Search

Artificial intelligence (AI) readers of mammograms compare favourably to individual radiologists in detecting breast cancer. However, AI readers cannot perform at the level of multi-reader systems used by screening programs in countries such as Australia, Sweden, and the UK. Therefore, implementation demands human-AI collaboration. Here, we use a large, high-quality retrospective mammography dataset from Victoria, Australia to conduct detailed simulations of five potential AI-integrated screening pathways, and examine human-AI interaction effects to explore automation bias. Operating an AI reader as a second reader or as a high confidence filter improves current screening outcomes by 1.9–2.5% in sensitivity and up to 0.6% in specificity, achieving 4.6–10.9% reduction in assessments and 48–80.7% reduction in human reads. Automation bias degrades performance in multi-reader settings but improves it for single-readers. This study provides insight into feasible approaches for AI-integrated screening pathways and prospective studies necessary prior to clinical adoption. Successful human-AI collaboration could greatly contribute to breast cancer mammographic screening. Here, the authors use a large-scale retrospective mammography dataset to simulate and compare five plausible AI-integrated screening pathways, finding optimal ways in which human-AI collaboration could be implemented in real-world settings. [ABSTRACT FROM AUTHOR]

Abstract Men who carry mutations in BRCA1 or BRCA2 are at increased risk for prostate cancer. However the efficacy of prostate screening in this setting is uncertain and limited data exists on the uptake of prostate screening by mutation carriers. This study prospectively evaluated uptake of prostate cancer screening in a multi-institutional cohort of mutation carriers. Subjects were unaffected male BRCA1 and BRCA2 mutation carriers, aged 40–69 years, enrolled in the Kathleen Cuningham Consortium for Research into Familial Breast Cancer (kConFab) and who had completed a mailed, self-report follow-up questionnaire 3 yearly after study entry. Of the 75 male carriers in this study, only 26 (35%) had elected to receive their mutation result. Overall, 51 (68%) did not recall having received a recommendation to have prostate screening because of their family history, but 41 (55%) had undergone a prostate specific antigen (PSA) test and 32 (43%) a digital rectal examination (DRE) in the previous 3 years. Those who were aware of their mutation result were more likely to have received a recommendation for prostate screening (43 vs. 6%, p = 0.0001), and to have had a PSA test (77 vs. 43%, p = 0.005) and a DRE (69 vs. 29%, p = 0.001) in the previous 3 years. The majority of unaffected males enrolled in kConFab with a BRCA1/2 mutation have not sought out their mutation result. However, of those aware of their positive mutation status, most have undergone at least one round of prostate screening in the previous 3 years.

The performance of breast cancer risk models for women with a family history but negative BRCA1 and/or BRCA2 mutation test results is uncertain. We calculated the cumulative 10-year invasive breast cancer risk at cohort entry for 14 657 unaffected women (96.1% had an affected relative) not known to carry BRCA1 or BRCA2 mutations at baseline using three pedigree-based models (Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm, BRCAPRO, and International Breast Cancer Intervention Study). During follow-up, 482 women were diagnosed with invasive breast cancer. Mutation testing was conducted independent of incident cancers. All models underpredicted risk by 26.3%-56.7% for women who tested negative but whose relatives had not been tested (n = 1363; 63 breast cancers). Although replication studies with larger sample sizes are needed, until these models are recalibrated for women who test negative and have no relatives tested, caution should be used when considering changing the breast cancer risk management intensity of such women based on risk estimates from these models. [ABSTRACT FROM AUTHOR]

Benign breast disease (BBD) is an established breast cancer (BC) risk factor, but it is unclear whether the magnitude of the association applies to women at familial or genetic risk. This information is needed to improve BC risk assessment in clinical settings. Using the Prospective Family Study Cohort, we used Cox proportional hazards models to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) for the association of BBD with BC risk. We also examined whether the association with BBD differed by underlying familial risk profile (FRP), calculated using absolute risk estimates from the Breast Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm (BOADICEA) model. During 176,756 person‐years of follow‐up (median: 10.9 years, maximum: 23.7) of 17,154 women unaffected with BC at baseline, we observed 968 incident cases of BC. A total of 4,704 (27%) women reported a history of BBD diagnosis at baseline. A history of BBD was associated with a greater risk of BC: HR = 1.31 (95% CI: 1.14–1.50), and did not differ by underlying FRP, with HRs of 1.35 (95% CI: 1.11–1.65), 1.26 (95% CI: 1.00–1.60), and 1.40 (95% CI: 1.01–1.93), for categories of full‐lifetime BOADICEA score <20%, 20 to <35%, ≥35%, respectively. There was no difference in the association for women with BRCA1 mutations (HR: 1.64; 95% CI: 1.04–2.58), women with BRCA2 mutations (HR: 1.34; 95% CI: 0.78–2.3) or for women without a known BRCA1 or BRCA2 mutation (HR: 1.31; 95% CI: 1.13–1.53) (pinteraction = 0.95). Women with a history of BBD have an increased risk of BC that is independent of, and multiplies, their underlying familial and genetic risk. What's new? Benign breast disease (BBD) is an established breast cancer (BC) risk factor, but it is unclear whether the magnitude of the association applies to women at familial or genetic risk. To find out, the authors used a family‐based prospective cohort of women enriched for breast cancer family history (BCFH) to examine the association of BBD with BC risk. They observed a 30% increased BC risk associated with BBD, independent of BCFH. Previous studies have been underpowered to examine this interaction with extent of family history; this study confirms the importance of both BBD and BCFH when performing clinical risk assessment. [ABSTRACT FROM AUTHOR]

