Bibliographic citations
Paucar, J., (2023). Tecnologías basadas en inteligencia artificial para el diagnóstico del síndrome coronario agudo: una revisión sistemática [Universidad Peruana Cayetano Heredia]. https://hdl.handle.net/20.500.12866/15537
Paucar, J., Tecnologías basadas en inteligencia artificial para el diagnóstico del síndrome coronario agudo: una revisión sistemática []. PE: Universidad Peruana Cayetano Heredia; 2023. https://hdl.handle.net/20.500.12866/15537
@misc{renati/911316,
title = "Tecnologías basadas en inteligencia artificial para el diagnóstico del síndrome coronario agudo: una revisión sistemática",
author = "Paucar Escalante, Jesus Francisco",
publisher = "Universidad Peruana Cayetano Heredia",
year = "2023"
}
Objective: To identify the development of artificial intelligence-based technologies capable of diagnosing acute coronary syndrome (ACS). Materials and methods: Certain systematic searches were conducted across multiple databases, including Medline, SCOPUS, IEEE XPLORE, and EMBASE, to identify studies related to the use of intelligent tools such as Machine Learning (ML) and Deep Learning (DL) for diagnosing Acute Coronary Syndrome (ACS) in accordance with the definition provided in the 2021 practical clinical guidelines of the European Society of Cardiology. This search encompassed studies published up to August 2, 2021. We considered cohort and case-control studies that directly impacted the diagnostic potential of ACS, while excluding studies exclusively utilizing ECG signals. The assessment of study bias was carried out using the Newcastle-Ottawa Scale.. Results: A total of 24 scientific articles were identified for the systematic review. No meta-analysis was performed due to the clinical heterogeneity of the studies while the approach was based on three perspectives: 1) Technology used, 2) Countries of study development and 3) Generation of the algorithm applied in each study. A higher frequency was found for studies performed by tomography with a great development of algorithms based on ML and DL finding the best results for the case of DL with 99.5% accuracy. Likewise, by countries, it was found the predominance of studies in China followed by the United States whose aspirations are based on the leadership in the field of AI. Conclusion: An accuracy of 99.5% was found in DL for the diagnosis of ACS and some others with an accuracy above 90% with opportunities for improvement.
This item is licensed under a Creative Commons License