Machine learning: principles and applications for thoracic surgery.

Area of Science:

• Medical Technology
• Artificial Intelligence in Medicine
• Thoracic Surgery

Background:

• Machine learning (ML) has advanced significantly over the past decade.
• These advancements have profound implications for various scientific disciplines.
• The integration of ML into healthcare is rapidly evolving.

Purpose of the Study:

• To analyze the impact of recent machine learning (ML) advances on surgical practice.
• To focus specifically on the future influence of ML in thoracic surgery.
• To explore the potential of ML to transform surgical procedures and patient care.

Main Methods:

• A comprehensive review of existing literature was conducted.
• Literature was sourced from both technical and clinical domains.
• Relevant studies on machine learning applications in surgery were synthesized.

Main Results:

• Machine learning (ML) techniques like supervised, unsupervised, and reinforcement learning can enhance surgical care.
• Key applications in cardiac surgery include diagnostics, skill assessment, prognostication, intraoperative augmentation, and research acceleration.
• Limitations such as interpretability, data quality, ethics, and implementation challenges were identified.

Conclusions:

• Machine learning (ML) technologies are poised to significantly augment the future practice of thoracic surgery.
• The integration of ML is expected to lead to improvements in surgical performance.
• Ultimately, ML adoption aims to achieve better patient outcomes in thoracic surgery.