{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/18287"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/18287","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"AI Approaches for Feature Extraction in Multimodal Biomedical Data","abstract":"Artificial intelligence (AI) has myriad applications for biomedical engineering and healthcare. In particular, with the diverse modalities and high resolution of physiological data, the potential for data-driven approaches to elucidate meaningful insights is enormous. However, the enormity and profundity of this data is also a hindrance. AI approaches can fail to learn due to "feature dilution", where a model is overloaded with data points, and spurious or noisy features prevent it from successfully aligning to and converging on semantic or predictive features in the dataset. Traditional methods of feature extraction either rely on manual physiological inference or leverage pre-trained AI models for well-characterized applications. We posit that AI itself can be leveraged to augment feature identification through the exploitation of learned representations and intelligent processes. To address this problem, we present three approaches for the application of artificial intelligence to the task of feature extraction in three different modes of biomedical data: 1. AxoDetect (AD), a complete image-to-model software pipeline for in silico nerve stimulation using computer vision (CV); 2. Probability Gradient Thresholding (PGT), a deep learning-based dynamic time window extraction method for the identification of neuronal compound action potential (CAP) spikes from neuronal recordings; and 3. Latent Semantic Atom Analysis (LSAA), a hybrid approach using Matching Pursuit (MP) and DeepSets (DS) to learn patient-specific representations of atherosclerosis in the coronary arteries from human heart sound data. AxoDetect excels at segmenting nerves without requiring labeled datasets, segmenting between ten to one hundred times faster than similar deep learning methods. The models which are functionalized and constructed by the software have statistically indistinguishable results when compared to the gold standard modeling methods (Wilcoxon followed by MWU with Bonferroni correction). A combined RNN-LSTM approach to PGT was able to achieve over 95% point-wise accuracy on the testing set in identifying a data point's belonging to a neuronal spike on in silico recordings. Finally, using LSAA we can not only predict presence or absence of cardiac stent with high accuracy (88% on the test set, 94\\% on the full dataset), we can isolate and cluster semantic groups of atoms representing cardiac occlusion.","abstract_html":"Artificial intelligence (AI) has myriad applications for biomedical engineering and healthcare. In particular, with the diverse modalities and high resolution of physiological data, the potential for data-driven approaches to elucidate meaningful insights is enormous. However, the enormity and profundity of this data is also a hindrance. AI approaches can fail to learn due to "feature dilution", where a model is overloaded with data points, and spurious or noisy features prevent it from successfully aligning to and converging on semantic or predictive features in the dataset. Traditional methods of feature extraction either rely on manual physiological inference or leverage pre-trained AI models for well-characterized applications. We posit that AI itself can be leveraged to augment feature identification through the exploitation of learned representations and intelligent processes. To address this problem, we present three approaches for the application of artificial intelligence to the task of feature extraction in three different modes of biomedical data: 1. AxoDetect (AD), a complete image-to-model software pipeline for in silico nerve stimulation using computer vision (CV); 2. Probability Gradient Thresholding (PGT), a deep learning-based dynamic time window extraction method for the identification of neuronal compound action potential (CAP) spikes from neuronal recordings; and 3. Latent Semantic Atom Analysis (LSAA), a hybrid approach using Matching Pursuit (MP) and DeepSets (DS) to learn patient-specific representations of atherosclerosis in the coronary arteries from human heart sound data. AxoDetect excels at segmenting nerves without requiring labeled datasets, segmenting between ten to one hundred times faster than similar deep learning methods. The models which are functionalized and constructed by the software have statistically indistinguishable results when compared to the gold standard modeling methods (Wilcoxon followed by MWU with Bonferroni correction). A combined RNN-LSTM approach to PGT was able to achieve over 95% point-wise accuracy on the testing set in identifying a data point's belonging to a neuronal spike on in silico recordings. Finally, using LSAA we can not only predict presence or absence of cardiac stent with high accuracy (88% on the test set, 94\\% on the full dataset), we can isolate and cluster semantic groups of atoms representing cardiac occlusion.","abstract_has_math":false,"creators":["Lloyd, David Anderson 1996-"],"institution":"University of Houston","degree_name":"Doctor of Philosophy","degree_level":null,"degree_discipline":"Biomedical Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Akay, Metin"],"committee_chairs":[],"committee_members":["Smith, Scott","Romero-Ortega, Mario I.","Du, Yuncheng","Wu, Tianfu","Akay, Yasemin"],"year":2024,"date_issued":"2024-12","date_published":"2024-12","updated_at":"2026-07-24T02:32:54Z","subjects":["Neural Engineering","CAD","Biomedical Engineering"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/18287","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Akay, Metin"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Smith, Scott","Romero-Ortega, Mario I.","Du, Yuncheng","Wu, Tianfu","Akay, Yasemin"]},{"key":"dc:creator","label":"Author","values":["Lloyd, David Anderson 