{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/70225"},"canonical_url":"https://search.dev.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/70225","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"Meta-learning in Medicine","abstract":"In recent years, the amount of digital information stored in electronic health records (EHRs) has increased dramatically. At the same time, the advances in the field of machine learning, specifically deep learning has accommodated the opportunity for knowledge discovery and data mining algorithms to gain insight from this digital health data. Predictive modeling of clinical risks from EHRs, such as in-hospital mortality rate, in-hospital length of stay and chronic disease onset, can be helpful to the improvement of the quality of healthcare delivery. However, there are many challenges, such as sparsity, irregularity and temporality, associated with this clinical data. Therefore, this provides an opportunity for meta-learning methodologies to solve such problems and to have a large impact on medicine and quality of healthcare delivery. In this paper, we provide the background of this problem, review the commonly used strategies for solving such problems and discuss the state-of-the-art of meta-learning models. To address the clinical challenges associated with EHR data, we propose a meta-learning model, which uses latent-ODE as the base-learner and LSTM as the meta-learner, to solve disease phenotyping tasks. We then demonstrate that our proposed method outperforms the state-of-the-art models addressing classification tasks on healthcare data.","abstract_html":"In recent years, the amount of digital information stored in electronic health records (EHRs) has increased dramatically. At the same time, the advances in the field of machine learning, specifically deep learning has accommodated the opportunity for knowledge discovery and data mining algorithms to gain insight from this digital health data. Predictive modeling of clinical risks from EHRs, such as in-hospital mortality rate, in-hospital length of stay and chronic disease onset, can be helpful to the improvement of the quality of healthcare delivery. However, there are many challenges, such as sparsity, irregularity and temporality, associated with this clinical data. Therefore, this provides an opportunity for meta-learning methodologies to solve such problems and to have a large impact on medicine and quality of healthcare delivery. In this paper, we provide the background of this problem, review the commonly used strategies for solving such problems and discuss the state-of-the-art of meta-learning models. To address the clinical challenges associated with EHR data, we propose a meta-learning model, which uses latent-ODE as the base-learner and LSTM as the meta-learner, to solve disease phenotyping tasks. We then demonstrate that our proposed method outperforms the state-of-the-art models addressing classification tasks on healthcare data.","abstract_has_math":false,"creators":["Gheissari, Pargol","Huang, Yong"],"institution":"Cornell University","degree_name":"M.S., Information Science","degree_level":"Master of Science","degree_discipline":"Information Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":["Azenkot, Shiri"],"year":2020,"date_issued":"2020-05","date_published":"2020-05","updated_at":"2026-07-24T01:48:58Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/v91k-j875"],"render_values":[{"text":"https://doi.org/10.7298/v91k-j875","href":"https://doi.org/10.7298/v91k-j875","code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 10838","ProQuest Publication ID: 27955778","ProQuest Submission ID: 10833","ProQuest Publication ID: 27955533"],"render_values":[{"text":"ProQuest Submission ID: 10838","href":null,"code":true},{"text":"ProQuest Publication ID: 27955778","href":null,"code":true},{"text":"ProQuest Submission ID: 10833","href":null,"code":true},{"text":"ProQuest Publication ID: 27955533","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/1813/70225","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Azenkot, Shiri"]},{"key":"dc:creator","label":"Author","values":["Gheissari, Pargol","Huang, Yong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-08-10T19:48:51Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-08-10T19:48:51Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-05"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Information Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master of Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S., Information Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Cornell University"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/v91k-j875"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 10838","ProQuest Publication ID: 27955778","ProQuest Submission ID: 10833","ProQuest Publication ID: 27955533"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/70225"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["30 pages"]},{"key":"dc:description.abstract","label":"Abstract","values":["In recent years, the amount of digital information stored in electronic health records (EHRs) has increased dramatically. At the same time, the advances in the field of machine learning, specifically deep learning has accommodated the opportunity for knowledge discovery and data mining algorithms to gain insight from this digital health data. Predictive modeling of clinical risks from EHRs, such as in-hospital mortality rate, in-hospital length of stay and chronic disease onset, can be helpful to the improvement of the quality of healthcare delivery. However, there are many challenges, such as sparsity, irregularity and temporality, associated with this clinical data. Therefore, this provides an opportunity for meta-learning methodologies to solve such problems and to have a large impact on medicine and quality of healthcare delivery. In this paper, we provide the background of this problem, review the commonly used strategies for solving such problems and discuss the state-of-the-art of meta-learning models. To address the clinical challenges associated with EHR data, we propose a meta-learning model, which uses latent-ODE as the base-learner and LSTM as the meta-learner, to solve disease phenotyping tasks. We then demonstrate that our proposed method outperforms the state-of-the-art models addressing classification tasks on healthcare data."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Meta-learning in Medicine"]}]}],"canonical_facts":{"dc:contributor.committeemember":["Azenkot, Shiri"],"dc:creator":["Gheissari, Pargol","Huang, Yong"],"dc:date.accessioned":["2020-08-10T19:48:51Z"],"dc:date.available":["2020-08-10T19:48:51Z"],"dc:date.issued":["2020-05"],"dc:description":["30 pages"],"dc:description.abstract":["In recent years, the amount of digital information stored in electronic health records (EHRs) has increased dramatically. At the same time, the advances in the field of machine learning, specifically deep learning has accommodated the opportunity for knowledge discovery and data mining algorithms to gain insight from this digital health data. Predictive modeling of clinical risks from EHRs, such as in-hospital mortality rate, in-hospital length of stay and chronic disease onset, can be helpful to the improvement of the quality of healthcare delivery. However, there are many challenges, such as sparsity, irregularity and temporality, associated with this clinical data. Therefore, this provides an opportunity for meta-learning methodologies to solve such problems and to have a large impact on medicine and quality of healthcare delivery. In this paper, we provide the background of this problem, review the commonly used strategies for solving such problems and discuss the state-of-the-art of meta-learning models. To address the clinical challenges associated with EHR data, we propose a meta-learning model, which uses latent-ODE as the base-learner and LSTM as the meta-learner, to solve disease phenotyping tasks. We then demonstrate that our proposed method outperforms the state-of-the-art models addressing classification tasks on healthcare data."],"dc:format.mimetype":["application/pdf"],"dc:identifier.doi":["https://doi.org/10.7298/v91k-j875"],"dc:identifier.other":["ProQuest Submission ID: 10838","ProQuest Publication ID: 27955778","ProQuest Submission ID: 10833","ProQuest Publication ID: 27955533"],"dc:identifier.uri":["https://hdl.handle.net/1813/70225"],"dc:language.iso":["en"],"dc:title":["Meta-learning in Medicine"],"dc:type":["dissertation or thesis"],"thesis:degree_discipline":["Information Science"],"thesis:degree_level":["Master of Science"],"thesis:degree_name":["M.S., Information Science"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-07-24T01:48:58Z"}