{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/129921"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/129921","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Learning risk models for pancreatic cancer from electronic health records","abstract":"Pancreatic cancer is the third most lethal cancer in the U.S., causing an estimated 45,750 deaths in 2019. Of all treatments, surgical resection provides the best survival rate for pancreatic cancer. This is not feasible for the majority of pancreatic cancer patients, whose cancer is typically not diagnosed until the tumor is unresectable. Most symptoms of pancreatic cancer are typically subtle, which underscores the need for better risk modeling to predict a patient's chance of pancreatic cancer well before it would usually be diagnosed. We propose a series of novel models that apply standard machine learning techniques to Electronic Health Records (EHRs) to predict risk of pancreatic cancer in advance of cancer diagnosis. On the test dataset, two of our models achieved AUROCs of 0.85 (CI 0.81 - 0.90) and 0.79 (CI 0.77 - 0.82) with a 365-day lead time.","abstract_html":"Pancreatic cancer is the third most lethal cancer in the U.S., causing an estimated 45,750 deaths in 2019. Of all treatments, surgical resection provides the best survival rate for pancreatic cancer. This is not feasible for the majority of pancreatic cancer patients, whose cancer is typically not diagnosed until the tumor is unresectable. Most symptoms of pancreatic cancer are typically subtle, which underscores the need for better risk modeling to predict a patient's chance of pancreatic cancer well before it would usually be diagnosed. We propose a series of novel models that apply standard machine learning techniques to Electronic Health Records (EHRs) to predict risk of pancreatic cancer in advance of cancer diagnosis. On the test dataset, two of our models achieved AUROCs of 0.85 (CI 0.81 - 0.90) and 0.79 (CI 0.77 - 0.82) with a 365-day lead time.","abstract_has_math":false,"creators":["McCleary, Jennifer(Jennifer A.)"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Martin C. Rinard."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-22T22:21:55Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/129921","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Martin C. Rinard."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["McCleary, Jennifer(Jennifer A.)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-02-19T20:58:01Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-02-19T20:58:01Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/129921"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020","Cataloged from student-submitted PDF of thesis.","Includes bibliographical references (pages 67-74)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Pancreatic cancer is the third most lethal cancer in the U.S., causing an estimated 45,750 deaths in 2019. Of all treatments, surgical resection provides the best survival rate for pancreatic cancer. This is not feasible for the majority of pancreatic cancer patients, whose cancer is typically not diagnosed until the tumor is unresectable. Most symptoms of pancreatic cancer are typically subtle, which underscores the need for better risk modeling to predict a patient's chance of pancreatic cancer well before it would usually be diagnosed. We propose a series of novel models that apply standard machine learning techniques to Electronic Health Records (EHRs) to predict risk of pancreatic cancer in advance of cancer diagnosis. On the test dataset, two of our models achieved AUROCs of 0.85 (CI 0.81 - 0.90) and 0.79 (CI 0.77 - 0.82) with a 365-day lead time."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M. Eng."]},{"key":"dc:title","label":"Title","values":["Learning risk models for pancreatic cancer from electronic health records"]}]}],"canonical_facts":{"dc:contributor.advisor":["Martin C. Rinard."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["McCleary, Jennifer(Jennifer A.)"],"dc:date.accessioned":["2021-02-19T20:58:01Z"],"dc:date.available":["2021-02-19T20:58:01Z"],"dc:date.issued":["2020"],"dc:description":["Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020","Cataloged from student-submitted PDF of thesis.","Includes bibliographical references (pages 67-74)."],"dc:description.abstract":["Pancreatic cancer is the third most lethal cancer in the U.S., causing an estimated 45,750 deaths in 2019. Of all treatments, surgical resection provides the best survival rate for pancreatic cancer. This is not feasible for the majority of pancreatic cancer patients, whose cancer is typically not diagnosed until the tumor is unresectable. Most symptoms of pancreatic cancer are typically subtle, which underscores the need for better risk modeling to predict a patient's chance of pancreatic cancer well before it would usually be diagnosed. We propose a series of novel models that apply standard machine learning techniques to Electronic Health Records (EHRs) to predict risk of pancreatic cancer in advance of cancer diagnosis. On the test dataset, two of our models achieved AUROCs of 0.85 (CI 0.81 - 0.90) and 0.79 (CI 0.77 - 0.82) with a 365-day lead time."],"dc:description.degree":["M. Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/129921"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Learning risk models for pancreatic cancer from electronic health records"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:55Z"}