Michael R. Anderson

Effectiveness of a Community Health Worker Intervention Among African American and Latino Adults With Type 2 Diabetes: A Randomized Controlled Trial

OBJECTIVES We tested the effectiveness of a culturally tailored, behavioral theory-based community health worker intervention for improving glycemic control. METHODS We used a randomized, 6-month delayed control group design among 164 African American and Latino adult participants recruited from 2 health systems in Detroit, Michigan. Our study was guided by the principles of community-based participatory research. Hemoglobin A1c (HbA1c) level was the primary outcome measure. Using an empowerment-based approach, community health workers provided participants with diabetes self-management education and regular home visits, and accompanied them to a clinic visit during the 6-month intervention period. RESULTS Participants in the intervention group had a mean HbA1c value of 8.6% at baseline, which improved to a value of 7.8% at 6 months, for an adjusted change of -0.8 percentage points (P < .01). There was no change in mean HbA1c among the control group (8.5%). Intervention participants also had significantly greater improvements in self-reported diabetes understanding compared with the control group. CONCLUSIONS This study contributes to the growing evidence for the effectiveness of community health workers and their role in multidisciplinary teams engaged in culturally appropriate health care delivery.

Racial and Ethnic Approaches to Community Health (REACH) Detroit Partnership: Improving Diabetes-Related Outcomes Among African American and Latino Adults

OBJECTIVES We sought to determine the effects of a community-based, culturally tailored diabetes lifestyle intervention on risk factors for diabetes complications among African Americans and Latinos with type 2 diabetes. METHODS One hundred fifty-one African American and Latino adults with diabetes were recruited from 3 health care systems in Detroit, Michigan, to participate in the Racial and Ethnic Approaches to Community Health (REACH) Detroit Partnership diabetes lifestyle intervention. The curriculum, delivered by trained community residents, was aimed at improving dietary, physical activity, and diabetes self-care behaviors. Baseline and postintervention levels of diabetes-specific quality-of-life, diet, physical activity, self-care knowledge and behaviors, and hemoglobin A1C were assessed. RESULTS There were statistically significant improvements in postintervention dietary knowledge and behaviors and physical activity knowledge. A statistically significant improvement in A1C level was achieved among REACH Detroit program participants (P<.0001) compared with a group of patients with diabetes in the same health care system in which no significant changes were observed (P=.160). CONCLUSIONS A culturally tailored diabetes lifestyle intervention delivered by trained community residents produced significant improvement in dietary and diabetes self-care related knowledge and behaviors as well as important metabolic improvements.

The Development, Implementation, and Process Evaluation of the REACH Detroit Partnership's Diabetes Lifestyle Intervention

PURPOSE The purpose of this article was to describe the development, implementation, and process evaluation findings of a culturally tailored diabetes lifestyle intervention for African Americans and Latinos. METHODS African American and Latino adults with type 2 diabetes from 3 health care systems in Detroit, Michigan, participated in diabetes lifestyle intervention of the Racial and Ethnic Approaches to Community Health Detroit Partnership. The intervention curricula were culturally and linguistically tailored for each population. Trained community residents delivered the curricula in 5 group meetings aimed at improving dietary, physical activity, and diabetes self-care behaviors of study participants. The aims of the process evaluation were to assess participant satisfaction with the intervention, utility, and applicability of information and cultural relevance of intervention materials. Content analysis was used to analyze qualitative data. Matrices were developed along thematic lines, and common themes were determined by grouping responses by question. RESULTS Ninety-eight percent of participants attended 1 or more intervention classes; 41% attended all 5 meetings. Attendance rates ranged from 59% to 88% for individual meetings. Participants reported that program information and activities were useful, culturally relevant, and applicable to diabetes self-management. Participants also appreciated the convenient community location for meetings and the social support received from other participants. CONCLUSIONS A community-based, culturally tailored diabetes lifestyle intervention delivered by trained community residents was associated with high participant satisfaction and retention.

Foofah: Transforming Data By Example

Data transformation is a critical first step in modern data analysis: before any analysis can be done, data from a variety of sources must be wrangled into a uniform format that is amenable to the intended analysis and analytical software package. This data transformation task is tedious, time-consuming, and often requires programming skills beyond the expertise of data analysts. In this paper, we develop a technique to synthesize data transformation programs by example, reducing this burden by allowing the analyst to describe the transformation with a small input-output example pair, without being concerned with the transformation steps required to get there. We implemented our technique in a system, FOOFAH, that efficiently searches the space of possible data transformation operations to generate a program that will perform the desired transformation. We experimentally show that data transformation programs can be created quickly with FOOFAH for a wide variety of cases, with 60% less user effort than the well-known WRANGLER system.

Does Gender Influence Participation?: Predictors of Participation in a Community Health Worker Diabetes Management Intervention With African American and Latino Adults

Purpose The purpose of the study was to determine the effects of gender on participation in a community-based, culturally tailored diabetes lifestyle intervention, led by trained community health workers (CHW) and conducted with African Americans and Latinos with type 2 diabetes. Methods This study utilized data collected from 180 participants. Multivariable binary and cumulative logistic regression models were used to analyze associations between gender and race/ethnicity with study completion and participation in 3 aspects of the intervention: group classes, CHW home visits, and CHW-accompanied doctor visits. Results Among Latinos, men were less likely than women to complete the study, attend group classes, and complete CHW home visits. There were no gender differences in participation seen among African Americans. Conclusions Diabetes management interventions may need to adapt their designs to optimize retention and participation of Latino men. Among African American men, the CHW model may be promising. Reasons for low participation among Latino men should receive more study. Future studies should assess whether similar findings apply in other communities and populations.

