Investigating ECG Diagnosis with Ambiguous Labels using Partial Label Learning

TL;DR

This study systematically evaluates partial label learning methods for ECG diagnosis, addressing label ambiguity issues inherent in real-world clinical data and highlighting their varying robustness and limitations.

Contribution

First comprehensive analysis of PLL algorithms applied to ECG diagnosis, exploring their effectiveness under diverse ambiguity scenarios and identifying key challenges.

Findings

PLL methods show varied robustness to ambiguity types

Current PLL approaches have notable limitations in clinical settings

Insights guide future development of ambiguity-aware ECG models

Abstract

Label ambiguity is an inherent problem in real-world electrocardiogram (ECG) diagnosis, arising from overlapping conditions and diagnostic disagreement. However, current ECG models are trained under the assumption of clean and non-ambiguous annotations, which limits both the development and the meaningful evaluation of models under real-world conditions. Although Partial Label Learning (PLL) frameworks are designed to learn from ambiguous labels, their effectiveness in medical time-series domains, ECG in particular, remains largely unexplored. In this work, we present the first systematic study of PLL methods for ECG diagnosis. We adapt nine PLL algorithms to multi-label ECG diagnosis and evaluate them using a diverse set of clinically motivated ambiguity generation strategies, capturing both unstructured (e.g., random) and structured ambiguities (e.g., cardiologist-derived similarities, treatment relationships, and diagnostic taxonomies). Our experiments on the PTB-XL and Chapman datasets demonstrate that PLL methods vary substantially in their robustness to different types and degrees of ambiguity. Through extensive analysis, we identify key limitations of current PLL approaches in clinical settings and outline future directions for developing robust and clinically aligned ambiguity-aware learning frameworks for ECG diagnosis.