There remains debate about whether risk-reducing salpingo-oophorectomy (RRSO), which reduces ovarian cancer risk, also reduces breast cancer risk. We examined the association between RRSO and breast cancer risk using a prospective cohort of 17 917 women unaffected with breast cancer at baseline (7.2% known carriers of BRCA1 or BRCA2 mutations). During a median follow-up of 10.7 years, 1046 women were diagnosed with incident breast cancer. Modeling RRSO as a time-varying exposure, there was no association with breast cancer risk overall (hazard ratio [HR] = 1.04, 95% confidence interval [CI] = 0.87 to 1.24) or by tertiles of predicted absolute risk based on family history (HR = 0.68, 95% CI = 0.32 to 1.47, HR = 0.94, 95% CI = 0.70 to 1.26, and HR = 1.10, 95% CI = 0.88 to 1.39, for lowest, middle, and highest tertile of risk, respectively) or for BRCA1 and BRCA2 mutation carriers when examined separately. There was also no association after accounting for hormone therapy use after RRSO. These findings suggest that RRSO should not be considered efficacious for reducing breast cancer risk. [ABSTRACT FROM AUTHOR]

Background: Breast cancer (BC) incidence is increasing in women under age 40 years, underscoring the need for research on BC risk factors for younger women., Methods: We used data from an international family cohort (n=26,348) to examine whether recreational physical activity (RPA) during adolescence and early adulthood are associated with BC risk before age 40. The cohort includes 2,502 women diagnosed with BC before age 40, including 2,408 diagnosed before study enrollment (68% within 5 years of enrollment). Women reported their average hours-per-week of moderate and strenuous RPA during adolescence (12-17 years) and early adulthood (25-34 years), which were converted to total age-adjusted metabolic equivalents-per-week and categorized into quartiles. We conducted attained age analyses until age 40 (follow-up time began at age 18) using Cox proportional hazards regression models adjusted for study center, race and ethnicity, and education., Results: Being in the highest versus lowest quartile of RPA during adolescence and early adulthood were respectively associated with 12% [HR (95% CI): 0.88 (0.78, 0.98)] and 16% [HR (95% CI): 0.84 (0.74, 0.95) lower BC risks before age 40. Being in the highest quartile of RPA during both adolescence and early adulthood (Pearson correlation=0.52) versus neither timepoint was associated with a 22% lower risk [HR (95% CI): 0.78 (0.68, 0.89)]., Conclusions: Findings suggest that RPA during adolescence and early adulthood may lower BC risk before age 40., Impact: Policies promoting physical activity during adolescence and early adulthood may be important for reducing the growing burden of breast cancer in younger women.

