Artificial Intelligence methods in the diagnosis and treatment of chronic diseases

Castillo Pastrana N.B.A.; Vasquez Garcia C.M.; Medina Perez G.P.; Alegría La Rosa de Benavides L.M. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2024) · DOI: 10.18687/laccei2024.1.1.1574

Resumen

The progressive use of Artificial Intelligence is being implemented in diagnosing and treating patients with chronic diseases, which constitutes the focus of interest of this Systematic Literature Review (RSL). The main objective is to identify AI methods that contribute to the health sector in the diagnosis and treatment of chronic diseases to improve clinical outcomes and the quality of life of patients. By formulating PICO questions, an exhaustive search was conducted in the Scopus database, recovering 14,255 articles published between 2019 and 2023. After applying the inclusion and exclusion criteria according to the PRISMA guidelines, 20 relevant articles were selected for analysis. The analysis of the results obtained reveals that Machine Learning stands out as the most prominent approach, representing 30% of the Artificial Intelligence methods used in medical studies on chronic diseases. In addition, 15% of studies use a combination of several AI methods. It is concluded that Machine Learning is particularly relevant in precision, with diagnosis rates between 65% and 91.4% and an overall accuracy of 89%. This approach covers approximately 55% of the selected articles, addressing chronic diseases such as physiological, physical, pulmonary, and natural.

Instituciones: Universidad Tecnológica del Perú