Acta haematologica · 2025
Artificial Intelligence in Hematopoietic Stem Cell Transplantation Care and Complication Management.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
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.
Turki Amin T, Mussetti Alberto, Scheidler Katja Marie, Kehrmann Jan, Crivello Pietro, Hosch René, Nensa Felix, Polizzi Stefano
Аннотация
BACKGROUND: The practice of allogeneic hematopoietic stem cell transplantation (alloHCT) has evolved from an experimental therapy with high mortality rates to a routine treatment that is increasingly performed worldwide. Parallel to this expansion, transplantation has become safer and applicable at higher ages through adapted reduced-intensity protocols and improved supportive care. Advancements in artificial intelligence (AI) methods and computing power over recent decades have driven increasing interest in their application to medicine and, more recently, to hematology.
SUMMARY: Concurrently, the expansion of large-scale datasets from transplant registries, hospitals, and national care networks has contributed to the emergence of big data in the field. The implementation of standardized data integration processes across hospitals and networks has created new opportunities to enhance diagnosis, therapy, and patient monitoring while providing decision support for physicians. While the majority of AI models and tools remain at the experimental level and are based on single-center studies, their impact on the medical domain appears sustainable. The current global excitement about these tools reflects the digital transformation in the practice of medicine, but more validation and medical device studies are needed to enable clinical integration.
KEY MESSAGES: Here, we review the current state of knowledge and advancements in AI applications within hematology, with a particular focus on alloHCT. We discuss emerging tools for preventing transplant-related complications, including donor selection, reducing non-relapse mortality, managing infection, and controlling graft-versus-host disease.
SUMMARY: Concurrently, the expansion of large-scale datasets from transplant registries, hospitals, and national care networks has contributed to the emergence of big data in the field. The implementation of standardized data integration processes across hospitals and networks has created new opportunities to enhance diagnosis, therapy, and patient monitoring while providing decision support for physicians. While the majority of AI models and tools remain at the experimental level and are based on single-center studies, their impact on the medical domain appears sustainable. The current global excitement about these tools reflects the digital transformation in the practice of medicine, but more validation and medical device studies are needed to enable clinical integration.
KEY MESSAGES: Here, we review the current state of knowledge and advancements in AI applications within hematology, with a particular focus on alloHCT. We discuss emerging tools for preventing transplant-related complications, including donor selection, reducing non-relapse mortality, managing infection, and controlling graft-versus-host disease.