Interactive visual analytics for medical data: application to COVID-19 clinical information during the first wave
- José M. Enguita 3
- Diego García 3
- María D. Chiara 12
- Nuria Valdés 24
- Ana González 3
- Abel A. Cuadrado 3
- Ignacio Díaz 3
- 1 Institute of Sanitary Research of the Principado de Asturias
-
2
Hospital Universitario Central de Asturias
info
- 3 University of Oviedo, Dept of Electrical Engineering
- 4 Department of Internal Medicine, Section of Endocrinology and Nutrition
Año de publicación: 2022
Congreso: European Symposium on Artificial Neural Networks, Computational Intelligence andMachine Learning (ESANN) (2022. Bruges, Belgium)
Tipo: Aportación congreso
Resumen
Biomedical data recorded as a result of clinical practiceare often multi-domain –involving lab measurements, medication, patientattributes, logistic information–, and also highly unstructured, with highrates of missing data and asynchronously sampled measurements. In thisscenario, we need tools capable of providing a broad picture prior to moredetailed analyses. We present here a visual analytics approach that usesthe morphing projections technique to combine the visualization of a t-SNEprojection of clinical time series, with views of other clinical or patient’sinformation. The proposed approach is demonstrated on an applicationcase study of COVID-19 clinical information taken during the first wave.
Información de financiación
This work is part of Grant PID2020-115401GB-I00 funded by MCIN/AEI/ 10.13039/501100011033.Financiadores
-
Ministerio de Ciencia e Innovación
Spain
- PID2020-115401GB-I00