Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Use of Artificial Intelligence for Automated X-ray Analysis During the War in Ukraine
0
Zitationen
8
Autoren
2025
Jahr
Abstract
<bold>Background:</bold> During the full-scale war against Ukraine, access to medical services has become severely limited, creating an urgent need to improve diagnostic processes. Additionally, chronic stress and frequent air raid alarms increase the workload on doctors, raising the risk of diagnostic errors. The implementation of artificial intelligence (AI) for X-ray interpretation helps minimize this risk and enhances diagnostic accuracy. Intervention: The aim of this project was to implement an AI-based system for automated X-ray analysis as part of tuberculosis diagnostics in Ukraine during the war. The objective was to develop a solution that reduces the burden on healthcare professionals while ensuring faster and more accurate disease detection. <bold>Methods:</bold> Advanced AI solutions were introduced to analyze X-ray images for TB and other lung diseases. These systems were integrated into phthisiopulmonology centers using mobile X-ray units. <bold>Results:</bold> In 2024, 14 AI-powered systems were deployed. They are now actively used in clinical practice, accelerating TB diagnosis. Paired with portable X-ray machines, AI enables examinations in hard-to-reach locations, areas with displaced populations, frontline regions, and destroyed healthcare facilities. <bold>Conclusions:</bold> The implementation of AI-based X-ray analysis systems improves diagnostic accuracy, reduces the time required to obtain results, and enhances the efficiency of medical processes under conditions of limited resources and crisis situations.
Ähnliche Arbeiten
Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study
2020 · 22.609 Zit.
La certeza de lo impredecible: Cultura Educación y Sociedad en tiempos de COVID19
2020 · 19.271 Zit.
A Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
2024 · 14.256 Zit.
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
2018 · 8.522 Zit.
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
2021 · 7.130 Zit.