Skip to content

Development and validation of a machine learning-based model for detection of cirrhosis in autoimmune hepatitis

Development and validation of a machine learning-based model for detection of cirrhosis in autoimmune hepatitis

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2400085541
Enrollment
Unknown
Registered
2024-06-12
Start date
2024-06-15
Completion date
Unknown
Last updated
2024-07-08

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

Conditions

autoimmune hepatitis

Interventions

Gold Standard:Cirrhosis was determined based on histological findings from liver biopsy, clinical, biochemical, and/or radiological results.
Index test:Machine learning models (logistic regression model and extreme gradient boosting model), aspartate aminotransferase-to-platelet ratio index (APRI), and fibrosis-4 index (FIB-4).

Sponsors

the First Affiliated Hospital of Anhui Medical University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 75 Years

Inclusion criteria

Inclusion criteria: Retrospective collection of clinical and laboratory data from AIH patients aged =18 years, admitted to the hospital from 2016 to 2024, including demographic characteristics, serum biochemical indicators, routine blood tests, coagulation function tests, serum immunoglobulins, and serum autoantibodies.

Exclusion criteria

Exclusion criteria: Patients with comorbid conditions, such as other autoimmune liver diseases, viral hepatitis, drug-induced liver injury, non-alcoholic fatty liver disease (NAFLD) or alcoholic liver disease; those with liver cancer; or those who have undergone liver transplantation.

Design outcomes

Primary

MeasureTime frame
Accuracy;Sensitivity;Specificity;Positive predicative value;Negative predictive value;

Countries

China

Contacts

Public ContactBingtian Dong

the First Affiliated Hospital of Anhui Medical University

dongbingtian@foxmail.com+86 187 5923 1731

Outcome results

None listed

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