Related Experiment Video
Updated: Jan 25, 2026

Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
Published on: December 9, 2022
Decoding Data Science Upskilling: Insights From 5 Years of Data Science Projects at the Centers for Disease Control
Mayer Antoine1, Adebowale I Ojo, Mary Catherine Bertulfo
1Author Affiliations: Division of Workforce Development, National Center for State, Tribal, Local, and Territorial Public Health Infrastructure and Workforce (NCSTLTPHIW), Centers for Disease Control and Prevention (CDC), Atlanta, Georgia (Mr Antoine, Drs Ojo, Bertulfo, Okomo-Adhiambo, and Kirkcaldy), and United States Public Health Service, Rockville, Maryland (Dr Kirkcaldy).
Public health organizations are increasingly using data science, with projects focusing on visualization and AI/ML. Upskilling and modernization are needed to fully leverage these data science technologies.
Area of Science:
- Public Health Data Science
- Workforce Development
- Data Modernization
Background:
- Public health organizations recognize data science's potential.
- A knowledge gap exists regarding data science applications in public health.
Purpose of the Study:
- Provide a comprehensive overview of data science applications in public health settings.
- Describe characteristics of projects from the CDC's Data Science Upskilling (DSU) program (2019-2023).
- Guide future workforce development and data modernization efforts in public health data science.
Main Methods:
- Manual review of DSU applications and project presentations (2019-2023).
- Analysis of 112 projects based on domain, task, data science topic/method, data modality, tools, and programming languages.
- Tracking of trends in data science methodology adoption over five cohorts.
Main Results:
- Projects addressed infectious diseases (13%), COVID-19 (13%), and vaccines (11%).
- Data visualization (54%) and statistics (51%) were common; Artificial Intelligence (AI) and Machine Learning (ML) use increased from 33% (2019) to 56% (2023).
- Projects supported decision-making (52%) and process improvement (22%), utilizing R (55%), Python (56%), RStudio (50%), and Jupyter Notebooks (41%).
Conclusions:
- Prioritization of data visualization tools highlights needs for infrastructure and training.
- Increasing AI/ML adoption necessitates staff upskilling in these advanced methodologies.
- Effective data science integration requires strategic workforce development and data modernization.
Related Concept Videos
Psychology as a Science
The scientific method in psychology involves six critical steps: making observations, formulating hypotheses, conducting tests, analyzing...
Overview of Biostatistics in Health Sciences
Statistical Package for the Social Sciences (SPSS)
SPSS streamlines the process from data preparation to analysis and reporting. It is characterized by its user-friendly interface, which conceals...
How Data are Classified: Numerical Data
Quantitative data may be either discrete or continuous. All quantitative data that take on only specific numerical...
How Data are Classified: Categorical Data
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
Data Reporting and Recording

