A Machine Learning Architecture to Predict Post-Hepatectomy Liver Failure Using Liver Regeneration Biomarkers and Time-Phased Data

Completed

• Conditions: Liver Failure After Operative Procedure
• Interventions: Procedure: Extensive hepatectomy

• Registration Number: NCT05779098
• Lead Sponsor: Shen Feng

Brief Summary

Post-hepatectomy liver failure (PHLF) is the leading cause of morbidity and mortality following major hepatectomy. Existing prediction models fail to capture the dynamic liver regeneration and perioperative changes, limiting their predictive accuracy. We aimed to develop a machine learning (ML) modelling system (PILOT architecture) integrating liver regeneration biomarkers with time-phased perioperative clinical data to accurately predict PHLF risk.

Detailed Description

Not available

Study Timeline

• Study First Submitted: 2023-03-09
• Study First Submitted QC: 2023-03-21
• Study First Posted: 2023-03-22
• Study Start: 2023-04-01
• Primary Completion: 2025-04-01
• Study Completion: 2025-04-01
• Status Verified: 2025-05
• Last Update Submitted: 2025-05-18
• Last Update Posted: 2025-05-22

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 1071

Inclusion Criteria

Extensive hepatectomy in our hospital（≥ three Hepatic segment）

Exclusion Criteria

Serious basic diseases Intolerable surgery Refuse to perform ICG test before operation

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Extensive hepatectomy	Extensive hepatectomy	-

Primary Outcome Measures

Name	Time	Method
Postoperative liver failure	1-5 days after surgery

Trial Locations

Locations (1)

Department of Hepatobiliary and Pancreatic Surgery, Tenth People's Hospital of Tongji University, School of Medicine, Tongji University, Shanghai, China; 🇨🇳 Shanghai, China