About the Project

VaSequIs is an interdisciplinary research project developing an AI-supported early warning system designed to detect and prevent infectious disease outbreaks. It is a cooperation of IKIM - AG Data Science with the Department for Medical Microbiology, the Department for Hygiene, the external partner Hygium. By combining data from patients with samples from drinking water and wastewater systems, the project aims to strengthen patient safety and improve hygiene monitoring in healthcare environments.

Monitoring Health Through Environmental Data

The project uses advanced sequencing methods to analyze samples collected from patient care settings as well as from drinking water and wastewater infrastructure. Samples are taken at critical connection points between public water supply networks, hospital systems, and wastewater pipelines. Automated sampling technology enables continuous collection over extended periods, providing reliable data on pathogens circulating within healthcare environments. This approach offers valuable insights into infection dynamics beyond traditional clinical testing alone.

From Analysis to Prediction

Samples are examined using molecular biological analysis and genome sequencing to identify viruses and bacteria and track their occurrence over time. These data are then analyzed using artificial intelligence to detect patterns and forecast potential outbreaks. Early identification of emerging risks allows hygiene specialists to act proactively, supporting prevention rather than reaction. This contributes to the development of a comprehensive monitoring framework focused on protecting patients.

Overview

Practical Impact

The project integrates microbiological, epidemiological, and data science methods into a unified approach that directly informs hygiene management and regulatory practice. By linking research findings with real-world implementation, VaSequIs advances modern infection prevention strategies and supports safer healthcare environments.

Vision

VaSequIs represents a forward-looking model for infection control that connects environmental monitoring, clinical data, and artificial intelligence. Its goal is to shift healthcare systems toward proactive prevention and improved public health resilience.

Funding

Project Team

  • PI: Prof. Dr. Jan Buer
  • Co-PI: Prof. Dr. Folker Meyer
  • Co-PI: PD. Dr. Jan Kehrmann
  • Co-PI: Dr. Robin Otchwemah
  • Co-PI: Prof. Dr. Dr. Martin Exner



Data Science