Improving outcomes of in situ split liver transplantation in Italy over the last 25 years.

BACKGROUND & AIMS: Split liver transplant(ation) (SLT) is still considered a challenging procedure that is by no means widely accepted. We aimed to present data on 25-year trends in SLT in Italy, and to investigate if, and to what extent, outcomes have improved nationwide during this time. METHODS: The study included all consecutive SLTs performed from May 1993 to December 2019, divided into three consecutive periods: 1993-2005, 2006-2014, and 2015-2019, which match changes in national allocation policies. Primary outcomes were patient and graft survival, and the relative impact of each study period. RESULTS: SLT accounted for 8.9% of all liver transplants performed in Italy. A total of 1,715 in situ split liver grafts were included in the analysis: 868 left lateral segments (LLSs) and 847 extended right grafts (ERGs). A significant improvement in patient and graft survival (p <0.001) was observed with ERGs over the three periods. Predictors of graft survival were cold ischaemia time (CIT) <6 h (p = 0.009), UNOS status 2b (p <0.001), UNOS status 3 (p = 0.009), and transplant centre volumes: 25-50 cases vs. <25 cases (p = 0.003). Patient survival was significantly higher with LLS grafts in period 2 vs. period 1 (p = 0.008). No significant improvement in graft survival was seen over the three periods, where predictors of graft survival were CIT <6 h (p = 0.007), CIT <6 h vs. ≥10 h (p = 0.019), UNOS status 2b (p = 0.038), and UNOS status 3 (p = 0.009). Retransplantation was a risk factor in split liver graft recipients, with significantly worse graft and patient survival for both types of graft (p <0.001). CONCLUSIONS: Our analysis showed Italian SLT outcomes to have improved over the last 25 years. These results could help to dispel reservations regarding the use of this procedure. IMPACT AND IMPLICATIONS: Split liver transplant(ation) (SLT) is still considered a challenging procedure and is by no means widely accepted. This study included all consecutive in situ SLTs performed in Italy from May 1993 to December 2019. With more than 1,700 cases, it is one of the largest series, examining long-term national trends in in situ SLT since its introduction. The data presented indicate that the outcomes of SLT improved during this 25-year period. Improvements are probably due to better recipient selection, refinements in surgical technique, conservative graft-to-recipient matching, and the continuous, yet carefully managed, expansion of donor selection criteria under a strict mandatory split liver allocation policy. These results could help to dispel reservations regarding the use of this procedure.

Prognostic role of artificial intelligence among patients with hepatocellular cancer: A systematic review.

BACKGROUND: Prediction of survival after the treatment of hepatocellular carcinoma (HCC) has been widely investigated, yet remains inadequate. The application of artificial intelligence (AI) is emerging as a valid adjunct to traditional statistics due to the ability to process vast amounts of data and find hidden interconnections between variables. AI and deep learning are increasingly employed in several topics of liver cancer research, including diagnosis, pathology, and prognosis. AIM: To assess the role of AI in the prediction of survival following HCC treatment. METHODS: A web-based literature search was performed according to the Preferred Reporting Items for Systemic Reviews and Meta-Analysis guidelines using the keywords "artificial intelligence", "deep learning" and "hepatocellular carcinoma" (and synonyms). The specific research question was formulated following the patient (patients with HCC), intervention (evaluation of HCC treatment using AI), comparison (evaluation without using AI), and outcome (patient death and/or tumor recurrence) structure. English language articles were retrieved, screened, and reviewed by the authors. The quality of the papers was assessed using the Risk of Bias In Non-randomized Studies of Interventions tool. Data were extracted and collected in a database. RESULTS: Among the 598 articles screened, nine papers met the inclusion criteria, six of which had low-risk rates of bias. Eight articles were published in the last decade; all came from eastern countries. Patient sample size was extremely heterogenous (n = 11-22926). AI methodologies employed included artificial neural networks (ANN) in six studies, as well as support vector machine, artificial plant optimization, and peritumoral radiomics in the remaining three studies. All the studies testing the role of ANN compared the performance of ANN with traditional statistics. Training cohorts were used to train the neural networks that were then applied to validation cohorts. In all cases, the AI models demonstrated superior predictive performance compared with traditional statistics with significantly improved areas under the curve. CONCLUSION: AI applied to survival prediction after HCC treatment provided enhanced accuracy compared with conventional linear systems of analysis. Improved transferability and reproducibility will facilitate the widespread use of AI methodologies.