Abstract 5577: Text-mining methods applied to clinical records support an association between androgen deprivation therapy and subsequent cardiometabolic disease

Proceedings: AACR 106th Annual Meeting 2015; April 18-22, 2015; Philadelphia, PA We conducted this study to examine the association of androgen deprivation therapy in the treatment of prostate cancer with future metabolic and cardiovascular disease. Here we utilize electronic medical record data from 1.8 million subjects in the Stanford Translational Research Integrated Database Environment. Specifically, we extracted ICD-9 diagnostic codes, patient medication lists and data from clinical notes using a previously validated text-analytics pipeline. Through this approach, we identified a cohort of 4,578 individuals with prostate cancer containing data on all defined covariates including Gleason score, age, race and use of antiplatelet, anticoagulant, antihypertensive and lipid lowering agents. We used multivariable logistic regression techniques to examine the association of androgen deprivation therapy use with diabetes, peripheral arterial disease, and stroke. Following prostate cancer diagnosis, there were 80 new diagnoses of diabetes, 39 new diagnoses of peripheral arterial disease and 72 new diagnoses of stroke with 409 individuals receiving androgen deprivation therapy. The use of androgen deprivation therapy to treat prostate cancer was associated with an increased risk of diabetes (odds ratio [OR] = 2.37; 95% confidence interval [CI] 1.40-4.03; P = 0.001), peripheral arterial disease (OR = 2.15; 95% CI 1.07-4.32; P = 0.032) and stroke (OR = 2.88; 95% CI 1.72-4.80; P<0.001). Here we further demonstrate the utility of clinical data obtained during routine care to investigate clinical hypotheses. Additionally, we add evidence to the growing body of literature linking the use of androgen deprivation therapy to future cardiovascular and metabolic disease. Citation Format: Kevin T. Nead, Gregory L. Gaskin, Cariad Chester, Nigam H. Shah, Nicholas J. Leeper. Text-mining methods applied to clinical records support an association between androgen deprivation therapy and subsequent cardiometabolic disease. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 5577. doi:10.1158/1538-7445.AM2015-5577