Revolution or routine? Comparing AI and traditional imaging in thoracic surgery outcomes: a systematic review.

Abstract

Artificial intelligence (AI) and machine learning (ML) are increasingly pivotal in advancing postoperative imaging for thoracic surgery, presenting transformative potentials in clinical practice. This comprehensive review investigates the current applications and future directions of AI and ML by comparing them with traditional imaging methods. It highlights how these technologies assist in the early detection of postoperative complications such as infections, anastomotic leaks, and pleural effusions through sophisticated image analysis algorithms. The discussion extends to the automation of routine imaging tasks, which not only improves efficiency but also allows radiologists to focus on more complex cases. Looking ahead, the article considers the implications of emerging technologies such as deep learning and neural networks. This further enhances the capabilities of AI in medical imaging. By providing a thorough overview of the current landscape and anticipating future advancements, this article highlights the profound impact of AI and ML on improving patient care and outcomes in thoracic surgery.