstrates how artificial intelligence can support clinicians in forecasting cardiovascular risk, delivering just-in-time interventions for anxiety, and ultimately fostering healthier, more independent ageing. This work proposes new data-driven machine learning-based solutions utilizing health data from multiple modalities, such as electrocardiography (ECG), blood volume pulse (BVP), electrodermal activity (EDA) etc. signals, to improve early disease prediction and progression in physical and mental health disorders. We measure our ability to use these signals to classify anomalies in the cardiovascular health and physiological body reactions in persons with disorders. This thesis is a multidisciplinary effort that involves novel combinations of sensors, audio, machine learning, biomechanics, and dynamical analyses to better characterize physiological signals from the body. These studies on the integration of AI and health data may provide a viable patient-centric approach to aid clinicians in designing novel AI-based disease prediction strategies and monitoring disease progression. This may help providers to individualize or generalize treatment plans and design improved clinical trials; thus, help reduce the skyrocketing healthcare costs in the future. The focus of this dissertation is on the following three areas under the broad umbrella of AI for digital healthcare: 1) Feature transformation for ECG signals so that we can get information about the cardiovascular risk in an automated settings, 2) Understanding the lab data collection for the mental health research settings i.e., anxiety and multimodal data analysis for the detection of state anxiety, where we focus on early- stage disease detection and propose feature engineering settings with machine learning models to identify physiological reactions for state anxiety, and 3) Transforming what we learned from the lab (controlled environment settings) to the daily life settings (uncontrolled environment settings) through wearable devices.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms","The student, Ayse Dogan, accepted the attached license on 2025-10-24 at 10:36.","The student, Ayse Dogan, submitted this Dissertation for approval on 2025-10-24 at 10:46.","This Dissertation was approved for publication on 2025-10-27 at 13:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22830 on 2026-02-19 at 18:24:26"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Machine learning enhancements for wearable device investigation of acute anxiety and cardiovascular diseases"]}]}],"canonical_facts":{"dc:contributor":["Sowers, Richard B.","Hernandez, Manuel E.","Cao, Caroline","Sreenivas, Ramavarapu S."],"dc:creator":["Dogan, Ayse"],"dc:date":["2025-12","2025-10-27"],"dc:description":["Promoting well-being and healthy ageing in young adults increasingly hinges on detecting and managing conditions that silently erode quality of life, chief among them cardiovascular health and anxiety-related disorders. This dissertation advances both fields by developing data-driven methods that move clinical assessment from infrequent clinic visits to continuous, patient-centred monitoring. We address two persistent challenges: (i) identifying early autonomic markers of cardiovascular health before life-threatening damage occurs; and (ii) recognising context-specific surges in anxiety that impair daily functioning yet often escape formal diagnosis. By integrating multimodal wearable signals with modern machine-learning techniques, the work demonstrates how artificial intelligence can support clinicians in forecasting cardiovascular risk, delivering just-in-time interventions for anxiety, and ultimately fostering healthier, more independent ageing. This work proposes new data-driven machine learning-based solutions utilizing health data from multiple modalities, such as electrocardiography (ECG), blood volume pulse (BVP), electrodermal activity (EDA) etc. signals, to improve early disease prediction and progression in physical and mental health disorders. We measure our ability to use these signals to classify anomalies in the cardiovascular health and physiological body reactions in persons with disorders. This thesis is a multidisciplinary effort that involves novel combinations of sensors, audio, machine learning, biomechanics, and dynamical analyses to better characterize physiological signals from the body. These studies on the integration of AI and health data may provide a viable patient-centric approach to aid clinicians in designing novel AI-based disease prediction strategies and monitoring disease progression. This may help providers to individualize or generalize treatment plans and design improved clinical trials; thus, help reduce the skyrocketing healthcare costs in the future. The focus of this dissertation is on the following three areas under the broad umbrella of AI for digital healthcare: 1) Feature transformation for ECG signals so that we can get information about the cardiovascular risk in an automated settings, 2) Understanding the lab data collection for the mental health research settings i.e., anxiety and multimodal data analysis for the detection of state anxiety, where we focus on early- stage disease detection and propose feature engineering settings with machine learning models to identify physiological reactions for state anxiety, and 3) Transforming what we learned from the lab (controlled environment settings) to the daily life settings (uncontrolled environment settings) through wearable devices.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms","The student, Ayse Dogan, accepted the attached license on 2025-10-24 at 10:36.","The student, Ayse Dogan, submitted this Dissertation for approval on 2025-10-24 at 10:46.","This Dissertation was approved for publication on 2025-10-27 at 13:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22830 on 2026-02-19 at 18:24:26"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/132474"],"dc:language":["en"],"dc:rights":["Copyright 2025 Ayse Dogan"],"dc:subject":["wearable devices, signal processing, digital phenotyping, label generation, ECG"],"dc:title":["Machine learning enhancements for wearable device investigation of acute anxiety and cardiovascular diseases"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Industrial Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:07Z"}