Visualization for Infection Analysis and Decision Support in Hospitals.

Multridrug-resistant (MDR) bacteria are currently a serious threat to public health. They are primarily associated with hospital-acquired infections and their spread is related to an increase in the morbidity, mortality and healthcare cost. Therefore, their control and prevention is a priority problem today. In this control, the need of detecting MDR-bacteria outbreaks inside a hospital stands out. This complex process requires interweaving reports with temporal and spatial information. In this matter, computer-aided visualization techniques might play an important role, by helping explain and understand data-driven decision making. Thus, the hypothesis of this PhD thesis is that spatial-temporal modeling and visualization techniques allow clinicians to increase their confidence and comprehension of AI-based epidemiological analysis and prediction models. During the first phase of this PhD project, we have carried out a detailed analysis of what has been done on the application of spatial-temporal visualization techniques on epidemiological data. The results of this investigation have helped us identify the current trends and gaps in this field. Following this, we have implemented a simulation model and its simulator, with the objective of generating clinically realistic spatial-temporal data of infection outbreaks within hospitals.