As the lead of the Visualization Methodology and Evaluation work package, we will develop novel interactive visualization techniques based on an initial requirements analysis. Users will be able to analyze patient risk factors using the newly developed visualizations. In addition, a dashboard for risk monitoring with an alarm function will be implemented.

As a partner of the Digital Demonstrator App for Risk Analysis and Prediction work package, we will implement an interface and visualizations to make general risk analysis features and specific prediction models accessible to users.

As a partner of the Digital Demonstrator for (Semi)-Automated Surveillance Across Hospitals work package, we will develop a browser-based application to visualize and analyze HOB surveillance indicators. In the next step, the application will be expanded with benchmarking methods to enable comparisons with aggregates.

About the project:

Healthcare-associated infections (HAI), including nosocomial bacteremia (HOB, hospital-onset bacteremia), pose a significant burden on affected patients, healthcare personnel, and society as a whole. This longstanding and globally escalating problem is also referred to as an insidious pandemic. HAI prevention is a crucial aspect of patient safety, firmly embedded in actionable patient safety solutions. Risk-oriented interventions necessitate standardized and structured data, knowledge, and evidence. Consequently, experts can benefit from computerized risk assessment based on standardized and integrated data analysis from various sources, presented in a machine-readable format.

The RISK PRINCIPE project focuses on nosocomial bacteremia (HOB). Building upon interoperable data, algorithms, tools, and system components are being developed, combined with infection control expertise. The aim is to create a reporting and surveillance app, as well as a risk prediction app. RISK PRINCIPE leverages the expertise of diverse disciplines and utilizes the findings from infection use cases within the German Medical Informatics Initiative (MII) (HiGHmed, SMITH). By harmonizing the data models of the Medical Data Integration Centers, convergence towards the MII core data set and its extensions, particularly in the field of microbiology, is promoted, contributing to the interoperability working group. The expertise of all MII consortia is incorporated, as confirmed by endorsement letters (DIFUTURE, HiGHmed, MIRACUM, SMITH).

Sustainability and transferability of the developed solutions are guiding principles. The joint outcome will bridge the gap between individual risk assessment, HOB, and general infection control measures by providing a timely and robust system that aligns with user requirements. In summary, the goal of RISK PRINCIPE is the development and implementation of automated surveillance and data-driven risk prediction of HOB, including visualization. Therefore, the central focus lies on effective and efficient infection prevention.