No abstract

Younger patients, those with psychiatric illness, and those with insurance define a group that is more likely to be noncompliant with treatment and hence may require up-front intervention to improve outcomes.

Background: Chemoprevention with anti-estrogens such as tamoxifen has been shown to lower mammographic density (MD), a strong predictor of breast cancer risk. However, measurement of MD is limited by variability in radiologists’ interpretations. We developed a novel, fully-automated convolutional neural network (CNN)-derived mammographic evaluation that is a more accurate predictor of breast cancer risk than MD. We evaluated whether chemoprevention with anti-estrogens is associated with a significant change in CNN breast cancer risk among women with atypical hyperplasia (AH), lobular or ductal carcinoma in situ (LCIS/DCIS). Methods: We conducted a retrospective cohort study using serial mammograms from women diagnosed with AH, LCIS, or DCIS at Columbia University Irving Medical Center (CUIMC) between 2007 and 2015. We collected mammograms at baseline (at diagnosis of AH/LCIS/DCIS or prior to initiation of chemoprevention) and 3-5 years follow-up. We extracted information from the electronic health record on age, race/ethnicity, menopausal status, body mass index (BMI), and chemoprevention uptake (yes/no). Briefly, each mammogram was normalized as a map of z-scores and resized to an input image size of 256 × 256. Then a contracting and expanding fully convolutional CNN architecture was composed entirely of 3 × 3 convolutions, a total of four strided convolutions instead of pooling layers, and symmetric residual connections. L2 regularization and augmentation methods were implemented to prevent over-fitting. CNN risk score was expressed as a continuous variable (0-1). We used 2-sample t-test to compare change in CNN risk score from baseline to follow-up among women who took chemoprevention compared to those who did not. We conducted multivariable linear regression adjusting for known breast cancer risk factors (age, BMI, menopausal status, race/ethnicity) to determine whether receipt of chemoprevention was associated with change in CNN risk score. Results: Among 728 evaluable women, mean age was 60.4 years (SD, 11.1), 70.4% were postmenopausal, and 248 (34.1%) received chemoprevention with anti-estrogens while 480 (65.9%) did not. Women who received chemoprevention compared to those who did not had a greater mean change in CNN risk score from baseline to 3-5 years of follow-up, -0.069 (SD, 0.278) and -0.019 (SD, 0.244), respectively (p=0.014). In multivariate analysis, women who received chemoprevention compared to those who did not had a 0.038 point greater decrease in CNN risk score (p=0.085, 95% confidence interval [CI]= -0.081, +0.005). Conclusions: We demonstrated that our CNN-based mammographic evaluation is modifiable with anti-estrogen therapy among high-risk women. Future studies should determine whether changes in CNN risk score are associated with the development of breast cancer, in order to further evaluate the CNN mammographic evaluation as a potential pharmacodynamic biomarker of response to breast cancer chemoprevention. Citation Format: Julia E. McGuinness, Vicky Ro, Aishwarya Anuraj, Haley Manley, Simukayi Mutasa, Richard Ha, Katherine D. Crew. Effect of breast cancer chemoprevention on a convolutional neural network-based mammographic evaluation using a mammographic dataset of women with atypical hyperplasia, lobular or ductal carcinoma in situ [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PR-04.

45 years of age. Relevant demographic, tumor, and survival variables were extracted for analysis. Hospitals were divided into community cancer programs (100-500 annual cancer cases) and comprehensive community or academic/research programs (500 annual cancer cases). Cox regression was used to identify predictors of survival. Results: We identified 54,565 OCSCC patients, 7.6% of whom are younger than 45 years of age (nZ3828). Of these patients, 80% were between 35 and 44 years of age. More males were affected (65.7%) than females. Caucasians represented 86.3% of cases, followed by African Americans (9.5%) and patients of "other" races (4.2%). Private insurance (65.6%) was most common, with Medicaid (17.6%), uninsured (11.7%), and Medicare (5.1%) comprising the rest. Overall survival at 2 and 5 years was 76% and 66%, respectively. The oral tongue subsite was most common (55.4%), followed by floor of mouth (FOM; 28.5%), gingiva/retromolar trigone (15.4%), and buccal mucosa (0.7%). An increasing incidence of oral tongue cancers was seen, while FOM cancers showed a decreasing trend over the study period. A minority of cases was treated at low-volume community cancer centers, which saw more stage I-II disease. Uninsured and Medicaid patients had more advanced stage III-IV disease (P<.001), while those with private insurance had more early-stage disease. Further analysis including treatment, insurance, demographics, and survival was performed. cStage I-II patients without private insurance were more likely to receive some form of chemotherapy. Ethnicity, insurance status, income, age group, pathologic stage, and positive surgical margins are significant prognosticators on univariate analysis. In multivariate analysis, high pathologic stage, nonprivate insurance, treatment at a low-volume community center, and positive margins remained predictors of worse survival. Conclusion: In young patients with oral cavity cancers, differences in treatment, presentation, and survival were seen in those with health disparities. In addition to staging and surgical margins, treatment at low-volume community cancer centers and nonprivate insurance status predicted worse survival.

Background For gravely ill patients who have no treatment options and who are ineligible for clinical trials, the US Food and Drug Administration (FDA) established the Expanded Access Program (EAP). Motivated by efforts to weaken FDA regulation and sold as providing greater access to experimental drugs, the federal Right to Try Act (RTT) was passed in 2017. It reduces FDA oversight by not requiring physicians to report safety data and foregoes approval of protocols by local institutional review boards. Methods This study explored the views of 17 neuro-oncologists from 15 different academic medical centers with varying experience with EAP and RTT using convenience sampling. We conducted semi-structured interviews and qualitative analysis to identify emerging themes. Results Most oncologists were confused between the two pathways, had little familiarity with RTT, and had little knowledge about experimental medicine available through either pathway. Oncologists reported a preference of enrolling patients in clinical trials over off-trial preapproval pathways with scant data. As a result, oncologists revealed concerns over properly evaluating risks for their patients. Conclusion Our findings suggest that neuro-oncologists need better resources and clearer mechanisms at their institutions to help navigate EAP and RTT in order to counsel patients interested in experimental medicine.