Gender-Equity Model for Liver Allocation Using Artificial Intelligence (GEMA-AI) for Waiting List Liver Transplant Prioritization.

Abstract

Background & aims: We aimed to develop and validate an artificial intelligence score (gender-equity model for liver allocation using artificial intelligence [GEMA-AI]) to predict liver transplantation (LT) waiting list outcomes using the same input variables contained in existing models.

Methods: This was a cohort study including adult LT candidates enlisted in the United Kingdom (2010-2020) for model training and internal validation and in Australia (1998-2020) for external validation. GEMA-AI combined international normalized ratio, bilirubin, sodium, and the Royal Free Hospital glomerular filtration rate in an explainable artificial neural network. GEMA-AI was compared with gender-equity model for liver allocation corrected by serum sodium (GEMA-Na), Model for End-Stage Liver Disease 3.0, and Model for End-Stage Liver Disease corrected by serum sodium for waiting list prioritization.

Results: The study included 9320 patients: 5762 in the training cohort, 1920 in the internal validation cohort, and 1638 in the external validation cohort. The prevalence of 90-day mortality or delisting for sickness ranged from 5.3% to 6% across different cohorts. GEMA-AI showed better discrimination than GEMA-Na, Model for End-Stage Liver Disease corrected by serum sodium, and Model for End-Stage Liver Disease 3.0 in the internal and external validation cohorts, with a more pronounced benefit in women and in patients showing at least 1 extreme analytical value. Accounting for identical input variables, the transition from a linear to a nonlinear score (from GEMA-Na to GEMA-AI) resulted in a differential prioritization of 6.4% of patients within the first 90 days and would potentially save 1 in 59 deaths overall, and 1 in 13 deaths among women. Results did not substantially change when ascites was not included in the models.

Conclusions: The use of explainable machine learning models may be preferred over conventional regression-based models for waiting list prioritization in LT. GEMA-AI made more accurate predictions of waiting list outcomes, particularly for the sickest patients.