Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Oct 8, 2025

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

Published on: August 18, 2015

Explainable process trace classification: An application to stroke.

Giorgio Leonardi¹, Stefania Montani¹, Manuel Striani¹

¹DISIT, Computer Science Institute, Università del Piemonte Orientale, Viale Michel 11, I-15121 Alessandria, Italy.

Journal of Biomedical Informatics

|December 30, 2021

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Towards the Definition of a Prognostic Model for Mantle Cell Lymphoma.

Studies in health technology and informatics·2026

Same author

From Discharge Letters to Process Traces with LLMs: A Human-in-the-Loop Pipeline.

Studies in health technology and informatics·2026

Same author

Investigating the impact of outpatient services on length of stay: an easily interpretable approach.

Frontiers in artificial intelligence·2026

Same author

A deep learning approach to predicting hospitalized patients' SEIRD states using multimodal spatiotemporal data.

International journal of medical informatics·2025

Same author

NRTS: A Client-Server Architecture for Supporting Education in a Neonatal Resuscitation Simulation Scenario.

Studies in health technology and informatics·2023

Same author

High-Fidelity simulation-based program improves flow state scale in the perinatal team.

Italian journal of pediatrics·2021

Same journal

Causal intervention validation of gene regulatory signals in scGPT.

Journal of biomedical informatics·2026

Same journal

CoAff-DTI: Fine-grained drug-target interaction prediction using pre-trained language models and affinity-guided mechanisms.

Journal of biomedical informatics·2026

Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026

Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026

Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026

Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026

See all related articles

This study introduces trace saliency maps to explain deep learning in healthcare process classification. This method enhances interpretability for quality assessment in stroke management.

Area of Science:

Health Informatics
Machine Learning in Healthcare
Process Mining

Background:

Medical process trace classification uses activity sequences for quality assessment.
Deep learning excels at classification but lacks explainability, hindering clinical trust.
Explainable AI is crucial for adopting advanced analytics in healthcare.

Purpose of the Study:

To address the explainability challenge in deep learning for medical process trace classification.
To improve the interpretability of classification models for healthcare professionals.
To enhance quality assessment in stroke management through explainable AI.

Main Methods:

Introduction of trace saliency maps as a novel technique.
Application of trace saliency maps to highlight significant activities in process traces.

Keywords:

Deep learning Explainable artificial intelligence Process traces Stroke management

More Related Videos

Modeling Stroke in Mice - Middle Cerebral Artery Occlusion with the Filament Model

Modeling Stroke in Mice - Middle Cerebral Artery Occlusion with the Filament Model

Published on: January 6, 2011

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Published on: August 11, 2023

Related Experiment Videos

Last Updated: Oct 8, 2025

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

Published on: August 18, 2015

Modeling Stroke in Mice - Middle Cerebral Artery Occlusion with the Filament Model

Modeling Stroke in Mice - Middle Cerebral Artery Occlusion with the Filament Model

Published on: January 6, 2011

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Published on: August 11, 2023

Utilizing deep learning architectures for classification tasks.

Main Results:

Trace saliency maps effectively highlight key activities influencing classification.
The approach successfully explains deep learning model outputs for medical users.
Demonstrated feasibility and interpretability in a stroke management use case.

Conclusions:

Trace saliency maps offer a viable solution for explainable AI in medical process classification.
The method enhances trust and interpretability for deep learning in healthcare.
Potential for broader application across different medical domains and black-box models.