Gender-Equity Model for Liver Allocation using Artificial Intelligence (GEMA-AI) for waiting list liver transplant prioritization

Áreas de investigación:

• Applications - Donor-recipient matching in liver transplants

Año:

2025

Tipo de publicación:

Artículo

Autores:

• Gómez-Orellana, Antonio Manuel
• Rodríguez-Perálvarez, Manuel
• Guijo-Rubio, David
• Gutiérrez, Pedro Antonio
• Majumdar, Avik
• McCaughan, Geoffrey W.
• Taylor, Rhiannon
• Tsochatzis, Emmanuel
• Hervás-Martínez, César

Journal:

Clinical Gastroenterology and Hepatology

Volumen:

Conditionally Accepted

ISSN:

1542-3565

BibTex:

@article{GEMA-AI-2025, author = "Antonio Manuel G{\'o}mez-Orellana and Manuel Rodr{\'i}guez-Per{\'a}lvarez and David Guijo-Rubio and Pedro Antonio Guti{\'e}rrez and Avik Majumdar and McCaughan, Geoffrey W. and Rhiannon Taylor and Emmanuel Tsochatzis and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "Background {\&}amp; Aims We aimed to develop and validate an artificial intelligence score (GEMA-AI) to predict liver transplant (LT) waiting list outcomes using the same input variables contained in existing models. Methods 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 Glomerular Filtration Rate in an explainable Artificial Neural Network. GEMA-AI was compared with GEMA-Na, MELD 3.0, and MELD-Na for waiting list prioritization. Results The study included 9,320 patients: training cohort n=5,762, internal validation cohort n=1,920, and external validation cohort n=1,638. The prevalence of 90-days mortality or delisting for sickness ranged 5.3%-6% across different cohorts. GEMA-AI showed better discrimination than GEMA-Na, MELD-Na and MELD 3.0 in the internal and external validation cohorts, with a more pronounced benefit in women and in patients showing at least one extreme analytical value. Accounting for identical input variables, the transition from a linear to a non-linear 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 one in 59 deaths overall, and one 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.", awards = "JCR (2024): 11.6, Position: 9/143 (Q1), Category: GASTROENTEROLOGY {\&}amp; HEPATOLOGY", comments = "JCR (2024): 11.6, Position: 9/143 (Q1), Category: GASTROENTEROLOGY {\&}amp; HEPATOLOGY", doi = "10.1016/j.cgh.2024.12.010", issn = "1542-3565", journal = "Clinical Gastroenterology and Hepatology", note = "JCR (20224): 11.6, Position: 9/143 (Q1), Category: GASTROENTEROLOGY {\&}amp; HEPATOLOGY", title = "{G}ender-{E}quity {M}odel for {L}iver {A}llocation using {A}rtificial {I}ntelligence ({GEMA}-{AI}) for waiting list liver transplant prioritization", url = "doi.org/10.1016/j.cgh.2024.12.010", volume = "Conditionally Accepted", year = "2025", }

Nota:

JCR (20224): 11.6, Position: 9/143 (Q1), Category: GASTROENTEROLOGY & HEPATOLOGY

Abstract:

Background & Aims We aimed to develop and validate an artificial intelligence score (GEMA-AI) to predict liver transplant (LT) waiting list outcomes using the same input variables contained in existing models. Methods 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 Glomerular Filtration Rate in an explainable Artificial Neural Network. GEMA-AI was compared with GEMA-Na, MELD 3.0, and MELD-Na for waiting list prioritization. Results The study included 9,320 patients: training cohort n=5,762, internal validation cohort n=1,920, and external validation cohort n=1,638. The prevalence of 90-days mortality or delisting for sickness ranged 5.3%-6% across different cohorts. GEMA-AI showed better discrimination than GEMA-Na, MELD-Na and MELD 3.0 in the internal and external validation cohorts, with a more pronounced benefit in women and in patients showing at least one extreme analytical value. Accounting for identical input variables, the transition from a linear to a non-linear 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 one in 59 deaths overall, and one 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.

Comentarios:

JCR (2024): 11.6, Position: 9/143 (Q1), Category: GASTROENTEROLOGY & HEPATOLOGY