We want to test whether clustering impacts a user's preference on a list of mini graphs (subgraphs) and if so, we will continue to research and conduct future studies on their impact.

We are exploring what primary care physicians feel is important for them to know about nutrition given their clinical experience, how they would have liked to learn nutrition during their medical training, and desired ways to support them in providing nutrition care in their current practice. We are also evaluating a tool that may make nutrition counseling easier and more efficient for providers. The results of the study can potentially lead to improvements in nutrition training in medicine and quality of nutrition care.

To identify the skills needed to effectively manage a medical laboratory in today's healthcare system and to assess the gap in management training in new laboratory leaders.

The goal of the study is to examine how North Carolina school districts spent funds made available through the Elementary and Secondary School Emergency Relief legislation.

The purpose of this project is to gather information from different group to adapt a community-based treatment intervention for community-dwelling individuals with psychosis in Malawi. In this study, we will interview patients, caregivers, community leaders, traditional healers, and clinicians to better tailor this treatment approach to address the needs of this population

We aim to develop, field-test, and promote improved ways to measure and assess the public health hazards associated with sanitation systems and practices in sub-Saharan Africa, with the overall goal of informing sanitation planning and implementation at community levels. This will involve learning more about the range and distribution of sanitation technologies encountered in two cities of Africa (i.e., Kampala and Lusaka). Learning more about the levels of microbiological hazard in onsite sanitation systems especially septic tanks and other technology-specific lessons can be usefully incorporated in citywide sanitation improvement tools.

To learn if one kind of treatment approach, either (1) endoscopic surveillance or (2) endoscopic eradication therapy, is better, the same, or worse for treating patients with Barrett's esophagus and low-grade dysplasia.

This is a study evaluating whether the use of an electronic web-based tool containing surveys could support patients and doctors make better treatment decisions together. New patients, 60 years or older, will be randomized to either receive the tool or not. Surveys will be collected from patients about their experience in making treatment decisions to evaluate whether the tool was beneficial.

To develop an artificial intelligence (AI) and machine learning (ML) process focused on physicians' variability during the pre-treatment peer review processes and assess the impact of the process in the RT work system on patient safety.

Predictive modeling has recently attracted a lot of attention from organizations trying to leverage AI and big data to improve their work processes such as decision-making. However, real-world problems are rarely well-formulated machine learning problems. Practitioners have to supply a well-defined predictive target to operationalize a predictive model. In such cases, they often resort to using observed variables to approximate the actual construct of interest. For example, people have used high sales numbers as a proxy for a good employee. Proxy label selection is a recurring challenge when predictive ML is applied to real-world problems. The purpose of this interview study is to understand how ML practitioners select proxy labels, evaluate proxy labels, and iterate through the different tasks involved.