Community Corner

Brooke Patterson

1. What are your current research interests?

My current research interests center on the intersection of health systems, data analytics, and equity in care delivery. Specifically, I’m focused on optimizing data-driven decision-making in healthcare through better data governance, interactive dashboards, and predictive analytics. I’m also interested in evaluating the effectiveness of healthcare interventions in real-world settings, particularly through the lens of implementation science. Building on my background in global and public health, I’m passionate about leveraging data to close gaps in care and improve health outcomes across diverse populations.

2. How do you define Data Science?

I define Data Science as the multidisciplinary practice of extracting actionable insights from structured and unstructured data using statistical analysis, machine learning, and domain expertise. It encompasses the entire pipeline—from data collection and cleaning to analysis, visualization, and interpretation. In my field, data science is a tool for improving clinical decision-making, streamlining operations, and enhancing patient outcomes. It also plays a crucial role in ensuring that research findings are both meaningful and translatable into real-world solutions.

3. Can you share an interesting or surprising result you’ve found in your data?

One surprising finding came during a project analyzing treatment modalities and survival outcomes in pancreatic cancer. We discovered that delays in treatment initiation, even when adjusted for cancer stage and demographics, had a measurable impact on survival—highlighting systemic issues in access to timely care. This reinforced the importance of not only clinical decisions but also health system logistics in patient outcomes. The findings underscored the value of real-world evidence and the potential of data science to uncover actionable insights that might not be immediately obvious from clinical trials alone.

4. Are there any interesting new tools or libraries you or your students have been using?

Yes, recently I've been incorporating dbt (data build tool) into our data transformation workflows, which has significantly improved our data pipeline transparency and version control. One particularly impactful enhancement has been setting up an ODBC connection between SQL Server and R. This has substantially reduced data processing time and allowed for more seamless querying and analysis of large datasets directly within R. It’s improved the efficiency of our workflows, especially when working with real-time or high-volume healthcare data. Our team has also been fine tuning the Additionally, we’ve been working on expanding our LHS data dictionary to make it more user friendly. 

5. What are you most excited about in the field of data science in the next 5 years?

I’m most excited about the growing convergence of data science and health equity, especially the use of predictive models to proactively identify and address disparities in healthcare. The rise of explainable AI (XAI) also excites me—helping bridge the gap between advanced models and clinician trust. Additionally, as more health systems adopt interoperable EHRs and standardized data structures, we’ll be better equipped to perform real-time analytics and support precision public health initiatives, as well as collaborate in more federated learning enviornments. The increasing democratization of data tools will empower more professionals—regardless of technical background—to engage in meaningful analytics.