Image de couverture de livre

On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Geiger, Alexander, Wagner, Lars, Rueckert, Daniel, Wilhelm, Dirk, Jell, Alissa
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multimodal Graph-based Classification of Esophageal Motility Disorders
par: Geiger, Alexander, et autres
Publié: (2026)

Detecting and clustering swallow events in esophageal long-term high-resolution manometry
par: Geiger, Alexander, et autres
Publié: (2024)

Robust prediction under missingness shifts
par: Rockenschaub, Patrick, et autres
Publié: (2024)

Informative missingness and its implications in semi-supervised learning
par: Wu, Jinran, et autres
Publié: (2025)

Dynamic feature selection in medical predictive monitoring by reinforcement learning
par: Chen, Yutong, et autres
Publié: (2024)

ICYM2I: The illusion of multimodal informativeness under missingness
par: Choi, Young Sang, et autres
Publié: (2025)

A conformalized learning of a prediction set with applications to medical imaging classification
par: Hirsch, Roy, et autres
Publié: (2024)

Soft-CAM: Making black box models self-explainable for medical image analysis
par: Djoumessi, Kerol, et autres
Publié: (2025)

Bridging visual saliency and large language models for explainable deep learning in medical imaging
par: Nguezet, Paul Valery, et autres
Publié: (2026)

Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
par: Mohammadi, Marziyeh, et autres
Publié: (2025)

Latent variable model for high-dimensional point process with structured missingness
par: Sinelnikov, Maksim, et autres
Publié: (2024)

Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability
par: Yavari, Ali, et autres
Publié: (2025)

Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
par: Arasteh, Soroosh Tayebi, et autres
Publié: (2023)

Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training
par: Usynin, Dmitrii, et autres
Publié: (2023)

Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data
par: Diaz, Ivan, et autres
Publié: (2023)

A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers
par: Stępka, Ignacy, et autres
Publié: (2024)

Attachment Anchors: A Novel Framework for Laparoscopic Grasping Point Prediction in Colorectal Surgery
par: Schneider, Dennis N., et autres
Publié: (2026)

Sensitivity, Specificity, and Consistency: A Tripartite Evaluation of Privacy Filters for Synthetic Data Generation
par: Koeken, Adil, et autres
Publié: (2025)

Metric Hub: A metric library and practical selection workflow for use-case-driven data quality assessment in medical AI
par: Becker, Katinka, et autres
Publié: (2026)

MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets
par: Oufattole, Nassim, et autres
Publié: (2024)

Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting
par: Weers, Alexander, et autres
Publié: (2026)

Class-specific feature selection for classification explainability
par: Aguilar-Ruiz, Jesus S.
Publié: (2024)

Distance-based mutual congestion feature selection with genetic algorithm for high-dimensional medical datasets
par: Nematzadeh, Hossein, et autres
Publié: (2024)

Integrated path stability selection
par: Melikechi, Omar, et autres
Publié: (2024)

Datasheets for AI and medical datasets (DAIMS): a data validation and documentation framework before machine learning analysis in medical research
par: Marandi, Ramtin Zargari, et autres
Publié: (2025)

Adaptive data selection improves wearable prediction under low baseline performance
par: Kargarandehkordi, Ali
Publié: (2026)

Electrocardiogram-based diagnosis of liver diseases: an externally validated and explainable machine learning approach
par: Alcaraz, Juan Miguel Lopez, et autres
Publié: (2024)

Performance evaluation of predictive AI models to support medical decisions: Overview and guidance
par: Van Calster, Ben, et autres
Publié: (2024)

Limits of trust in medical AI
par: Hatherley, Joshua
Publié: (2025)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
par: Jørgensen, Mikkel Godsk, et autres
Publié: (2026)

Sample size determination for machine learning in medical research
par: Arifin, Wan Nor, et autres
Publié: (2025)

Data reuse enables cost-efficient randomized trials of medical AI models
par: Nercessian, Michael, et autres
Publié: (2025)

Fixing confirmation bias in feature attribution methods via semantic match
par: Cinà, Giovanni, et autres
Publié: (2023)

Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
par: Hölzl, Florian A., et autres
Publié: (2025)

An interpretable prototype parts-based neural network for medical tabular data
par: Karolczak, Jacek, et autres
Publié: (2026)

An explainable machine learning-based approach for analyzing customers' online data to identify the importance of product attributes
par: Karimzadeh, Aigin, et autres
Publié: (2024)

Differential privacy representation geometry for medical image analysis
par: Arasteh, Soroosh Tayebi, et autres
Publié: (2026)

Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide
par: Szep, Marton, et autres
Publié: (2024)

BEND: Benchmarking DNA Language Models on biologically meaningful tasks
par: Marin, Frederikke Isa, et autres
Publié: (2023)

When predict can also explain: few-shot prediction to select better neural latents
par: Dabholkar, Kabir, et autres
Publié: (2024)