# bernard2015visual
# A Visual-Interactive System for Prostate Cancer Cohort Analysis
Concept
This paper presents an interactive visualization system for analyzing cohorts of prostate cancer patients as shown in Figure 1 [1]. Prostate cancer often progresses slowly, in many cases patient's (especially seniors) life quality is unaffected by the tumor. Bernard et al. collaborated with two prostate cancer experts and developed the system to help clinicians make accurate clinical decisions by balancing side effects and expected results of performing a surgery.
Implementation
Figure 1 shows an overview of the proposed system that supports the visualization of a cohort of patients. Patient attributes such as results from diagnosis, clinical events and measurements, are visualized on the left and right side. The center view is the Patient View that visualizes the current patient cohort, different phases are color coded to help clinicians identify potential correlations between phases and attributes. At the bottom, a history function enables the user to revisit pervious cohorts.
Figure 2 shows the Patient View with sorting and filtering functions, the user is able to activate them by brushing on the patient list to focus on specific similarities and to obtain a fine-grained cohort.
Related Work
The authors review the approaches proposed in the survey of interactive visualization systems of EHR by Rind et al. [2]. The use of glyphs is inspired by Borgo et al. [3].
Overall user interface and interactive function designs are inspired by previous EHR systems such as LifeLine2 [4] and DICON [5]. StratomeX [6] is a statistical technique for identifying and refining meaningful patient cohorts, which is used by the authors to reveal relations between multiple datasets.
Data Characteristics
- Data source: University Medical Center Hamburg-Eppendorf
- Size: 16,000 patients
- Spatial dimensionality: 2D
- Temporal dimensionality: static
- Type: multivariate
Papers Cited
13
Cites Glyph-Based Visualization: Foundations, Design Guidelines, Techniques and Applications
Years Spanned
2009-2015
Application Domain
- Electronic Health Record Visualization
- Medical focus: Oncology - Prostate Cancer
Reference
Bernard, J., Sessler, D., May, T., Schlomm, T., Pehrke, D., & Kohlhammer, J. (2015). A visual-interactive system for prostate cancer cohort analysis. IEEE Computer Graphics and Applications, 35(3), 44–55. https://doi.org/10.1109/MCG.2015.49 ↩︎
Rind, A., Wang, T. D., Aigner, W., Miksch, S., Wongsuphasawat, K., Plaisant, C., & Shneiderman, B. (2011). Interactive Information Visualization to Explore and Query Electronic Health Records. Foundations and Trends® in Human–Computer Interaction, 5(3), 207–298. https://doi.org/10.1561/1100000039 ↩︎
Borgo, R., Kehrer, J., Chung, D. H. S., Maguire, E., Laramee, R. S., Hauser, H., … Chen, M. (2013). Glyph-based Visualization: Foundations, Design Guidelines, Techniques and Applications. Eurographics State of the Art Reports. https://doi.org/10.2312/conf/EG2013/stars/039-063 ↩︎
Plaisant, C., Mushlin, R., Snyder, A., Li, J., Heller, D., & Shneiderman, B. (1998). LifeLines: using visualization to enhance navigation and analysis of patient records. Proceedings / AMIA ... Annual Symposium. AMIA Symposium. ↩︎
DICON: Interactive visual analysis of multidimensional clusters. IEEE Transactions on Visualization and Computer Graphics. https://doi.org/10.1109/TVCG.2011.188 ↩︎
Turkay, C., Lex, A., Streit, M., Pfister, H., & Hauser, H. (2014). Characterizing cancer subtypes using dual analysis in Caleydo StratomeX. IEEE Computer Graphics and Applications. https://doi.org/10.1109/MCG.2014.1 ↩︎