EXPLIMED 2025
Explainable Artificial Intelligence for the Medical Domain 2025

Table of Contents

• Preface
  Summary: There were 24 papers submitted for peer-review to this workshop. Out of these, 15 papers were accepted for this volume, 13 as regular papers and 2 as short papers.

Session 1

• Federated Inductive Logic Programming for Explainable Artificial Intelligence
  Yasmine Akaichi, Jean-Marie Jacquet, Isabelle Linden, Wim Vanhoof
• Massive Activations in Graph Neural Networks: Decoding Attention dor Domain-Dependent Interpretability
  Lorenzo Bini, Marco Sorbi, Stephane Marchand-Maillet
• Comparative Plausibility Evaluation of Heatmaps for Vision Transformers in Digital Mammography
  Ramsha Aasim, Ghada Zamzmi, Jana G. Delfino, Joseph Jaja, Miguel A. Lago
• High Cost, Low Trust? MSA-PNet Fixes Both for Medical Imaging
  Dost Muhammad, Muhammad Salman, Malika Bendechache
• CRISP-NAM: Competing Risk Interpretable Survival Prediction with Neural Additive Models
  Dhanesh Ramachandram, Ananya Raval

Session 2

• An Interpretable Prototype Parts-based Neural Network for Medical Tabular Data
  Jacek Karolczak, Jerzy Stefanowski
• Using Design Thinking for Explainable AI: A Case Study Predicting the Start of the Palliative Phase in Patients with COPD or Heart Failure
  Iris Heerlien, Jeroen Linssen, Lorenzo Gatti, Maya Sappelli, Betsie Van Gaal, Richard Evering, Noah Letwory
• Evaluation of Explainable AI by Medical Experts: a Survey of the Existing Approaches
  Nikolay Babakov, Elena Rezgova, Ehud Reiter, Alberto Bugarín
• MRxaI: Black-Box Explainability for Image Classifiers in a Medical Setting
  Nathan Blake, David Kelly, Santiago Calderon Peña, Akchunya Chanchal, Hana Chockler
• LLM-Driven Clinical Trial Matching for Lung Cancer Patients: An Explainable Approach
  Vittoria Peppoloni, Giuseppe Leone, Laura Mazzeo, Alberto Ferrarin, Vanja Miskovic, Giuseppe Lo Russo, Paolo Baili, Arsela Prelaj, Federica Corso

Session 3

• xSTAE: Explaining Classifier Decisions through EEG Signal Style Transfer Autoencoding
  Natalia Koliou, Panagiotis Zazos, Christophoros Romesis, Cristian Bosch, Stasinos Konstantopoulos, Panagiotis Trakadas
• Vision-Language Models in ECG Interpretation: An Exploratory Study
  Sileshi Nibret Zeleke, Mario Bochicchio
• Pilot Assessment of Transparency of LLM-based Systems to Support Emergency Rooms
  Michał Chojnicki, Katarzyna Kaczmarek-Majer, Paweł Burchardt, Yanwu Ren, Marek Z. Reformat
• Beyond Static Importance: Quantifying Stability and Distribution Drift
  Marcin Ostrowski, Olgierd Hryniewicz
• Exploring the Expressive Power of Large Language Models in Neuro-Fuzzy System Explainability: A Study on EEG-Based Seizure Detection
  Gabriella Casalino, Giovanna Castellano, Daniele Margherita, Alberto Gaetano Valerio, Gennaro Vessio, Gianluca Zaza