Aplicación de modelos de inteligencia artificial en la interpretación de radiografías de tórax para el diagnóstico de tuberculosis pulmonar
Year: 2026
Type: article
Study design: Systematic Review
Abstract: Pulmonary tuberculosis (PTB) remains a major cause of infectious mordidita and mortality worldwide. Artificial intelligence (AI), particularly through deep learning techniques, has emerged as a promising tool for automated diagnosis using chest X-ray imaging. This scoping review aimed to map and characterize the available scientific evidence on AI models applied to PTB diagnosis. A systematic search was conducted across six international databases following the Joanna Briggs Institute methodology and PRISMA-ScR guidelines. Twenty studies published between 2020 and 2025 were included, predominantly employing convolutional neural networks (CNN), hybrid architectures with transformers, and contextual segmentation models. Reported accuracies ranged from 96% to 99.9%. AI demonstrated diagnostic performance superior to human interpretation under controlled conditions, although challenges remain regarding standardization, clinical validation, and geographic representativeness.
DOI: 10.71112/5vy5w189
Language: English
Topic: COVID-19 diagnosis using AI
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7167218871