{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/79903"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/79903","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Deep Predictive Models for Mining Electronic Health Records","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Ma, Fenglong"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Gao, Jing","Computer Science and Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-07-30T15:10:53Z","date_published":"2019-07-30T15:10:53Z","updated_at":"2026-07-27T19:05:19Z","subjects":["computer science"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/79903","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Gao, Jing","Computer Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Ma, Fenglong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-07-30T15:10:53Z","2019","2019-05-16 18:03:55"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/79903"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","There is an increasing growth in the amount of electronic health records (EHRs) being collected by healthcare facilities. Data mining techniques hold great potential to system­atically use such data for identifying not only inefficiencies but also best practices that improve care and reduce costs. However, mining medical knowledge from raw EHR data is challenging, due to its own issues, including temporality, high dimensionality, sparsity and interpretability. To accurately predict patients' future health status by an­alyzing raw EHR data, in this thesis, we propose a series of novel deep learning-based approaches and focus on the following two perspectives : (1) how to thoroughly explore the unique characteristics of EHR data itself; and (2) how to effectively incorporate external information to significantly enhance the predictive power of deep models...To sum up, in this thesis, we develop novel approaches for the disease prediction tasks by mining useful and meaningful medical knowledge from noisy EHR data. With the proposed models, it is possible for us to get closer to the goal of personalized medicine. As the accumulation of EHR data is increasing exponentially over time, and the techniques are rapidly developed, there are still great opportunities as well as numer­ous research challenges for inference of useful and meaning medical knowledge from massive EHR data.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep Predictive Models for Mining Electronic Health Records"]}]}],"canonical_facts":{"dc:contributor":["Gao, Jing","Computer Science and Engineering"],"dc:creator":["Ma, Fenglong"],"dc:date":["2019-07-30T15:10:53Z","2019","2019-05-16 18:03:55"],"dc:description":["Ph.D.","There is an increasing growth in the amount of electronic health records (EHRs) being collected by healthcare facilities. Data mining techniques hold great potential to system­atically use such data for identifying not only inefficiencies but also best practices that improve care and reduce costs. However, mining medical knowledge from raw EHR data is challenging, due to its own issues, including temporality, high dimensionality, sparsity and interpretability. To accurately predict patients' future health status by an­alyzing raw EHR data, in this thesis, we propose a series of novel deep learning-based approaches and focus on the following two perspectives : (1) how to thoroughly explore the unique characteristics of EHR data itself; and (2) how to effectively incorporate external information to significantly enhance the predictive power of deep models...To sum up, in this thesis, we develop novel approaches for the disease prediction tasks by mining useful and meaningful medical knowledge from noisy EHR data. With the proposed models, it is possible for us to get closer to the goal of personalized medicine. As the accumulation of EHR data is increasing exponentially over time, and the techniques are rapidly developed, there are still great opportunities as well as numer­ous research challenges for inference of useful and meaning medical knowledge from massive EHR data.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/79903"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["computer science"],"dc:title":["Deep Predictive Models for Mining Electronic Health Records"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:19Z"}