Observational studies have reported an inverse association between vitamin D intake and breast cancer risk. We examined whether vitamin D supplementation in high-risk premenopausal women reduces mammographic density (MD), an established breast cancer risk factor. We conducted a multicenter randomized double-blind placebo-controlled trial in premenopausal women at high risk for breast cancer [5-year risk ≥ 1.67%, lifetime risk ≥ 20%, lobular carcinoma in situ, prior stage 0-II breast cancer, hereditary breast cancer syndrome, or high MD (heterogeneously/extremely dense)], with a baseline serum 25-hydroxyvitamin D [25(OH)D] ≤ 32 ng/mL. Participants were randomized to 12 months of vitamin D3 20,000 IU/week or matching placebo. The primary endpoint was change in MD from baseline to 12 months using the Cumulus technique. Secondary endpoints included serial blood biomarkers [25(OH)D, 1,25-dihydroxyvitamin D (1,25(OH)D), insulin-like growth factor (IGF)-1, IGF-binding protein-3] and MD change at 24 months. Among 208 women randomized, median age was 44.6 years, 84% were white, 33% had baseline 25(OH)D < 20 ng/mL, and 78% had high baseline MD. Comparing the active and placebo groups at 12 months, MD changes were small and did not significantly differ. Mean MD changes at 12 and 24 months were -0.3% and -1.2%, respectively, in the active arm and +1.5% and +1.6% with placebo (P > 0.05). We observed a mean change in serum 25(OH)D of +18.9 versus +2.8 ng/mL (P < 0.01) and IGF-1 of -9.8 versus -1.8 ng/mL (P = 0.28), respectively. At 12 months, MD was positively correlated with serum IGF-1 and IGF-1/IGFBP-3 (P < 0.01). This trial does not support the use of vitamin D supplementation for breast cancer risk reduction.

Deep learning-based mammographic evaluations could noninvasively assess response to breast cancer chemoprevention. We evaluated change in a convolutional neural network-based breast cancer risk model applied to mammograms among women enrolled in SWOG S0812, which randomly assigned 208 premenopausal high-risk women to receive oral vitamin D3 20 000 IU weekly or placebo for 12 months. We applied the convolutional neural network model to mammograms collected at baseline (n = 109), 12 months (n = 97), and 24 months (n = 67) and compared changes in convolutional neural network-based risk score between treatment groups. Change in convolutional neural network-based risk score was not statistically significantly different between vitamin D and placebo groups at 12 months (0.005 vs 0.002, P = .875) or at 24 months (0.020 vs 0.001, P = .563). The findings are consistent with the primary analysis of S0812, which did not demonstrate statistically significant changes in mammographic density with vitamin D supplementation compared with placebo. There is an ongoing need to evaluate biomarkers of response to novel breast cancer chemopreventive agents.