Explaining Medical Time Series Classification Through Boundary-Aware Feature Analysis
Sirocchi C, Verda D (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 2830 CCIS
Pages Range: 105-119
Conference Proceedings Title: Communications in Computer and Information Science
Event location: Bologna, ITA
ISBN: 9783032167071
DOI: 10.1007/978-3-032-16708-8_9
Abstract
Borderline clinical cases, characterised by highly similar patient profiles but divergent outcomes, pose a persistent challenge in medical decision-making. Laboratory data from electronic health records can help trace temporal trajectories of disease progression and uncover subtle differences between such cases. However, their sparse, irregular, and asynchronous nature complicates analysis and calls for tailored methods. Recent efforts in modelling such data have primarily relied on deep learning architectures, which typically prioritise overall performance and often lack interpretability, particularly in difficult boundary cases. This study introduces a methodology to identify features and criteria associated with divergent outcomes in borderline cases. Medical time series are summarised into interpretable statistics and pairwise distances are computed to identify similar admissions with either the same or different outcomes. Feature-wise differences within these pairs are then used to train monotonic gradient boosting models that highlight key discriminative factors. Applied to hospital mortality prediction in two ICU cohorts, the approach shows that features relevant in borderline cases differ from those emphasised by models trained on all admissions. Rule extraction from shallow monotonic trees yields interpretable patterns associated with outcome divergence. These findings suggest that the proposed framework can contribute to the refinement of clinical guidelines and strengthen decision support in uncertain scenarios. The method implementation is openly available at: https://github.com/ChristelSirocchi/TS-XAI.
Authors with CRIS profile
Involved external institutions
Italy (IT)How to cite
APA:
Sirocchi, C., & Verda, D. (2026). Explaining Medical Time Series Classification Through Boundary-Aware Feature Analysis. In Pierangela Bruno, Francesco Calimeri, Giorgio Terracina, Francesco Cauteruccio, Mauro Dragoni, Fabio Stella (Eds.), Communications in Computer and Information Science (pp. 105-119). Bologna, ITA: Springer Science and Business Media Deutschland GmbH.
MLA:
Sirocchi, Christel, and Damiano Verda. "Explaining Medical Time Series Classification Through Boundary-Aware Feature Analysis." Proceedings of the 1st International Joint Workshop on Artificial Intelligence for Healthcare, and Hybrid Models for Coupling Deductive and Inductive Reasoning, HC@AIxIA+HYDRA 2025, Bologna, ITA Ed. Pierangela Bruno, Francesco Calimeri, Giorgio Terracina, Francesco Cauteruccio, Mauro Dragoni, Fabio Stella, Springer Science and Business Media Deutschland GmbH, 2026. 105-119.
BibTeX: Download