The performance of breast cancer risk models for women with a family history but negative BRCA1 and/or BRCA2 mutation test results is uncertain. We calculated the cumulative 10-year invasive breast cancer risk at cohort entry for 14 657 unaffected women (96.1% had an affected relative) not known to carry BRCA1 or BRCA2 mutations at baseline using three pedigree-based models (Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm, BRCAPRO, and International Breast Cancer Intervention Study). During follow-up, 482 women were diagnosed with invasive breast cancer. Mutation testing was conducted independent of incident cancers. All models underpredicted risk by 26.3%-56.7% for women who tested negative but whose relatives had not been tested (n = 1363; 63 breast cancers). Although replication studies with larger sample sizes are needed, until these models are recalibrated for women who test negative and have no relatives tested, caution should be used when considering changing the breast cancer risk management intensity of such women based on risk estimates from these models., (© The Author(s) 2019. Published by Oxford University Press. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Background: iPrevent is an online breast cancer (BC) risk management decision support tool. It uses an internal switching algorithm, based on a woman's risk factor data, to estimate her absolute BC risk using either the International Breast Cancer Intervention Study (IBIS) version 7.02, or Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm version 3 models, and then provides tailored risk management information. This study assessed the accuracy of the 10-year risk estimates using prospective data., Methods: iPrevent-assigned 10-year invasive BC risk was calculated for 15 732 women aged 20-70 years and without BC at recruitment to the Prospective Family Study Cohort. Calibration, the ratio of the expected (E) number of BCs to the observed (O) number and discriminatory accuracy were assessed., Results: During the 10 years of follow-up, 619 women (3.9%) developed BC compared with 702 expected (E/O = 1.13; 95% confidence interval [CI] =1.05 to 1.23). For women younger than 50 years, 50 years and older, and BRCA1/2 -mutation carriers and noncarriers, E/O was 1.04 (95% CI = 0.93 to 1.16), 1.24 (95% CI = 1.11 to 1.39), 1.13 (95% CI = 0.96 to 1.34), and 1.13 (95% CI = 1.04 to 1.24), respectively. The C-statistic was 0.70 (95% CI = 0.68 to 0.73) overall and 0.74 (95% CI = 0.71 to 0.77), 0.63 (95% CI = 0.59 to 0.66), 0.59 (95% CI = 0.53 to 0.64), and 0.65 (95% CI = 0.63 to 0.68), respectively, for the subgroups above. Applying the newer IBIS version 8.0b in the iPrevent switching algorithm improved calibration overall (E/O = 1.06, 95% CI = 0.98 to 1.15) and in all subgroups, without changing discriminatory accuracy., Conclusions: For 10-year BC risk, iPrevent had good discriminatory accuracy overall and was well calibrated for women aged younger than 50 years. Calibration may be improved in the future by incorporating IBIS version 8.0b., (© The Author(s) 2019. Published by Oxford University Press.)

There remains debate about whether risk-reducing salpingo-oophorectomy (RRSO), which reduces ovarian cancer risk, also reduces breast cancer risk. We examined the association between RRSO and breast cancer risk using a prospective cohort of 17 917 women unaffected with breast cancer at baseline (7.2% known carriers of BRCA1 or BRCA2 mutations). During a median follow-up of 10.7 years, 1046 women were diagnosed with incident breast cancer. Modeling RRSO as a time-varying exposure, there was no association with breast cancer risk overall (hazard ratio [HR] = 1.04, 95% confidence interval [CI] = 0.87 to 1.24) or by tertiles of predicted absolute risk based on family history (HR = 0.68, 95% CI = 0.32 to 1.47, HR = 0.94, 95% CI = 0.70 to 1.26, and HR = 1.10, 95% CI = 0.88 to 1.39, for lowest, middle, and highest tertile of risk, respectively) or for BRCA1 and BRCA2 mutation carriers when examined separately. There was also no association after accounting for hormone therapy use after RRSO. These findings suggest that RRSO should not be considered efficacious for reducing breast cancer risk., (© The Author(s) 2018. Published by Oxford University Press.)

Objective: To estimate the prevalence of the use of cancer risk-reducing measures among Australian BRCA1 and BRCA2 mutation carriers., Design, Setting and Participants: Prospective follow-up of female carriers of BRCA1 or BRCA2 mutations who had no personal history of cancer and were enrolled in a multiple-case breast cancer family cohort study (kConFab). Data, including cancer events and uptake of risk-reducing surgery and medication were collected by self-report at cohort entry and 3 yearly thereafter. Surgery was confirmed from pathology and medical records. Women were followed up from enrolment until cancer diagnosis, date of last follow-up, or death. Data were collected from 3 November 1997 to 21 May 2012., Main Outcome Measures: Uptake of risk-reducing surgery and/or medication., Results: Of 175 BRCA1 and 150 BRCA2 mutation carriers (median age, 37 years at cohort enrolment), 69 (21%) underwent risk-reducing mastectomy, 125 (38%) underwent risk-reducing bilateral salpingo-oophorectomy and nine (3%) participated in a clinical trial of risk-reducing medication, during 2447 person-years of follow-up (median follow-up, 9 years). Sixty-eight women (21%) reported incident cancers, including 52 breast cancers and nine ovarian cancers (defined in this article as high-grade serous cancers of the ovary, fallopian tube or peritoneum)., Conclusions: There is considerable scope to increase the uptake of cancer risk-reducing measures in Australian BRCA1 and BRCA2 mutation carriers. These findings should drive (i) future research into the factors contributing to low uptake in Australia and (ii) changes to policy and practice to help better translate genetic knowledge into reductions in cancer incidence.