Artificial intelligence in transplantation (machine-learning classifiers and transplant oncology)

Area of Science:

• Transplant oncology
• Hepatocellular carcinoma research
• Machine learning applications in medicine

Background:

• Transplant oncology utilizes liver transplantation for hepatobiliary malignancies.
• Hepatocellular carcinoma is a primary diagnosis within transplant oncology.
• Recent advancements focus on integrating diverse data for improved outcomes.

Purpose of the Study:

• To review machine learning (ML) developments in transplant oncology.
• To focus on ML applications for hepatocellular carcinoma (HCC).
• To highlight ML's role in predicting outcomes for liver transplant candidates.

Main Methods:

• Review of ML in clinicopathological variable identification for HCC.
• Analysis of ML in genomic data processing for HCC.
• Evaluation of ML in image processing (histopathology and radiomics) for HCC.

Main Results:

• ML classifiers enhance clinical prediction accuracy in transplant oncology.
• ML aids in identifying key factors influencing HCC recurrence and survival.
• ML assists in prognostication for patients eligible for liver transplantation.

Conclusions:

• Machine learning effectively analyzes clinicopathological, genomic, and imaging data in transplant oncology.
• Integration of multi-domain data is crucial for future ML advancements in HCC.
• ML tools improve prognostic accuracy and patient selection for liver transplantation in HCC.