Machine learning improves the accuracy of graft weight prediction in living donor liver transplantation

Abstract

Precise graft weight (GW) estimation is essential for planning living donor liver transplantation to select grafts of adequate size for the recipient. This study aimed to investigate whether a machine-learning model can improve the accuracy of GW estimation. Data from 872 consecutive living donors of a left lateral sector, left lobe, or right lobe to adults or children for living-related liver transplantation were collected from January 2011 to December 2019. Supervised machine-learning models were trained (80% of observations) to predict GW using the following information: donor's age, sex, height, weight, and body mass index; graft type (left, right, or left lateral lobe); computed tomography estimated graft volume and total liver volume. Model performance was measured in a random independent set (20% of observations) and in an external validation cohort using the mean absolute error (MAE) and the mean absolute percentage error and compared with methods currently available for GW estimation. The best-performing machine-learning model showed an MAE value of 50 ± 62 g in predicting GW, with a mean error of 10.3%. These errors were significantly lower than those observed with alternative methods. In addition, 62% of predictions had errors <10%, whereas errors >15% were observed in only 18.4% of the cases compared with the 34.6% of the predictions obtained with the best alternative method ( p < 0.001). The machine-learning model is made available as a web application ( http://graftweight.shinyapps.io/prediction ). Machine learning can improve the precision of GW estimation compared with currently available methods by reducing the frequency of significant errors. The coupling of anthropometric variables to the preoperatively estimated graft volume seems necessary to improve the accuracy of GW estimation.