Dataset Information

Engaging diverse underserved communities to bridge the mammography divide.

ABSTRACT: BACKGROUND:Breast cancer screening continues to be underutilized by the population in general, but is particularly underutilized by traditionally underserved minority populations. Two of the most at risk female minority groups are American Indians/Alaska Natives (AI/AN) and Latinas. American Indian women have the poorest recorded 5-year cancer survival rates of any ethnic group while breast cancer is the number one cause of cancer mortality among Latina women. Breast cancer screening rates for both minority groups are near or at the lowest among all racial/ethnic groups. As with other health screening behaviors, women may intend to get a mammogram but their intentions may not result in initiation or follow through of the examination process. An accumulating body of research, however, demonstrates the efficacy of developing 'implementation intentions' that define when, where, and how a specific behavior will be performed. The formulation of intended steps in addition to addressing potential barriers to test completion can increase a person's self-efficacy, operationalize and strengthen their intention to act, and close gaps between behavioral intention and completion. To date, an evaluation of the formulation of implementation intentions for breast cancer screening has not been conducted with minority populations. METHODS/DESIGN:In the proposed program, community health workers will meet with rural-dwelling Latina and American Indian women one-on-one to educate them about breast cancer and screening and guide them through a computerized and culturally tailored "implementation intentions" program, called Healthy Living Kansas-Breast Health, to promote breast cancer screening utilization. We will target Latina and AI/AN women from two distinct rural Kansas communities. Women attending community events will be invited by CHWs to participate and be randomized to either a mammography "implementation intentions" (MI2) intervention or a comparison general breast cancer prevention informational intervention (C). CHWs will be armed with notebook computers loaded with our Healthy Living Kansas-Breast Health program and guide their peers through the program. Women in the MI2 condition will receive assistance with operationalizing their screening intentions and identifying and addressing their stated screening barriers with the goal of guiding them toward accessing screening services near their community. Outcomes will be evaluated at 120-days post randomization via self-report and will include mammography utilization status, barriers, and movement along a behavioral stages of readiness to screen model. DISCUSSION:This highly innovative project will be guided and initiated by AI/AN and Latina community members and will test the practical application of emerging behavioral theory among minority persons living in rural communities.

SUBMITTER: Engelman KK

PROVIDER: S-EPMC3036625 | biostudies-literature | 2011 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Engaging diverse underserved communities to bridge the mammography divide.

Engelman Kimberly K KK Cupertino Ana Paula AP Daley Christine M CM Long Trish T Cully Angelia A Mayo Matthew S MS Ellerbeck Edward F EF Geana Mugur V MV Greiner Allen A

BMC public health 20110121

<h4>Background</h4>Breast cancer screening continues to be underutilized by the population in general, but is particularly underutilized by traditionally underserved minority populations. Two of the most at risk female minority groups are American Indians/Alaska Natives (AI/AN) and Latinas. American Indian women have the poorest recorded 5-year cancer survival rates of any ethnic group while breast cancer is the number one cause of cancer mortality among Latina women. Breast cancer screening rat ...[more]

PMID: 21255424

Similar Datasets

Project description:Breast cancer claims 11,400 lives on average every year in the UK, making it one of the deadliest diseases. Mammography is the gold standard for detecting early signs of breast cancer, which can help cure the disease during its early stages. However, incorrect mammography diagnoses are common and may harm patients through unnecessary treatments and operations (or a lack of treatment). Therefore, systems that can learn to detect breast cancer on their own could help reduce the number of incorrect interpretations and missed cases. Various deep learning techniques, which can be used to implement a system that learns how to detect instances of breast cancer in mammograms, are explored throughout this paper. Convolution Neural Networks (CNNs) are used as part of a pipeline based on deep learning techniques. A divide and conquer approach is followed to analyse the effects on performance and efficiency when utilising diverse deep learning techniques such as varying network architectures (VGG19, ResNet50, InceptionV3, DenseNet121, MobileNetV2), class weights, input sizes, image ratios, pre-processing techniques, transfer learning, dropout rates, and types of mammogram projections. This approach serves as a starting point for model development of mammography classification tasks. Practitioners can benefit from this work by using the divide and conquer results to select the most suitable deep learning techniques for their case out-of-the-box, thus reducing the need for extensive exploratory experimentation. Multiple techniques are found to provide accuracy gains relative to a general baseline (VGG19 model using uncropped 512 × 512 pixels input images with a dropout rate of 0.2 and a learning rate of 1 × 10-3) on the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) dataset. These techniques involve transfer learning pre-trained ImagetNet weights to a MobileNetV2 architecture, with pre-trained weights from a binarised version of the mini Mammography Image Analysis Society (mini-MIAS) dataset applied to the fully connected layers of the model, coupled with using weights to alleviate class imbalance, and splitting CBIS-DDSM samples between images of masses and calcifications. Using these techniques, a 5.6% gain in accuracy over the baseline model was accomplished. Other deep learning techniques from the divide and conquer approach, such as larger image sizes, do not yield increased accuracies without the use of image pre-processing techniques such as Gaussian filtering, histogram equalisation and input cropping.

Project description:BackgroundThere are more than 18 million cancer survivors in the United States. Yet, survivors of color remain under-represented in cancer survivorship research (Saltzman et al. in Contemp Clin Trials Commun 29:100986, 2022; Pang et al. in J Clin Oncol 34:3992-3999, 2016; Lythgoe et al. in Prostate Cancer Prostatic Dis 24:1208-1211, 2021). Our long-term goal is to enroll and follow a cohort of historically under-represented cancer survivors, to better understand modifiable risk factors that influence clinical and quality of life outcomes in these populations. Towards that goal, we describe herein how we applied community-based participatory research approaches to develop inclusive study materials for enrolling such a cohort.MethodsWe implemented community engagement strategies to inform and enhance the study website and recruitment materials for this cohort including: hiring a dedicated engagement coordinator/community health educator as a member of our team; working with the Helen Diller Family Comprehensive Cancer Center Office of Community Engagement (OCE) and Community Advisory Board members; presenting our educational, research, and study recruitment materials at community events; and establishing a community advisory group specifically for the study (4 individuals). In parallel with these efforts, 20 semi-structured user testing interviews were conducted with diverse cancer survivors to inform the look, feel, and usability of the study website.ResultsEngagement with community members was a powerful and important approach for this study's development. Feedback was solicited and used to inform decisions regarding the study name (eat move sleep, EMOVES), logo, study website content and imagery, and recruitment materials. Based on community feedback, we developed additional educational materials on healthy groceries and portion size in multiple languages and created a study video.ConclusionsIncluding an engagement coordinator as a permanent team member, partnering with the institutional community outreach and engagement resources (i.e., OCE), and allocating dedicated time and financial support for cultivating relationships with stakeholders outside the university were critical to the development of the study website and materials. Our community guided strategies will be tested as we conduct enrollment through community advisor networks and via the state cancer registry.

Dataset Information

Engaging diverse underserved communities to bridge the mammography divide.

Publications

Engaging diverse underserved communities to bridge the mammography divide.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets