Explainable AI for inflammatory conditions
Philipps-Universität Marburg
Research project · 2024 study
The problem
Different inflammatory conditions can cause similar symptoms. The study examines what additional support can be obtained from blood parameters.
IAP’s contribution and approach
IAP carried out this research project for Philipps-Universität Marburg. The work combines myeloid-activation markers, blood-count parameters and CRP with explainable AI, focusing on interpretable distinctions for clinical assessment.
Result and development stage
The study reports 81.0% overall accuracy (95% confidence interval 72–87%) in distinguishing inflammatory conditions. Reported accuracies for bacterial infection, viral infection and autoimmune disease/GVHD are 90.3%, 80.0% and 79.0%. The study included 80 patients and 38 healthy controls with internal cross-validation. Broader clinical application requires larger, independent validation.
Sources and further information
Related services
Which decision do you want to improve?
In a free, non-binding 20-minute introductory discussion, we clarify your objective, starting point and a useful next step.