Autoimmune Hepatitis
Conditions
Keywords
machine learning, registry, therapeutic response
Brief summary
The 5th International Autoimmune Hepatitis Group (IAIHG) research workshop emphasized the integration of large clinical cohorts with artificial intelligence (AI) for enhanced prediction of therapy responses and outcomes in Autoimmune Hepatitis (AIH). This project aims to develop and validate machine learning (ML) models using data from the R-Liver registry and other international cohorts. After rigorous preprocessing to ensure data uniformity and quality, the investigators will identify and characterize factors influencing therapy response. They will then implement ML models to predict complete biochemical response (CBR) at 6 and 12 months, using five-fold cross-validation, and validate these models in external cohorts from Spain, Canada, and the international AIH group, ensuring robustness and generalizability. Finally, the investigators will prospectively validate the models in newly registered cases, assessing both short-term and long-term outcomes. This project seeks to advance personalized treatment strategies in AIH, facilitating timely adjustments in therapy and improving patient prognosis through AI-driven decision support. This projects' interdisciplinary team, with expertise in clinical AI and hepatology, is well-equipped to address these challenges and enhance the clinical management of AIH.
Interventions
None listed
Sponsors
Hannover Medical School
Technische Universität Dresden
Study design
Observational model
CASE_ONLY
Time perspective
OTHER
Eligibility
Sex/Gender
ALL
Healthy volunteers
No
Inclusion criteria
* Diagnosis of Autoimmune hepatitis * Consent to provide data to the specific registry * available follow-up data at least within the first 12 months
Exclusion criteria
* variant syndromes * extrahepatic autoimmune disease * immunosuppressive treatment at diagnosis
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Number of patients with complete biochemical response at 6 months after diagnosis | 6 months | Complete biochemical response is defined as normal aspartate amino transferase (AST), alanine aminotransferase (ALT) and immunoglobulin G (IgG). |
| Number of patients with complete biochemical response at 12 months after diagnosis | 12 months | Complete biochemical response is defined as normal aspartate amino transferase (AST), alanine aminotransferase (ALT) and immunoglobulin G (IgG). |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Number of patients experiencing liver-related death or liver transplantation | From enrolment until the end of the study | — |
| Number of patients with decompensation of liver disease | From enrolment until the end of the study | Decompensation meaning a composite of new/worsening ascites, infection requiring hospitalization, acute-on-chronic liver failure, variceal bleeding, hepatic encephalopathy. |
| Number of patients with complete biochemical response through study completion | through study completion, an expected average of 1 year | Complete biochemical response is defined by normal AST, normal ALT and normal IgG |
| Number of patients with histological remission of AIH through study completion | through study completion, an expected average of 1 year | Histological remission is defined as modified hepatitis activity index below 4. |
| Number of patients that develop cirrhosis through study completion | through study completion, an expected average of 1 year | Cirrhosis is defined by imaging findings indicative of cirrhosis, histological staging indicating fibrosis or liver stiffness measurement that is in line with a cirrhotic liver. |
| Number of patients with intolerance to primary treatment necessitating regimen change | 12 months | Intolerance to treatment is reported by respective patients and assessed by respective treating physicians. It is expected to be gastrointestinal side effects and hematological side effects (cytopenias) that may typically occur from treatment with azathioprine or mycophenolate mofetil which lead to change of treatment regimens in patients with autoimmune hepatitis. |
| Number of patients with non-response to primary treatment necessitating treatment change | 12 months | Non-Response ist defined as persistently elevated aspartate aminotransferase, alanine aminotransferase and/or immunoglobulin G. It is considered a reason to change the therapeutic regimen. |
| Number of patients with third line treatment due to non-response to obtain biochemical response through study completion | through study completion, an expected average of 1 year | Non-response is defined as persistently elevated aminotransferases and/or immunoglobulin G. |
| Number of patients with normalization of aminotransferase levels in the blood irrespective of Immunoglobulin G levels | 6 months | Aminotransferases are alanine aminotransferase and asparatate aminotransferase. These enzymes indicate liver injury and are considered response markers measured from blood in clinical routine to assess therapeutic response in autoimmune hepatitis. |
| Number of patients with normalization of aminotransferase levels irrespective of Immunoglobulin G levels | 12 months | Aminotransferases are alanine aminotransferase and asparatate aminotransferase. These enzymes indicate liver injury and are considered response markers measured from blood in clinical routine to assess therapeutic response in autoimmune hepatitis. |
| Number of patients with steroid-free complete biochemical response | 6 months | Complete biochemical response is defined by normal blood levels for aminotransferases and normal immunoglobulin G. This outcome measure assesses this parameter in relation to the fact if the patient needed corticosteroid-therapy to obtain this outcome or if the patient only needed other immunosuppressive drugs (e.g. azathioprine, mycophenolate mofetil). |
Countries
Germany
Contacts
PRINCIPAL_INVESTIGATORBastian Engel, MD
Hannover Medical School, Hannover, Germany
Outcome results
None listed