1996-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-01-16T19:58:43Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-12"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Biomedical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Neural Engineering","CAD","Biomedical Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/18287"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Artificial intelligence (AI) has myriad applications for biomedical engineering and healthcare. In particular, with the diverse modalities and high resolution of physiological data, the potential for data-driven approaches to elucidate meaningful insights is enormous. However, the enormity and profundity of this data is also a hindrance. AI approaches can fail to learn due to "feature dilution", where a model is overloaded with data points, and spurious or noisy features prevent it from successfully aligning to and converging on semantic or predictive features in the dataset. Traditional methods of feature extraction either rely on manual physiological inference or leverage pre-trained AI models for well-characterized applications. We posit that AI itself can be leveraged to augment feature identification through the exploitation of learned representations and intelligent processes. To address this problem, we present three approaches for the application of artificial intelligence to the task of feature extraction in three different modes of biomedical data: 1. AxoDetect (AD), a complete image-to-model software pipeline for in silico nerve stimulation using computer vision (CV); 2. Probability Gradient Thresholding (PGT), a deep learning-based dynamic time window extraction method for the identification of neuronal compound action potential (CAP) spikes from neuronal recordings; and 3. Latent Semantic Atom Analysis (LSAA), a hybrid approach using Matching Pursuit (MP) and DeepSets (DS) to learn patient-specific representations of atherosclerosis in the coronary arteries from human heart sound data. AxoDetect excels at segmenting nerves without requiring labeled datasets, segmenting between ten to one hundred times faster than similar deep learning methods. The models which are functionalized and constructed by the software have statistically indistinguishable results when compared to the gold standard modeling methods (Wilcoxon followed by MWU with Bonferroni correction). A combined RNN-LSTM approach to PGT was able to achieve over 95% point-wise accuracy on the testing set in identifying a data point's belonging to a neuronal spike on in silico recordings. Finally, using LSAA we can not only predict presence or absence of cardiac stent with high accuracy (88% on the test set, 94\\% on the full dataset), we can isolate and cluster semantic groups of atoms representing cardiac occlusion."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["AI Approaches for Feature Extraction in Multimodal Biomedical Data"]}]}],"canonical_facts":{"dc:contributor.advisor":["Akay, Metin"],"dc:contributor.committeemember":["Smith, Scott","Romero-Ortega, Mario I.","Du, Yuncheng","Wu, Tianfu","Akay, Yasemin"],"dc:creator":["Lloyd, David Anderson 1996-"],"dc:date.accessioned":["2025-01-16T19:58:43Z"],"dc:date.issued":["2024-12"],"dc:description.abstract":["Artificial intelligence (AI) has myriad applications for biomedical engineering and healthcare. In particular, with the diverse modalities and high resolution of physiological data, the potential for data-driven approaches to elucidate meaningful insights is enormous. However, the enormity and profundity of this data is also a hindrance. AI approaches can fail to learn due to "feature dilution", where a model is overloaded with data points, and spurious or noisy features prevent it from successfully aligning to and converging on semantic or predictive features in the dataset. Traditional methods of feature extraction either rely on manual physiological inference or leverage pre-trained AI models for well-characterized applications. We posit that AI itself can be leveraged to augment feature identification through the exploitation of learned representations and intelligent processes. To address this problem, we present three approaches for the application of artificial intelligence to the task of feature extraction in three different modes of biomedical data: 1. AxoDetect (AD), a complete image-to-model software pipeline for in silico nerve stimulation using computer vision (CV); 2. Probability Gradient Thresholding (PGT), a deep learning-based dynamic time window extraction method for the identification of neuronal compound action potential (CAP) spikes from neuronal recordings; and 3. Latent Semantic Atom Analysis (LSAA), a hybrid approach using Matching Pursuit (MP) and DeepSets (DS) to learn patient-specific representations of atherosclerosis in the coronary arteries from human heart sound data. AxoDetect excels at segmenting nerves without requiring labeled datasets, segmenting between ten to one hundred times faster than similar deep learning methods. The models which are functionalized and constructed by the software have statistically indistinguishable results when compared to the gold standard modeling methods (Wilcoxon followed by MWU with Bonferroni correction). A combined RNN-LSTM approach to PGT was able to achieve over 95% point-wise accuracy on the testing set in identifying a data point's belonging to a neuronal spike on in silico recordings. Finally, using LSAA we can not only predict presence or absence of cardiac stent with high accuracy (88% on the test set, 94\\% on the full dataset), we can isolate and cluster semantic groups of atoms representing cardiac occlusion."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/18287"],"dc:language.iso":["English"],"dc:subject":["Neural Engineering","CAD","Biomedical Engineering"],"dc:title":["AI Approaches for Feature Extraction in Multimodal Biomedical Data"],"dc:type":["Thesis"],"thesis:degree_discipline":["Biomedical Engineering"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:32:54Z"}