Bridging the gap between HPC and big data frameworks

Apache Spark is a popular framework for data analytics with attractive features such as fault tolerance and interoperability with the Hadoop ecosystem. Unfortunately, many analytics operations in Spark are an order of magnitude or more slower compared to native implementations written with high performance computing tools such as MPI. There is a need to bridge the performance gap while retaining the benefits of the Spark ecosystem such as availability, productivity, and fault tolerance. In this paper, we propose a system for integrating MPI with Spark and analyze the costs and benefits of doing so for four distributed graph and machine learning applications. We show that offloading computation to an MPI environment from within Spark provides 3.1−17.7× speedups on the four sparse applications, including all of the overheads. This opens up an avenue to reuse existing MPI libraries in Spark with little effort.

Input selection for fast feature engineering

The application of machine learning to large datasets has become a vital component of many important and sophisticated software systems built today. Such trained systems are often based on supervised learning tasks that require features, signals extracted from the data that distill complicated raw data objects into a small number of salient values. A trained systems success depends substantially on the quality of its features. Unfortunately, feature engineering-the process of writing code that takes raw data objects as input and outputs feature vectors suitable for a machine learning algorithm-is a tedious, time-consuming experience. Because “big data” inputs are so diverse, feature engineering is often a trial-and-error process requiring many small, iterative code changes. Because the inputs are so large, each code change can involve a time-consuming data processing task (over each page in a Web crawl, for example). We introduce Zombie, a data-centric system that accelerates feature engineering through intelligent input selection, optimizing the “inner loop” of the feature engineering process. Our system yields feature evaluation speedups of up to 8× in some cases and reduces engineer wait times from 8 to 5 hours in others.

Psychosocial Factors That Influence Health Care Use and Self-Management for African American and Latino Men With Type 2 Diabetes: An Exploratory Study

The purpose of this study was to explore the psychosocial factors that influence diabetes self-management and health care utilization among men of color with type 2 diabetes. Data were collected from focus groups with African American men (n = 9) and Latino men (n = 13) who were part of a diabetes intervention. Sessions were analyzed using thematic content analysis techniques. Five themes were discussed in focus groups, including (a) social support as a motivator, (b) patient–provider relationships as facilitators of healthy behaviors, (c) immigration status and access to resources, (d) waiting until symptoms became severe before seeking medical attention, and (e) structural barriers. Public health interventions may need to tailor interventions to address the specific needs of men of color.

On Orienting Edges of Unstructured Two- and Three-Dimensional Meshes

Finite element codes typically use data structures that represent unstructured meshes as collections of cells, faces, and edges, each of which require associated coordinate systems. One then needs to store how the coordinate system of each edge relates to that of neighboring cells. However, we can simplify data structures and algorithms if we can a priori orient coordinate systems in such a way that the coordinate systems on the edges follow uniquely from those on the cells by rule. Such rules require that every unstructured mesh allow the assignment of directions to edges that satisfy the convention in adjacent cells. We show that the convention chosen for unstructured quadrilateral meshes in the deal.II library always allows to orient meshes. It can therefore be used to make codes simpler, faster, and less bug prone. We present an algorithm that orients meshes in O(N) operations. We then show that consistent orientations are not always possible for 3D hexahedral meshes. Thus, cells generally need to store the direction of adjacent edges, but our approach also allows the characterization of cases where this is not necessary. The 3D extension of our algorithm either orients edges consistently, or aborts, both within O(N) steps.

When Adults with Diabetes Attempt to Drink Less Soda : Resulting Adult-Child Interactions and Household Changes

OBJECTIVE To examine adult-child interactions related to soda consumption in families where 1 inner-city African-American or Latino adult with diabetes is attempting lifestyle changes. METHODS The study used semistructured individual interviews of adults and a child (age 10-17) in their home. Interviews were audiotaped, transcribed, coded and analyzed for themes. RESULTS We completed 28 interviews (14 adult-child pairs). Most adults in this group reduced or stopped drinking nondiet soda. Some parents included their children in that change by removing nondiet soda from the household and by delivering messages regarding soda to their children. Some children obtained soda outside the home. Sweetened fruit drinks remained in some households even after nondiet soda was removed. Nonetheless, many children reported adjusting to the lack of soda in the household and a lower intake of nondiet soda and sweetened fruit drinks, in contrast to continued high consumption of sweets and fried food. CONCLUSIONS These in-depth family interviews suggest that interventions intended to change adult consumption of sugar-sweetened beverages may also benefit their children, and this hypothesis merits further investigation in larger studies. A new diabetes diagnosis may motivate adults toward dietary change and provide opportunities to improve overall family health. Healthcare providers should emphasize decreasing availability of soda for everyone in the home.