Arch. cardiol. Méx; 88 (3), 2018
Publication year: 2018
Resumen Antecedentes:
El infarto agudo de miocardio representa la primera causa de muerte no trasmisible a nivel mundial. Su diagnóstico es una tarea altamente compleja que se ha intentado modelar mediante métodos automáticos. Se expone una revisión sistemática de estudios de pruebas diagnósticas de los síndromes coronarios agudos mediante sistemas inteligentes. Métodos:
Revisión sistemática de la literatura a partir de Medline, Embase, Scopus, IEEE/IET Electronic Library, ISI Web Of Science, Latindex y LILACS de la evaluación diagnóstica de los síndromes coronarios agudos mediante sistemas inteligentes. Fue realizada por 2 revisores de manera independiente y las discrepancias se resolvieron por una tercera persona. Se extrajeron las características operativas de cada herramienta. Resultados:
En total, 35 artículos cumplieron los criterios de inclusión. En 22 (62.8%) se utilizaron redes neuronales. Cinco comparan varias herramientas de sistemas inteligentes. En 13 se abarcaba todos los síndromes coronarios agudos y en 22 solo los infartos. En 21 los datos de entrada fueron la clínica y el electrocardiograma, en 10 solo el electrocardiograma. La mayoría utilizan como referente estándar el contexto clínico. Se encontraron altos niveles de precisión diagnóstica con un mejor rendimiento en el caso de redes neuronales y máquinas de soporte de vectores en comparación con las herramientas estadísticas de reconocimiento de patrones y árboles de decisiones. Conclusiones:
Encontramos una amplia evidencia de que los abordajes a través de las herramientas de sistemas inteligentes alcanzan un alto nivel de precisión por lo que deberían ser consideradas como herramientas para el soporte de las decisiones diagnósticas de los síndromes coronarios agudos.
Abstract Background:
Acute myocardial infarction is the leading cause of non-communicable deaths worldwide. Its diagnosis is a highly complex task, for which modelling through automated methods has been attempted. A systematic review of the literature was performed on diagnostic tests that applied intelligent systems tools in the diagnosis of acute coronary syndromes. Methods:
A systematic review of the literature is presented using Medline, Embase, Scopus, IEEE/IET Electronic Library, ISI Web of Science, Latindex and LILACS databases for articles that include the diagnostic evaluation of acute coronary syndromes using intelligent systems. The review process was conducted independently by 2 reviewers, and discrepancies were resolved through the participation of a third person. The operational characteristics of the studied tools were extracted. Results:
A total of 35 references met the inclusion criteria. In 22 (62.8%) cases, neural networks were used. In five studies, the performances of several intelligent systems tools were compared. Thirteen studies sought to perform diagnoses of all acute coronary syndromes, and in 22, only infarctions were studied. In 21 cases, clinical and electrocardiographic aspects were used as input data, and in 10, only electrocardiographic data were used. Most intelligent systems use the clinical context as a reference standard. High rates of diagnostic accuracy were found with better performance using neural networks and support vector machines, compared with statistical tools of pattern recognition and decision trees. Conclusions:
Extensive evidence was found that shows that using intelligent systems tools achieves a greater degree of accuracy than some clinical algorithms or scales and, thus, should be considered appropriate tools for supporting diagnostic decisions of acute coronary syndromes.