Hierarchical classification for differential diagnosis of fever of unknown origin: A multi-task learning approach with self-adaptive representation sharing.

Abstract

Leveraging label dependencies as prior knowledge during both training and testing has proven valuable across diverse domains such as image annotation and text categorization. In our previous research, we successfully reframed the clinical challenge of aiding decision-making for patients with fever of unknown origin (FUO) as a hierarchical classification problem, validating its feasibility through local methods. However, these approaches still encounter challenges, including high training costs and potential error propagation during predictions. Moreover, existing global approaches for exploiting label dependencies impose strict prerequisites-such as fixed data modalities, manual specification of information-sharing directions, and equal-length label sequences-that limit their applicability to FUO etiologies. In this paper, we introduce a novel global hierarchical classification method based on a multi-task learning architecture for the early diagnosis of FUO patients. Our method leverages multimodal clinical data and a predefined label hierarchy and comprises three key components: a task decomposition strategy employing End-of-Sequence (EOS) markers (with each parent node in the label hierarchy corresponding to an individual classification task), a multimodal data feature extraction and fusion module, and a self-adaptive representation sharing module (Sa-RSM). We evaluated our approach on an experimental dataset extracted from electronic health records (EHRs) of a large-scale tertiary hospital in China, spanning January 2011 to October 2020 and comprising 34,051 hospital admissions of 30,794 FUO patients. Our results clearly demonstrate that the proposed method not only achieves superior predictive performance but also proactively halts predictions at coarser-grained classification tasks. Moreover, even in cases of misclassification, our method exhibits lower mistake severity, underscoring its potential clinical utility.