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

> **NCT06031818** · — · UNKNOWN · sponsor: **Maastricht University** · enrollment: 80 (estimated)

## Conditions studied

- Post-hepatectomy Liver Failure
- Hepatocellular Carcinoma
- Artificial Intelligence

## Interventions

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

## Key facts

- **NCT ID:** NCT06031818
- **Lead sponsor:** Maastricht University
- **Sponsor class:** OTHER
- **Phase:** —
- **Study type:** OBSERVATIONAL
- **Status:** UNKNOWN
- **Start date:** 2023-12-10
- **Primary completion:** 2024-02-28
- **Final completion:** 2024-03-15
- **Target enrollment:** 80 (ESTIMATED)
- **Last updated:** 2024-02-06

## Collaborators

- [object Object]

## Primary source

ClinicalTrials.gov registry: https://clinicaltrials.gov/study/NCT06031818

## Citation

> US National Library of Medicine, ClinicalTrials.gov registration NCT06031818, "Usability and Clinical Effectiveness of an Interpretable Deep Learning Framework for Post-Hepatectomy Liver Failure Prediction". Retrieved via AI Analytics 2026-06-05 from https://api.ai-analytics.org/clinical/NCT06031818. Licensed CC0.

---

*[Clinical trials dataset](/datasets/clinical-trials) · CC0 1.0*