Artificial intelligence predicts recurrent autoimmune hepatitis after liver transplantation in a multicenter cohort study.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Bhat Mamatha, Sun Yingji, Manickavel Praveen, Maleki Saba, Ronca Vincenzo, Hansen Bettina E, Hirschfield Gideon, Elwir Saleh, Alsaed Mohamad, Milkiewicz Piotr, Janik Maciej K, Marschall Hanns-Ulrich, Burza Maria Antonella, Efe Cumali, Calışkan Ali Rıza, Harputluoglu Murat, Kabaçam Gökhan, Terrabuio Débora, de Quadros Onofrio Fernanda, Selzner Nazia, Bonder Alan, Parés Albert, Llovet Laura, Akyıldız Murat, Arikan Cigdem, Manns Michael P, Taubert Richard, Weber Anna-Lena, Schiano Thomas D, Haydel Brandy, Czubkowski Piotr, Socha Piotr, Ołdak Natalia, Akamatsu Nobuhisa, Tanaka Atsushi, Levy Cynthia, Martin Eric F, Goel Aparna, Sedki Mai, Jankowska Irena, Ikegami Toru, Rodriguez Maria, Sterneck Martina, Weiler-Normann Christina, Schramm Christoph, Donato Maria Francesca, Lohse Ansgar, Andrade Raul J, Patwardhan Vilas R, van Hoek Bart, Biewenga Maaike, Kremer Andreas E, Ueda Yoshihide, Deneau Mark, Pedersen Mark, Mayo Marlyn J, Floreani Annarosa, Burra Patrizia, Secchi Maria Francesca, Terziroli Beretta-Piccoli Benedetta, Sciveres Marco, Maggiore Giuseppe, Jafri Syed-Mohammed, Debray Dominique, Girard Muriel, Lacaille Florence, de Boer Ynto S, Lleo Ana, Mason Andrew L, Heneghan Michael, Oo Ye Htun, Lytvyak Ellina, Montano-Loza Aldo J, International AIH Study Group
Аннотация
METHODS: We conducted a multicenter, retrospective cohort study of 706 patients who underwent LT for AIH between January 1987 and June 2020 at 33 centers in North America, South America, Europe, and Asia. We trained 4 predictive machine learning models-Logistic Regression, Random Forest, XGBoost, and Gradient Boost-to predict recurrent AIH (rAIH) using 62 clinical and laboratory variables, including demographic, biochemical features, and immunosuppressive drugs up to 1-year post-transplant. Feature importance was assessed using SHapley Additive exPlanations (SHAP) to enable interpretability at both individual and population levels.Results:AIH recurred in 16.5% of patients after LT. SHAP analysis identified younger age at LT, higher necroinflammatory activity in the explanted liver, and elevated MELD score at LT as key predictors of rAIH in the overall population. Tacrolimus-based therapy was associated with a lower risk of recurrence, while cyclosporine use conferred a higher risk. The addition of long-term prednisone to a regimen of tacrolimus and mycophenolate mofetil did not provide additional protective effect against rAIH.
CONCLUSIONS: Our AI-powered clinical decision model provides personalized prediction of post-transplant rAIH. While it offers insight into modifiable and non-modifiable predictors, prospective validation is required before informing immunosuppressive decisions.