Integrating clinical, lab, and biopsy data to predict outcomes in acute alcoholic hepatitis

Integrative Epidemiology of Prognosis in Patients With Acute Alcoholic Hepatitis at AP-HP

Observational Assistance Publique - Hôpitaux de Paris · NCT07262515

This project will try to see if combining clinical information, blood tests, and biopsy findings can better predict outcomes for adults diagnosed with acute alcoholic hepatitis.

Quick facts

Study typeObservational
Enrollment1400 (estimated)
Ages18 Years and up
SexAll
SponsorAssistance Publique - Hôpitaux de Paris Academic / other
Locations1 site (Paris)
Trial IDNCT07262515 on ClinicalTrials.gov

What this trial studies

This is a retrospective, multicenter observational analysis using the AP-HP clinical data warehouse to build prognostic models for acute alcoholic hepatitis diagnosed since 2017. The investigators will extract demographics, comorbidities, laboratory values (liver, renal, coagulation, lactate), histology details, microbiology results, medications, and outcomes including infections, transplantation, organ failure, and mortality. Statistical methods will include classical survival models (Cox regression, accelerated failure time models) and machine learning approaches such as random forests and gradient boosting to create integrative risk scores. The goal is to produce more accurate, personalized predictions of overall survival and to identify intermediate factors that modify prognosis.

Who should consider this trial

Good fit: Adults (≥18 years) diagnosed with acute alcoholic hepatitis whose records are available in the AP-HP data warehouse, including those with linked laboratory and, when available, histology data.

Not a fit: Patients younger than 18, those without sufficient electronic clinical or laboratory records in the AP-HP system, or patients with liver injury from non-alcoholic causes are unlikely to benefit from the model developed here.

Why it matters

Potential benefit: If successful, clinicians could more accurately identify patients at high risk of complications or death and tailor monitoring, therapies, and referral for transplantation.

How similar studies have performed: Existing prognostic scores (e.g., MELD, Maddrey, Lille) provide limited accuracy and machine-learning approaches have shown promise in small cohorts, but large-scale integrative models combining histology and real-world data remain relatively novel.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Adult patients (≥18 years)
* Diagnosis of acute alcoholic hepatitis (ICD10 K701 or occurrence of the terms "HAA" (French translation of "AAH" or "hépatite alcoolique aiguë" (French translation of "acute alcoholic hepatitis") in a pathology report, followed by manual verification

Exclusion Criteria:

\- Patients younger than 18 years at diagnosis

Where this trial is running

Paris

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Acute Alcoholic HepatitisMachine LearningAccelerated failure timeRWE epidemiologyPrognosis prediction
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.