# A Survey of Visual Analytics for Public Health
Preim and Lawonn review the existing visual analytics solutions for supporting public health (PH) . PH datasets often contain temporal and spatial dimensions, this requires visual analytics techniques to provide support for PH decision-making.
The authors classify visual analytics solutions based on the visualization techniques (shown in Table 4) and analytics components (shown in Table 5).
The authors use Regression Analysis as a means to identify and characterize associations between lifestyle, exposition to risk factors and diseases.
The authors define Multiple Imputations as the computation of dependencies between variables and the generation of multiple replacements.
- PH data are often heterogeneous and imperfect in quality, this often requires customized solutions.
- Flexible combinations of the spatial and temporal dimension are important for PH decision-making, this requires advanced interactive visual interfaces to accommodate the user.
- Existing solutions do not provide an integrated data management feature, data from multiple sources require manual aggregation and validation.
- Existing solutions lack user guidance for their advanced VA and VIS features, PH professionals may not be able to explore existing features fully.
- Existing solutions lack long-term evaluation strategies, future improvements are therefore difficult to design.
- There is little research on how visual analytics may help to identify, assess or counteract quality problems in PH data.
Visual Analytics of Public Health Data
Preim, B., & Lawonn, K. (2020). A Survey of Visual Analytics for Public Health. Computer Graphics Forum, 39(1), 543–580. https://doi.org/10.1111/cgf.13891 ↩︎