Taking Action With Data: Improving Environmental Public Health at the Community Level.

CONTEXT: The Wisconsin Environmental Public Health Tracking Program (Wisconsin Tracking) compiles and provides data on health endpoints and related environmental exposures as a resource to local health departments, tribes, academia, and other stakeholders. The goal of providing these data is that stakeholders use them to develop projects that improve environmental health in their communities-that is, moving from "data to action." OBJECTIVE: To encourage use of Wisconsin Tracking data, we developed a minigrants program and issued a funding opportunity to local health departments and tribes. The opportunity requested proposals for small projects using our data, with the goal of making public health improvements in those communities. Wisconsin Tracking evaluated the minigrants program after its completion. DESIGN/SETTING: Eight local health departments in Wisconsin were awarded up to $10 500 to develop and implement projects over a 9-month period. METHODS: Wisconsin Tracking created a funding opportunity announcement requiring utilization of our data to develop projects by local health departments in Wisconsin. We reviewed and scored applications, evaluating proposals on a range of criteria. During the 9-month project period, Wisconsin Tracking staff members provided a variety of technical assistance to grantees. An evaluation of the overall program followed. RESULTS: Funded communities used Wisconsin Tracking data to improve public health infrastructure, leverage partnerships, establish new initiatives, respond to emergencies, improve communication with stakeholders and residents, and make a variety of public health improvements in their communities. CONCLUSIONS: Efforts to increase use of our data catalyzed development of small-scale environmental health projects. This minigrants program was successful at building relationships between local health departments and Wisconsin Tracking, increasing awareness of Wisconsin Tracking data and resources, and contributing to numerous documented public health improvements throughout Wisconsin.

Classifying publications from the clinical and translational science award program along the translational research spectrum: a machine learning approach.

BACKGROUND: Translational research is a key area of focus of the National Institutes of Health (NIH), as demonstrated by the substantial investment in the Clinical and Translational Science Award (CTSA) program. The goal of the CTSA program is to accelerate the translation of discoveries from the bench to the bedside and into communities. Different classification systems have been used to capture the spectrum of basic to clinical to population health research, with substantial differences in the number of categories and their definitions. Evaluation of the effectiveness of the CTSA program and of translational research in general is hampered by the lack of rigor in these definitions and their application. This study adds rigor to the classification process by creating a checklist to evaluate publications across the translational spectrum and operationalizes these classifications by building machine learning-based text classifiers to categorize these publications. METHODS: Based on collaboratively developed definitions, we created a detailed checklist for categories along the translational spectrum from T0 to T4. We applied the checklist to CTSA-linked publications to construct a set of coded publications for use in training machine learning-based text classifiers to classify publications within these categories. The training sets combined T1/T2 and T3/T4 categories due to low frequency of these publication types compared to the frequency of T0 publications. We then compared classifier performance across different algorithms and feature sets and applied the classifiers to all publications in PubMed indexed to CTSA grants. To validate the algorithm, we manually classified the articles with the top 100 scores from each classifier. RESULTS: The definitions and checklist facilitated classification and resulted in good inter-rater reliability for coding publications for the training set. Very good performance was achieved for the classifiers as represented by the area under the receiver operating curves (AUC), with an AUC of 0.94 for the T0 classifier, 0.84 for T1/T2, and 0.92 for T3/T4. CONCLUSIONS: The combination of definitions agreed upon by five CTSA hubs, a checklist that facilitates more uniform definition interpretation, and algorithms that perform well in classifying publications along the translational spectrum provide a basis for establishing and applying uniform definitions of translational research categories. The classification algorithms allow publication analyses that would not be feasible with manual classification, such as assessing the distribution and trends of publications across the CTSA network and comparing the categories of publications and their citations to assess knowledge transfer across the translational research spectrum.

Domestic abuse during the previous year in a sample of postpartum women.

OBJECTIVE: To determine the prevalence and the correlates of domestic abuse in women presenting for a postpartum visit. DESIGN: Data were collected via a cross-sectional survey. Multivariate logistic regression was used to determine characteristics of women reporting abuse. SETTING: Thirty-five obstetric clinics in Wisconsin. PARTICIPANTS: One thousand five hundred nineteen women who presented for a postpartum visit. Most were White, well educated, employed, and married. MAIN OUTCOME MEASURE: Physical and/or emotional abuse in the previous 12 months. RESULTS: One hundred twelve (7.4%) women were victims of abuse. Women who reported abuse were more likely to screen positive for postpartum depression (odds ratio 4.21, 95% confidence interval 2.19-8.09) be unmarried (odds ratio 7.05, 95% confidence interval 3.39-14.64), be older than 35 year (odds ratio 2.45, 95% confidence interval 1.10-5.50), be not in the labor force (odds ratio 2.39, 95% confidence interval 1.16-4.90), be of Hispanic ethnicity (odds ratio 2.73, 95% confidence interval 1.07-6.96), and have a partner who binge drinks (odds ratio 3.09, confidence interval 1.49-6.43). CONCLUSIONS: One in 14 women who present for a postpartum visit report emotional or physical abuse in the previous year. Although certain factors are more highly associated with domestic abuse, the high prevalence of abuse in this population supports the use of routine screening of women for domestic abuse.