Targeted Inpatient Screening Mammogram Program to Reduce Disparities in Breast Cancer Screening Rates.
Ontology highlight
ABSTRACT:
SUBMITTER: Hwang AS
PROVIDER: S-EPMC7800737 | biostudies-literature | 2021 Jan-Feb
REPOSITORIES: biostudies-literature
Publications
Targeted Inpatient Screening Mammogram Program to Reduce Disparities in Breast Cancer Screening Rates.
Hwang Andrew S AS Dontchos Brian N BN Dyer Karen K Murray Jennifer J Como Jennifer Searl JS Horn Daniel M DM
Annals of family medicine 20210101 1
Similar Datasets
Project description:PurposeDeveloping deep learning algorithms for breast cancer screening is limited due to the lack of labeled full-field digital mammograms (FFDMs). Since FFDM is a new technique that rose in recent decades and replaced digitized screen-film mammograms (DFM) as the main technique for breast cancer screening, most mammogram datasets were still stored in the form of DFM. A solution for developing deep learning algorithms based on FFDM while leveraging existing labeled DFM datasets is a generative algorithm that generates FFDM from DFM. Generating high-resolution FFDM from DFM remains a challenge due to the limitations of network capacity and lacking GPU memory.MethodIn this study, we developed a deep-learning-based generative algorithm, HRGAN, to generate synthesized FFDM (SFFDM) from DFM. More importantly, our algorithm can keep the image resolution and details while using high-resolution DFM as input. Our model used FFDM and DFM for training. First, a sliding window was used to crop DFMs and FFDMs into 256 × 256 pixels patches. Second, the patches were divided into three categories (breast, background, and boundary) by breast masks. Patches from the DFM and FFDM datasets were paired as inputs for training our model where these paired patches should be sampled from the same category of the two different image sets. U-Net liked generators and modified discriminators with two-channels output, one channel for distinguishing real and SFFDMs and the other for representing a probability map for breast mask, were used in our algorithm. Last, a study was designed to evaluate the usefulness of HRGAN. A mass segmentation task and a calcification detection task were included in the study.ResultsTwo public mammography datasets, the CBIS-DDSM dataset and the INbreast dataset, were included in our experiment. The CBIS-DDSM dataset includes 753 calcification cases and 891 mass cases with verified pathology information, resulting in a total of 3568 DFMs. The INbreast dataset contains a total of 410 FFDMs with annotations of masses, calcifications, asymmetries, and distortions. There were 1784 DFMs and 205 FFDM randomly selected as Dataset A. The remaining DFMs from the CBIS-DDSM dataset were selected as Dataset B. The remaining FFDMs from the INbreast dataset were selected as Dataset C. All DFMs and FFDMs were normalized to 100μm × 100μm in our experiments. A study with a mass segmentation task and a calcification detection task was performed to evaluate the usefulness of HRGAN.ConclusionsThe proposed HRGAN can generate high-resolution SFFDMs from DFMs. Extensive experiments showed the SFFDMs were able to help improve the performance of deep-learning-based algorithms for breast cancer screening on DFM when the size of the training dataset is small.
| S-EPMC9105019 | biostudies-literature
Project description:We compared the effectiveness of two outreach strategies on timely mammography adherence: a mammogram-specific reminder letter (sent just before a woman was due) to a birthday letter (addresses multiple preventive services and not timed around due dates). We evaluated screening mammography adherence following 79,848 mammogram-specific and 151,626 birthday letters mailed between 2002 and 2012 to women aged 40-74years enrolled in Kaiser Permanente Washington. Screening mammogram adherence was specifically tied to due date and was evaluated separately by age group and up-to-date or overdue status at the time of mailing. We used generalized estimating equations to account for correlation between repeated observations, to model the odds of screening mammography adherence by letter type. Among women up-to-date, adherence following birthday letters was 22-76% lower compared to the mammogram-specific reminders, with the greatest decreases in adherence in women aged 70-74. Birthday letters were more effective at activating screening uptake among some subgroups of overdue women aged 50-69 and most overdue women aged 70-74, but universally low adherence rates were observed in overdue women. Increasing number of recommended services for women aged 50-74 who were up-to-date resulted in 12-17% lower mammography adherence, but had no effect in women aged 40-49 or in overdue women. Birthday letters are less effective than mammogram-specific reminder letters at prompting women to undergo timely breast cancer screening, particularly among women up-to-date with screening. Birthday letters may be effective at increasing overall preventive care; however, supplemental outreach may be needed around the due date to increase timely preventive services receipt.
| S-EPMC5638650 | biostudies-literature
Project description:ObjectiveLow dose computed tomography (LDCT) became the standard method for lung cancer (LC) screening in 2013. However, it is unclear whether there are differences in survival rates based on sex and whether the differences depend on screening status. We aimed to evaluate the LC survival rates between females and males based on screening.Material and methodsThis retrospective cohort study examined data from the Boston LC Study (BLCS) between 2013 and 2021. LC screening depends on patients' demographics (age and smoking history) to determine whether a person is a high-risk individual and, therefore, undergo LDCT. Descriptive statistics were calculated for race, age, histology, smoking history, stage, and treatment. These variables' distributions were compared between sex and screening status using t-test and chi-square, respectively. Cox proportional hazards model and Kaplan-Meier curves were used to compare survival between sex and screening. Propensity score matching was applied to account for selection bias in screening when evaluating the association between screening and stage.ResultsA total of 1,216 LC patients were identified with a screening incidence of 9.4 %, among whom 56 % were female. Unscreened males had 1.59 times higher risk of mortality than unscreened females (P=.0002) and had a worse 5-year survival (male 50 %; 95 %CI, 0.38,0.6 vs female 70 %; 95 %CI,0.62,0.76). In contrast, there were no significant differences in survival between sexes among screened. In a balanced cohort of screened and unscreened, the odds of being diagnosed at late stages for females and smokers were 1.33 and 2.51 times that of males and nonsmokers; however, there were no statistical significance.ConclusionUnscreened females had a lower risk of mortality and better survival than unscreened males, while among the screened population, there was no difference in the overall survival. These observations demonstrate the influence of sex on survival prognosis in LC when screening is not performed.
| S-EPMC9618021 | biostudies-literature
Project description:IntroductionNationally, women of African heritage die at higher rates from breast cancer than women of other races or ethnicities. We developed Breast Cancer Champions (BCC) a peer-to-peer education program, which recruited 12 women and deployed them into the community in August 2020 during the height of the COVID pandemic. BCC aims to improve breast cancer screening rates for women of African heritage through peer-to-peer education, which has proven successful for addressing cancer-related health disparities.MethodsBCC community experts, or "Champions," are peer-to-peer educators that conduct awareness and screening events in their communities. Champion's education activities were tracked by bi-weekly check-in calls, which recorded the activity type, location, and the number of participants for each event. We used spatial and statistical analyses to determine the efficacy of the program at increasing screening rates for women within the area of Champion activity versus women outside of their activity area.ResultsOver 15 months, Champions conducted 245 in-person or online events to engage women in their community for screening. More women of African heritage were screened in areas Champions were active during the intervention compared to historical data comparing areas outside of the Champion activity in the prior 15 months (X 2 = 3.0845, p = 0.079).ConclusionBCC successes could be attributed to pivoting to online community building when in-person events were restricted and enabling Champions to design and conduct their own events, which increased outreach possibilities. We demonstrate improved screening outcomes associated with an updated peer-to-peer education program.
| S-EPMC10154761 | biostudies-literature
Project description:BackgroundTo evaluate the diagnostic performance of radiologists on breast cancer with or without artificial intelligence (AI) support.MethodsA retrospective study was performed. In total, 643 mammograms (average age: 54 years; female: 100%; cancer: 62.05%) were randomly allocated into two groups. Seventy-five percent of mammograms in each group were randomly selected for assessment by two independent radiologists, and the rest were read once. Half of the 71 radiologists could read mammograms with AI support, and the other half could not. Sensitivity, specificity, Youden's index, agreement rate, Kappa value, the area under the receiver operating characteristic curve (AUC) and the reading time of radiologists in each group were analyzed.ResultsThe average AUC was higher if the AI support system was used (unaided: 0.84; with AI support: 0.91; p < 0.01). The average sensitivity increased from 84.77% to 95.07% with AI support (p < 0.01), but the average specificity decreased (p = 0.07). Youden's index, agreement rate and Kappa value were larger in the group with AI support, and the average reading time was shorter (p < 0.01).ConclusionsThe AI support system might contribute to enhancing the diagnostic performance (e.g., higher sensitivity and AUC) of radiologists. In the future, the AI algorithm should be improved, and prospective studies should be conducted.
| S-EPMC9939225 | biostudies-literature
Project description:BackgroundMost women undergoing screening examinations in the U.S. do not receive immediate results and for many this results in increased stress, inconvenience, delayed diagnosis, and potential loss to follow-up.ObjectiveTo study the impact of same appointment mammogram results on breast cancer screening experience and patient satisfaction.Materials and methodsA 6-question survey with questions focused on breast cancer screening experience with our new service of same appointment mammogram results was distributed to 200 patients, with 185 patients returning their responses. Patients evaluated their current experience on receiving their screening results during the same appointment with their prior breast cancer screening experience. Patients who did not respond to their satisfaction score either before or after same appointment results were excluded from the patient cohort analyzing satisfaction score. Remaining questions were analyzed separately as additional satisfaction assessment tools.ResultsAbout 48% of the patients indicated an improvement in their screening experience with same appointment mammography results service, while 47% of the patients reported no significant difference in their experience.ConclusionAlthough not statistically significant, same appointment mammogram results were able to make a positive impact on breast cancer screening experience among 48% of the patients. Further research elucidating barriers to screening and other ways to improve patient satisfaction will be required to increase breast cancer screening compliance.
