{"63986":{"#nid":"63986","#data":{"type":"event","title":"Personalizing Breast Cancer Screening Policies","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETITLE:\u0026nbsp; \u003C\/strong\u003EPersonalizing Breast Cancer Screening Policies\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ESPEAKER:\u0026nbsp; \u003C\/strong\u003ETurgay Ayer, Faculty Candidate\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EABSTRACT:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EBreast cancer is the most common cancer and the\nprincipal cause of cancer deaths in women worldwide. Although mammography is\nthe most effective modality for breast cancer screening, it has several potential\nrisks, including high false-positive rates. Benefits and harms of mammography\ndepend on personal characteristics of women and balancing these benefits and\nharms is critical in designing a mammography screening schedule. In contrast to\nprior research and existing breast cancer screening guidelines which consider\npopulation-based screening recommendations, we propose a personalized\nmammography screening policy based on the personal risk characteristics of\nwomen and their prior screening history.\u003C\/p\u003E\n\n\u003Cp\u003EWe develop a novel finite-horizon partially\nobservable Markov decision process (POMDP) model for this problem. Our POMDP\nmodel incorporates two methods of detection (self or screen), age-specific\ndisease progression, mortality rates, and mammography test characteristics, as\nwell as prior screening history. We use a validated micro-simulation model\nbased on real data in estimating the parameters and solve this POMDP model\noptimally for individual patients. Our results show that our proposed\npersonalized screening schedules outperform the existing guidelines with\nrespect to the total expected quality-adjusted life years, while significantly\ndecreasing the number of mammograms and false-positives. We further find that\nthe mammography screening threshold risk increases with age. We derive several\nstructural properties of the model, including the sufficiency conditions that\nensure the existence of a control-limit policy.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Personalizing Breast Cancer Screening Policies"}],"uid":"27187","created_gmt":"2011-02-01 11:56:27","changed_gmt":"2016-10-08 01:53:24","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2011-02-17T10:00:00-05:00","event_time_end":"2011-02-17T11:00:00-05:00","event_time_end_last":"2011-02-17T11:00:00-05:00","gmt_time_start":"2011-02-17 15:00:00","gmt_time_end":"2011-02-17 16:00:00","gmt_time_end_last":"2011-02-17 16:00:00","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":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}