Automated Differential Time to Positivity Analysis for CRBSIs Using Historical Microbiological Data.

Catheter-related bloodstream infections (CRBSIs) are often difficult to diagnose due to the variability of pathogen sources and inconsistencies in laboratory data. Differential time to positivity (DTP) offers a means to distinguish CRBSIs from secondary bacteremia, but its practical application is complicated by heterogeneous nomenclature and variable reporting formats. We implemented an algorithm that standardizes microbiological records using a custom ontology-driven framework and applies clinically established thresholds. A fuzzy matching approach was then used to classify infections as likely catheter-related, unlikely, or non-diagnostic. This proof-of-concept validates the feasibility of automated DTP analysis and highlights the potential of semantic technologies to support clinical decision-making.