EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages
Researchers have developed EPPC-OASIS, a novel approach for extracting structured information from electronic patient-provider messages. This method uses ontology-aware adaptation and inference refinement to improve the accuracy and coherence of annotations. When tested on a de-identified corpus, the best performing pipeline achieved significant gains in F1 scores compared to existing baselines, suggesting its potential for scalable analysis of patient-provider communications. AI
IMPACT This new method could enable more scalable and accurate analysis of patient-provider communications, potentially improving healthcare insights.