Artificial Intelligence in Paediatric Tuberculosis

Area of Science:

• Medical imaging
• Artificial intelligence
• Pediatric tuberculosis

Background:

• Tuberculosis remains a major cause of child mortality globally.
• The COVID-19 pandemic has hindered the WHO's "End TB Strategy".
• AI applications in pediatric medical imaging are limited.

Purpose of the Study:

• To review the application of AI, specifically deep learning, in diagnosing and managing pediatric TB.
• To explore AI's role in chest imaging for computer-assisted diagnosis and screening.
• To discuss challenges and future directions of AI in pediatric TB.

Main Methods:

• Review of current literature on AI and deep learning in pediatric TB.
• Analysis of AI applications in chest imaging for TB diagnosis.
• Exploration of AI for TB screening in resource-constrained environments.

Main Results:

• Deep learning can enhance computer-assisted diagnosis in pediatric chest imaging.
• AI shows promise for improving TB screening workflows.
• Current AI applications in pediatric TB are emerging but limited.

Conclusions:

• AI, particularly deep learning, has significant potential to aid in the diagnosis and management of pediatric TB.
• AI can augment screening efforts and improve diagnostic workflows, especially in resource-limited settings.
• Further research and development are needed to overcome challenges and realize the full potential of AI in pediatric TB care.