Risk Prediction Models for Rare Melanomas
Abstract
We hypothesize that unique clinical, environmental, and genetic risk factors confer risk of acral, mucosal, and uveal melanoma among Veteran and civilian populations. Aims: 1) Identify clinical and environmental risk factors for each of the rare melanoma subtypes; 2) Integrate germline genetic factors for each rare melanoma risk model; and 3) Interrogate rare melanomas risk prediction model performance in two independent civilian cohorts. A nested case-control study based within the VA Corporate Data Warehouse (CDW) will be used to examine the association of clinical and environmental risk factors with rare melanoma risk. Cases will be identified by pulling all melanoma reports, identified by histology ICD morphology code, and then we will use natural language processing to identify anatomical site. We will ascertain information regarding deployment together with clinical, genetic, and administrative data (e.g., age, race-ethnicity, co-morbidities, medication, environmental exposures). Similar approaches will be used to pull a civilian case-control cohort from the MGH Research Patient Data Registry. Next, we will test the risk algorithms in prospective cohorts/patient registries. Identifying and targeting individuals at high-risk for rare melanomas can direct prevention efforts, enable early-intervention studies and ultimately reduce mortality.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 2022
- Accession Number
- AD1190463
Entities
People
- Kelly Cho
- Marc Hurlbert
- Martin Weinstock
- Maryam Asgari
- Michael J. Gaziano
- Nathanael Fillmore
- Peter Kraft
- Rachel Fischer
- Rebecca I Hartman
- Yevgeniy Semenov
Organizations
- Melanoma Research Alliance