NCT06031818View on ClinicalTrials.gov

Usability and Clinical Effectiveness of an Interpretable Deep Learning Framework for Post-Hepatectomy Liver Failure Prediction

RecruitingOBSERVATIONAL
Enrollment

80

Participants

Timeline

Start Date

December 10, 2023

Primary Completion Date

February 28, 2024

Study Completion Date

March 15, 2024

Conditions
Post-hepatectomy Liver FailureHepatocellular CarcinomaArtificial Intelligence
Interventions
OTHER

The explanation of deep learning framework (VAE-MLP) , including counterfactual explanations and layerwise relevance propagation

The radiologist and clinicians will be provided the model prediction results with the explanation of the model and they will fill in a questionnaire to evaluate the usability of the interpretable framework.

OTHER

The model prediction

The radiologist and clinicians will be provided the model prediction results without the explanation of the model and they will be asked to give their own prediction.

OTHER

The model prediction and the explanation of deep learning framework (VAE-MLP) , including counterfactual explanations and layerwise relevance propagation

The radiologist and clinicians will be provided the model prediction results with the explanation of the model and they will be asked to give their own prediction.

Trial Locations (1)

510000

RECRUITING

The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou

All Listed Sponsors
collaborator

First Affiliated Hospital, Sun Yat-Sen University

OTHER

lead

Maastricht University

OTHER