Liver cancer, or hepatocarcinoma, is one of the most common indications for transplantation: in Italy, more than half of the more than 1,500 liver transplants performed each year are due to hepatocarcinoma. In this context, it is essential to predict the possibility of tumour recurrence in order to avoid high-risk patients and to improve the care and management of transplanted patients.

An international study, published in Cancer Communications and coordinated by the Department of General and Specialist Surgery at Sapienza University of Rome, Italy, collected data from around 4,000 patients from North America, Europe and Asia to develop a calculator capable of predicting the risk of post-transplant hepatocarcinoma recurrence.

The online calculator, which is available completely free of charge, was developed using artificial intelligence with the help of engineers from the Politecnico di Torino. Thanks to this innovative and sophisticated system, the new calculator proved to be more reliable than existing ones, thus increasing the possibility of improving the treatment of all patients undergoing liver cancer transplantation.

"The score developed was called TRAIN-AI, which stands for Time-Response-AlphafetoproteIN-Artificial Intelligence," says Quirino Lai of Sapienza University. All the variables that make up the score are easily obtainable before transplantation so that they can be calculated practically anywhere in the world, thus relying on user-friendly parameters. Another important innovation was to develop a calculator based on thousands of patients from all over the world, whereas existing scores were based on regional, or at most national, contexts that were much more limited".

The possibility of predicting the risk of developing a recurrence is of enormous importance to the patient for two reasons: it may make it possible to identify a class at unacceptably high risk of recurrence that can then be excluded from the transplant itself (futile transplantation due to oncological cause); it may make it possible to study the patient in the post-transplant period more carefully (closer follow-ups, reduction of immunosuppressive therapy) in order to prevent recurrence in patients at increased risk.

References:

Development and validation of an artificial intelligence model for predicting post-transplant hepatocellular cancer recurrence -  Quirino Lai, Carmine De Stefano, Jean Emond, Prashant Bhangui, Toru Ikegami, Benedikt Schaefer, Maria Hoppe-Lotichius, Anna Mrzljak, Takashi Ito, Marco Vivarelli, Giuseppe Tisone, Salvatore Agnes, Giuseppe Maria Ettorre, Massimo Rossi, Emmanuel Tsochatzis, Chung Mau Lo, Chao-Long Chen, Umberto Cillo, Matteo Ravaioli, Jan Paul Lerut; EurHeCaLT and the West-East LT Study Group - Cancer Commun (Lond). 2023 doi: 10.1002/cac2.12468.

Further Information

Quirino Lai
Department of General and Specialist Surgery
quirino.lai@uniroma1.it