ERJ open research · 2026
Clinical phenotypes in α1-antitrypsin deficiency: a cluster analysis on EARCO data.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
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.
Somers Anse, Verstraete Kenneth, Demesmaeker Ella, Torres-Duran María, Turner Alice M, Tanash Hanan, Rodríguez-García Carlota, Stæhr Jensen Jens-Ulrik, Guido Corsico Angelo, López-Campos José Luis, Chapman Kenneth R, Clarenbach Christian F, Guimarães Catarina, Bartošovská Eva, Hernández-Pérez José María, Rodriguez-Hermosa Juan Luis, Lara Beatriz, Miravitlles Marc, Janssens Wim, Everaerts Stephanie, EARCO study investigators, EARCO study investigators
Аннотация
BACKGROUND: α-1 antitrypsin deficiency (AATD) is a rare, monogenic disorder predisposing individuals to liver and lung diseases. Yet, even within the same genotype, AATD is very heterogeneous in clinical presentation. This heterogeneity suggests a complex interplay of environmental and (epi)genetic factors, highlighting the need for a detection and study of clinical phenotypes.
METHODS: Here, we performed a cluster analysis using baseline data from the European Alpha-1 Research Collaboration (EARCO) to identify distinct clinical phenotypes in AATD.
RESULTS: We identified six clusters of AATD clinical phenotypes using K-prototypes with a cross-validated weighted F1 score of 0.926. Moreover, using a trained random forest classifier, we identified age at diagnosis, lung function and tobacco consumption as the most important features in distinguishing these clusters, in addition to the AATD-associated genotype.
CONCLUSIONS: Overall, these findings underscore the fact that, beyond genotype, a multitude of other factors significantly influence AATD clinical phenotypes. Accordingly, this emphasises the importance of integrating (epi)genetic, environmental and behavioural data in future fundamental and translational research to unravel the complex mechanisms underlying patient heterogeneity. Moreover, longitudinal follow-up of individuals allocated to these clusters will help to better understand disease progression and to assess the potential benefits of specific therapies in different phenotypes.
METHODS: Here, we performed a cluster analysis using baseline data from the European Alpha-1 Research Collaboration (EARCO) to identify distinct clinical phenotypes in AATD.
RESULTS: We identified six clusters of AATD clinical phenotypes using K-prototypes with a cross-validated weighted F1 score of 0.926. Moreover, using a trained random forest classifier, we identified age at diagnosis, lung function and tobacco consumption as the most important features in distinguishing these clusters, in addition to the AATD-associated genotype.
CONCLUSIONS: Overall, these findings underscore the fact that, beyond genotype, a multitude of other factors significantly influence AATD clinical phenotypes. Accordingly, this emphasises the importance of integrating (epi)genetic, environmental and behavioural data in future fundamental and translational research to unravel the complex mechanisms underlying patient heterogeneity. Moreover, longitudinal follow-up of individuals allocated to these clusters will help to better understand disease progression and to assess the potential benefits of specific therapies in different phenotypes.