TRAIN-AI: Deep Learning Model for the Prediction of Post-LT HCC Recurrence

• Sponsor: European Hepatocellular Cancer Liver Transplant Group (Other)
• Overall Status: Completed
• CT.gov ID: NCT05200195
• Collaborator: (none)
• Enrollment: 4,026
• Location: 1
• Actual Duration (Months): 26
• Patients Per Site Per Month: 155.1

Study Details

Study Description

Brief Summary

Identifying patients at high risk for recurrence of hepatocellular carcinoma (HCC) after liver transplantation (LT) represents a challenging issue. The present study aims to develop and validate an accurate post-LT recurrence prediction calculator using the machine learning method.

Condition or Disease	Intervention/Treatment	Phase
Liver Transplant Disorder; Liver Cancer; Recurrent Cancer	Procedure: Liver transplantation

Detailed Description

In 1996, the introduction of the Milan criteria (MC) strongly modified the selection process of hepatocellular cancer (HCC) patients waiting for liver transplantation (LT). Many attempts to widen MC have been proposed. Initially, exclusively morphology-based (nodules number and target lesion diameter) criteria were created. In the last years, extended criteria also based on biological parameters have been added. Among the most adopted biology-based features, the levels of different tumor markers, liver function parameters like the model for end-stage liver disease (MELD), the radiological response after neo-adjuvant therapies, and the length of waiting-time (WT) can be reported.

Unfortunately, all the proposed models showed suboptimal prediction abilities for the risk of post-LT recurrence. Such impairment was derived from the limitations of the standard statistical methods to account for many variables and their non-linear interactions. Therefore, developing a model based on Artificial Intelligence (AI) represents an attractive way to improve prediction ability.

Thus, the investigators hypothesize that an AI model focused on an accurate post-transplant HCC recurrence prediction should improve our ability to pre-operatively identify patients with different classes of risk for HCC recurrence after transplant.

This study aims to develop an AI-derived prediction model combining morphology and biology variables. A Training Set derived from an International Cohort was adopted for doing this. A Test Set derived from the same International Cohort and a Validation Cohort were adopted for the internal and external validation, respectively. A user-friendly web calculator was also developed.

Study Design

• Study Type: Observational
• Actual Enrollment: 4026 participants
• Observational Model: Cohort
• Time Perspective: Retrospective
• Official Title: Development and Validation of a Deep Learning Model for the Prediction of Hepatocellular Cancer Recurrence After Transplantation: The Time-Radiological Response- AlphafetoproteIN-Artificial Intelligence Model
• Actual Study Start Date: Jan 15, 2020
• Actual Primary Completion Date: Dec 15, 2021
• Actual Study Completion Date: Mar 15, 2022

Arms and Interventions

Arm	Intervention/Treatment
International Cohort Training Set The Training Set of the International Cohort (N=3,670) was composed of the 80% (n=2936) HCC patients transplanted from 2000 to 2018 across 17 centers in Europe and Asia.	Procedure: Liver transplantation; Deceased or living donor liver transplantation for the cure of hepatocellular cancer on cirrhosis
International Cohort Test Set The Test Set of the International Cohort (N=3,670) was composed of the 20% (n=734) HCC patients transplanted from 2000 to 2018 across 17 centers in Europe and Asia.	Procedure: Liver transplantation; Deceased or living donor liver transplantation for the cure of hepatocellular cancer on cirrhosis
Validation Cohort The external Validation Cohort was composed of 356 HCC patients transplanted at the Columbia University, New York, during the period 2000-2018.	Procedure: Liver transplantation; Deceased or living donor liver transplantation for the cure of hepatocellular cancer on cirrhosis

Outcome Measures

Primary Outcome Measures

1. Post-transplant HCC recurrence [5 years from liver transplantation]

   Intra- and/or extrahepatic recidivism of HCC after liver transplantation

Eligibility Criteria

Criteria

• Ages Eligible for Study: 18 Years and Older
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No

Inclusion Criteria:

• Consecutive adult (≥18 years) patients enlisted and transplanted with the primary diagnosis of HCC during the period 2000-2018.

Exclusion Criteria:

• Patients with HCC diagnosed only at pathological examination (incidental HCC)

• Patients with mixed hepatocellular-cholangiocellular cancer misdiagnosed as HCC

• Patients with cholangiocellular cancer misdiagnosed as HCC

• Patients dying early after LT (≤ one month)

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	Quirino Lai	Rome	RM	Italy	00151

Sponsors and Collaborators

• European Hepatocellular Cancer Liver Transplant Group

Investigators

• Principal Investigator: Quirino Lai, MD PhD, Sapienza University of Rome

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: Quirino Lai, Principal Investigator, European Hepatocellular Cancer Liver Transplant Group
• ClinicalTrials.gov Identifier: NCT05200195
• Other Study ID Numbers: #004
• First Posted: Jan 20, 2022
• Last Update Posted: Jun 30, 2022
• Last Verified: Jun 1, 2022

• Individual Participant Data (IPD) Sharing Statement: No
• Plan to Share IPD: No
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Keywords provided by Quirino Lai, Principal Investigator, European Hepatocellular Cancer Liver Transplant Group: artificial intelligence; deep learning; mathematical model
• Additional relevant MeSH terms: Recurrence

Study Results

No Results Posted as of Jun 30, 2022