| S-EPMC9361536 | biostudies-literature
Project description:IntroductionHearing loss substantially impacts pediatric development, and early identification improves outcomes. While intervening before school-entry is critical to optimize learning, early-childhood hearing screening practices are highly variable. Conditioned play audiometry (CPA) is the gold standard for preschool hearing screening, but otoacoustic emission (OAE) testing provides objective data that may improve screening outcomes.ObjectivesTo compare outcomes of a community-based low-income preschool hearing program before and after implementation of OAE in a single-visit, two-tiered paradigm. We hypothesized that this intervention would reduce referral rates and improve follow-up while maintaining stable rates of diagnosed sensorineural hearing loss.MethodsWe performed a cohort study of 3257 children screened from July 2014-June 2016. Department of Public Health data were analyzed pre- and post-implementation of second-line OAE testing for children referred on CPA screening with targeted follow-up by DPH staff. Primary outcomes included referral rates, follow-up rates, and diagnosis of sensorineural hearing loss.ResultsDemographics, pure-tone pass rates, and incidence of newly-diagnosed permanent hearing loss were similar across years. After intervention, overall pass rates increased from 92% to 95% (P = 0.0014), while only 0.7% remained unable to be tested (P<0.0001). 5% of children were unable to be tested by CPA screening but passed OAE testing, obviating further evaluation. Referral rate decreased from 8% to 5% (P = 0.0014), and follow-up improved from 36% to 91% (P<0.0001). Identification of pathology in children with follow-up increased from 19% to over 50%. Further, disparities in pass rates and ability to test seen in Year 1 were eliminated in Year 2.Conclusion and relevanceIn a community setting, implementation of second-line OAE screening for CPA referrals reduced referral rates, increased identification of hearing loss, reduced outcome disparities, and improved follow-up rates. This study provides lessons in how to improve outcomes and reduce disparities in early-childhood hearing screening.
| S-EPMC6287830 | biostudies-literature
Project description:Mobile mammography vans (mammovans) may help close the gap to access of breast cancer screening by providing resources to underserved communities. Minimal data exists on the populations served, the ability of mammovans to reach underserved populations, and the outcomes of participants. We sought to determine the demographic characteristics, number of breast cancers diagnosed, and number of women who used the American Italian Cancer Foundation (AICF) Mobile, No-Cost Breast Cancer Screening Program within the five boroughs of New York City. Data were collected by the AICF from 2014 to 2019 on a voluntary basis from participants at each screening location. Women aged 40 to 79 years who had not had a mammogram in the previous 12 months were invited to participate. Each participant underwent a clinical breast exam by a nurse practitioner followed by a screening mammogram. Images were read by a board-certified radiologist contracted by the AICF from Multi Diagnostic Services. There were 32,350 participants in this study. Sixty-three percent reported an annual household income ≤$25,000, and 30% did not have health insurance. More than half of participants identified as either African American (28%) or Hispanic (27%). Additional testing was performed for 5359 women found to have abnormal results on screening. In total, 68 cases of breast cancer were detected. Breast cancer disparities are multifactorial, with the greatest factor being limited access to care. Mobile, no-cost mammogram screening programs show great promise in helping to close the gap to screening access.
| S-EPMC8782895 | biostudies-literature
Project description:BackgroundColorectal cancer (CRC) screening is recommended as an integral part of cancer survivorship care. We compared the rates of CRC screening among breast and prostate cancer survivors by primary cancer type, patient, and geographic characteristics in a community-based health-care system with a mix of large and small metro urban areas.Materials and methodsData for this retrospective study were abstracted from medical records of a multi-specialty practice serving about 250,000 individuals in southern Maryland. Breast (N = 1056) and prostate (N = 891) cancer patients diagnosed prior to 2015 were followed up till June 2018. Screening colonoscopy within the last 10 years was considered to be guideline concordant. Multivariate logistic regression was used to determine the prevalence odds ratios of being concordant on CRC screening by age, gender, race, metro area type, obesity, diabetes, and hypertension.ResultsOverall 51% of survivors had undergone a screening colonoscopy. However, there was a difference in CRC screening rate between prostate (54%) and breast (44%) cancer survivors. Older age (≥65 years), being a breast cancer survivor compared to prostate cancer, and living in a large compared to small metropolitan area were associated with a lower probability of receiving CRC screening. Having hypertension was associated with higher likelihood of being current on colonoscopy screening guidelines among survivors; but diabetes and obesity were not associated with CRC screening.ConclusionsLow levels of CRC screening utilization were found among breast and prostate cancer survivors in a single center in Southern Maryland. Gender, comorbidities, and residential factors were associated with receipt of CRC screening.
| S-EPMC7926020 | biostudies-literature
Project description: Not available
| S-EPMC10891403 | biostudies-literature