International journal of surgery (London, England) · 2025
Artificial intelligence in echocardiography: trends, hotspots and future directions.
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.
Guo Qi, Ma Jiafu, Zhang Hongzhe, Lv Yuting, Yang Tiantian, Pei Xiaohua, Sun Yanli
Аннотация
BACKGROUND: Artificial intelligence (AI) is revolutionizing echocardiography by enhancing diagnostic accuracy, automating workflows, and addressing operator-dependent variability. Despite advancements, systematic analyses of AI's integration into echocardiography remain limited.
METHODS: We analyzed 1,296 publications from the Web of Science using bibliometrix R. Data included annual trends, author impact, institutional contributions, country contributions, and keyword evolution.
RESULTS: From 2019 to 2024, annual publications increased from 45 to 302, with citations peaking in 2019. The United States and China dominated output. Leading institutions included Mayo Clinic and Harvard University. Key contributors like SENGUPTA PP and LOPEZ-JIMENEZ F focused on AI-driven cardiac parameter quantification and pathology detection. High-frequency keywords highlighted priorities in "diagnosis," "classification," and "heart failure." Thematic evolution revealed a shift from structural abnormality studies (2000-2013) to deep learning applications (2019-2025).
CONCLUSION: From 2019 to 2024, annual publications increased rapidly, reflecting accelerated advancements in AI-driven echocardiography. Key research hotspots encompass automated image analysis, diagnostic classification, prognostic prediction, and workflow optimization, with deep learning models demonstrating significant potential to reduce operator dependency and enhance diagnostic precision. Future research will prioritize three critical challenges: data standardization across heterogeneous sources, development of fully automated diagnostic pipelines, and improving the clinical reliability of AI systems.
METHODS: We analyzed 1,296 publications from the Web of Science using bibliometrix R. Data included annual trends, author impact, institutional contributions, country contributions, and keyword evolution.
RESULTS: From 2019 to 2024, annual publications increased from 45 to 302, with citations peaking in 2019. The United States and China dominated output. Leading institutions included Mayo Clinic and Harvard University. Key contributors like SENGUPTA PP and LOPEZ-JIMENEZ F focused on AI-driven cardiac parameter quantification and pathology detection. High-frequency keywords highlighted priorities in "diagnosis," "classification," and "heart failure." Thematic evolution revealed a shift from structural abnormality studies (2000-2013) to deep learning applications (2019-2025).
CONCLUSION: From 2019 to 2024, annual publications increased rapidly, reflecting accelerated advancements in AI-driven echocardiography. Key research hotspots encompass automated image analysis, diagnostic classification, prognostic prediction, and workflow optimization, with deep learning models demonstrating significant potential to reduce operator dependency and enhance diagnostic precision. Future research will prioritize three critical challenges: data standardization across heterogeneous sources, development of fully automated diagnostic pipelines, and improving the clinical reliability of AI systems.