A Deep Learning Decision Support Tool to Improve Risk Stratification and Reduce Unnecessary Biopsies in BI-RADS 4 Mammograms.

Purpose: To evaluate the performance of a biopsy decision support algorithmic model, the intelligent-augmented breast cancer risk calculator (iBRISK), on a multicenter patient dataset. Materials and Methods: iBRISK was previously developed by applying deep learning to clinical risk factors and mammographic descriptors from 9700 patient records at the primary institution and validated using another 1078 patients. All patients were seen from March 2006 to December 2016. In this multicenter study, iBRISK was further assessed on an independent, retrospective dataset (January 2015-June 2019) from three major health care institutions in Texas, with Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions. Data were dichotomized and trichotomized to measure precision in risk stratification and probability of malignancy (POM) estimation. iBRISK score was also evaluated as a continuous predictor of malignancy, and cost savings analysis was performed. Results: The iBRISK model's accuracy was 89.5%, area under the receiver operating characteristic curve (AUC) was 0.93 (95% CI: 0.92, 0.95), sensitivity was 100%, and specificity was 81%. A total of 4209 women (median age, 56 years [IQR, 45-65 years]) were included in the multicenter dataset. Only two of 1228 patients (0.16%) in the "low" POM group had malignant lesions, while in the "high" POM group, the malignancy rate was 85.9%. iBRISK score as a continuous predictor of malignancy yielded an AUC of 0.97 (95% CI: 0.97, 0.98). Estimated potential cost savings were more than $420 million. Conclusion: iBRISK demonstrated high sensitivity in the malignancy prediction of BI-RADS 4 lesions. iBRISK may safely obviate biopsies in up to 50% of patients in low or moderate POM groups and reduce biopsy-associated costs.Keywords: Mammography, Breast, Oncology, Biopsy/Needle Aspiration, Radiomics, Precision Mammography, AI-augmented Biopsy Decision Support Tool, Breast Cancer Risk Calculator, BI-RADS 4 Mammography Risk Stratification, Overbiopsy Reduction, Probability of Malignancy (POM) Assessment, Biopsy-based Positive Predictive Value (PPV3) Supplemental material is available for this article. Published under a CC BY 4.0 license.See also the commentary by McDonald and Conant in this issue.

Time After Time: A Second Look at Evolving Rash With Multiple Exposures to Amoxicillin.

Pediatric penicillin drug reactions may present in many forms such as erythema multiforme, serum-sickness, serum-sickness-like reaction (SSLR), Henoch-Schonlein Purpura (HSP), and urticarial vasculitis. Here, we review the case of a 13-month-old with atypical presentation of a drug reaction with increasing severity after each exposure to amoxicillin. We discuss the various differential diagnoses in comparison to our patient's presentation and conclude with the recommendation of considering timing and previous exposures in the diagnosis of drug-associated rashes in pediatric population.

Breast cancer treatment delays in a majority minority community: is there a difference?

PURPOSE: Recent studies from large nationwide cancer databases have consistently shown that Hispanic women with breast cancer have delays in treatment initiation compared with non-Hispanic white women. However, time to treatment initiation has not been studied in a community where Hispanics are the majority. PATIENTS AND METHODS: We conducted a retrospective, observational study of 362 female patients with breast cancer treated at a large National Cancer Institute (NCI) -designated cancer center with a largely Hispanic population. We examined the relationship between race/ethnicity and time from mammogram to biopsy as well as time from biopsy to treatment initiation using Kaplan-Meier analyses and multivariable Cox proportional hazards regression. RESULTS: Half of the female patients with breast cancer were of Hispanic descent (50.0%; n = 181). Hispanic patients were more likely to be obese, have an Eastern Cooperative Oncology Group functional status ≥ 1, and have higher histologic grade disease (all P ≤ .05); no differences in American Joint Committee on Cancer stage at diagnosis were observed. After comprehensive adjustment for demographic and clinical characteristics, we found no significant differences between Hispanic versus non-Hispanic white patients in time from mammogram to biopsy (hazard ratio [HR], 0.91; 95% CI, 0.68 to 1.21) or time from biopsy to treatment (HR, 1.13; 95% CI, 0.69 to 1.88). CONCLUSION: Hispanic women and Non-Hispanic white women with breast cancer treated at an NCI-designated cancer center had similar times to biopsy and treatment initiation. These findings suggest that in majority minority communities with large cancer centers, racial disparities can be reduced. With a growing Hispanic population throughout the United States, future studies should examine the long-term impact on improved breast cancer survival in this population.