American heart journal plus : cardiology research and practice · 2026
From innovation to implementation: Addressing the AI adoption gap in cardiac surgery.
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.
Ngwu Dabeluchi, Hamadi Fahd, Akinyemi Oluranti, Wokocha Chinwe, Arora Niket
Аннотация
BACKGROUND: While artificial intelligence (AI) is advancing rapidly across cardiovascular medicine, its translation into cardiac surgery remains limited. Algorithms show promise in diagnostics, perioperative risk prediction, and workflow optimization, yet most applications remain confined to research environments. A focused synthesis is needed to clarify validated clinical value and persistent implementation barriers.
METHODS: We conducted a systematic review following PRISMA 2020 guidelines, searching PubMed, Scopus, and Web of Science for studies published between January 2015 and September 2024. We included 45 primary studies (2019-2024) and eight foundational studies (2015-2018) reporting original data or validated AI models relevant to any stage of cardiac surgical care. Findings were synthesized across five domains: diagnostic support, personalized treatment planning, intraoperative decision support, operational efficiency, and equitable access to care.
RESULTS: AI demonstrated strong performance in echocardiographic interpretation, outcome prediction, and perioperative resource planning, often surpassing conventional risk models. Computer-vision platforms supported surgical phase recognition and enhanced intraoperative imaging workflows, while operational tools improved scheduling accuracy, transfusion forecasting, and bed allocation. Evidence for AI-driven improvements in equitable care delivery was emerging but limited. Most studies were retrospective, single-center, and lacked external validation or clinical integration.
CONCLUSION: AI is positioned to augment cardiac surgery, with the most mature applications in imaging and operational logistics. Adoption remains constrained by heterogeneous data, limited interpretability, regulatory uncertainty, and poor workflow integration. Progress will require multicenter data collaboratives, strong validation frameworks, and clinician-centered implementation strategies that position AI as an augmentative partner, enhancing precision, judgment, and system efficiency.
METHODS: We conducted a systematic review following PRISMA 2020 guidelines, searching PubMed, Scopus, and Web of Science for studies published between January 2015 and September 2024. We included 45 primary studies (2019-2024) and eight foundational studies (2015-2018) reporting original data or validated AI models relevant to any stage of cardiac surgical care. Findings were synthesized across five domains: diagnostic support, personalized treatment planning, intraoperative decision support, operational efficiency, and equitable access to care.
RESULTS: AI demonstrated strong performance in echocardiographic interpretation, outcome prediction, and perioperative resource planning, often surpassing conventional risk models. Computer-vision platforms supported surgical phase recognition and enhanced intraoperative imaging workflows, while operational tools improved scheduling accuracy, transfusion forecasting, and bed allocation. Evidence for AI-driven improvements in equitable care delivery was emerging but limited. Most studies were retrospective, single-center, and lacked external validation or clinical integration.
CONCLUSION: AI is positioned to augment cardiac surgery, with the most mature applications in imaging and operational logistics. Adoption remains constrained by heterogeneous data, limited interpretability, regulatory uncertainty, and poor workflow integration. Progress will require multicenter data collaboratives, strong validation frameworks, and clinician-centered implementation strategies that position AI as an augmentative partner, enhancing precision, judgment, and system efficiency.