FindTrial
Sign In

An online interpretable dynamic prediction model for posthepatectomy liver failure based on machine learning algorithms: a retrospective cohort study

An online interpretable dynamic prediction model for posthepatectomy liver failure based on machine learning algorithms: a retrospective cohort study

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2400083151
Enrollment
Unknown
Registered
2024-04-16
Start date
2024-02-23
Completion date
Unknown
Last updated
2024-04-22

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Posthepatectomy liver failure

Interventions

PHLF group (according to the International Study Group of Liver Surgery (ISGLS) diagnostic criteria, PHLF severity was Grade B or C), Non-PHLF group (Grade A or no PHLF):None

Sponsors

The First Affiliated Hospital, University of South China
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 85 Years

Inclusion criteria

Inclusion criteria: (1) 18-85 years of age; (2) preoperative Child-Pugh grade A or B; and (3) no cardiopulmonary or renal insufficiency or hepatic encephalopathy preoperatively; (4) informed consent and voluntary participation in this study

Exclusion criteria

Exclusion criteria: (1) preoperative biliary obstruction and (2) two-stage hepatectomy

Design outcomes

Primary

MeasureTime frame
Area Under Precision Recall Curve (AUPRC);—

Secondary

MeasureTime frame
Area Under the Curve (AUC);Precision;F1 score;—

Countries

China

Contacts

Public ContactXiaoming Dai

The First Affiliated Hospital, University of South China

fydaixiaoming@126.com+86 139 7475 2414

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026