{"69145":{"#nid":"69145","#data":{"type":"event","title":"Optimizing Diagnostic Decisions Under Resource Constraints in Breast Cancer Screening","body":[{"value":"\u003Cp align=\u0022left\u0022\u003ETITLE: Optimizing\nDiagnostic Decisions Under Resource Constraints in Breast Cancer Screening\u003C\/p\u003E\u003Cp align=\u0022left\u0022\u003ESPEAKER: Oguzhan Alagoz\u003C\/p\u003E\u003Cp align=\u0022left\u0022\u003EABSTRACT:\u003C\/p\u003E\u003Cp\u003EMammography is the most commonly used screening\ntool for early diagnosis of breast cancer, the most common non-skin cancer\naffecting women in the U.S.\u0026nbsp; While\nmammography is inexpensive, the interventional procedures that result from\ndetected abnormalities (both false and true positives) increase the cost of\nthis population-based screening program significantly.\u0026nbsp; Based on the mammography findings,\nradiologists need to choose one of the following three options: 1) take\nimmediate diagnostic actions including prompt biopsy to confirm whether an\nabnormality is in fact a breast cancer; 2) recommend short-interval follow-up\nmammography; 3) recommend routine mammography. There are no validated\nstructured guidelines to aid radiologists in making patient management\ndecisions after mammography exams. Surprisingly, 55-85% of the breast biopsies\nultimately are found to be benign breast lesions and only less than 1% of\nshort-interval follow-up recommendations are found to be malignant, resulting\nin additional tests, patient-anxiety and expenditures.\u003C\/p\u003E\n\n\n\n\u003Cp\u003E\u0026nbsp;We develop a finite-horizon discrete-time\nconstrained Markov decision process (MDP) to model diagnostic decisions after\nmammography where we maximize the total expected quality adjusted life years\n(QALYs) of a patient under resource constraints. We prove that the optimal\nvalue function is concave in the allocated budget. We use clinical data to\nestimate the parameters of the MDP model and solve it as a mixed-integer\nprogram. We find that as women get older they should be biopsied less\naggressively. We further find that short-term follow-ups are the immediate\ntarget for elimination when budget becomes a concern. We compare our model to\nclinical practice and find that our model has a potential to improve breast\ncancer diagnosis and reduce associated costs significantly. \u003C\/p\u003E\u003Cp\u003EBIO:\u003C\/p\u003E\u003Cp\u003EOguzhan Alagoz is currently an Associate Professor\nof Industrial and Systems Engineering at the University of Wisconsin-Madison.\nIn addition, he is an associate professor at the Department of Population\nHealth Sciences and serves as the director of National Institute of Health\n(NIH)-funded Institute for Clinical and Translational Research-Simulation\nCenter at UW-Madison School of Medicine and Public Health. He received his BS\nfrom Bilkent University in 1997, MS from Middle East Technical University in\n2000, and PhD in industrial engineering from the University of Pittsburgh in\n2004. His research interests include stochastic optimization, medical decision\nmaking, completely and partially observable Markov decision processes,\nsimulation, risk-prediction modeling, health technology assessment, and scheduling.\nHe is on the editorial boards of \u003Cem\u003EMedical\nDecision Making\u003C\/em\u003E and \u003Cem\u003EIIE Transactions\non Healthcare Engineering\u003C\/em\u003E. He serves as the president of INFORMS Health\nApplications Section.\u0026nbsp; He has received\nvarious awards including a CAREER award from National Science Foundation (NSF),\noutstanding young industrial engineer in education award from IIE, Dantzig\nDissertation Honorable Mention Award from INFORMS, 2nd place award from INFORMS\nJunior Faculty Interest Group best paper competition, best paper award from\nINFORMS Service Science Section, and best poster award from UW Carbone\nComprehensive Cancer Center. He has been the principal investigator and\nco-investigator on grants more than $2.2 million funded by NSF and the National\nCancer Institute of NIH. He is a member of INFORMS, IIE, SMDM, and CISNET.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Optimizing Diagnostic Decisions Under Resource Constraints in Breast Cancer Screening"}],"uid":"27187","created_gmt":"2011-08-03 08:03:52","changed_gmt":"2016-10-08 01:55:18","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2011-09-27T12:00:00-04:00","event_time_end":"2011-09-27T14:00:00-04:00","event_time_end_last":"2011-09-27T14:00:00-04:00","gmt_time_start":"2011-09-27 16:00:00","gmt_time_end":"2011-09-27 18:00:00","gmt_time_end_last":"2011-09-27 18:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}