Next Visit Diagnosis Prediction via Medical Code-Centric Multimodal Contrastive EHR Modelling with Hierarchical Regularisation

arXiv:2401.11648v4 Announce Type: replace
Abstract: Predicting next visit diagnosis using Electronic Health Records (EHR) is an essential task in healthcare, critical for devising proactive future plans for both healthcare providers and patients. Nonetheless, many preceding studies have not sufficiently addressed the heterogeneous and hierarchical characteristics inherent in EHR data, inevitably leading to sub-optimal performance. To this end, we propose NECHO, a novel medical code-centric multimodal contrastive EHR learning framework with hierarchical regularisation. First, we integrate multifaceted information encompassing medical codes, …

abstract arxiv code cs.ai cs.ir cs.lg diagnosis ehr electronic electronic health records future health healthcare healthcare providers hierarchical medical modelling multimodal next patients prediction records studies type via