Artificial Intelligence in Thoracic Surgery: A Review Bridging Innovation and Clinical Practice for the Next Generation of Surgical Care

Abstract

Background: Artificial intelligence (AI) is rapidly transforming thoracic surgery by enhancing diagnostic accuracy, surgical precision, intraoperative guidance, and postoperative management. AI-driven technologies, including machine learning (ML), deep learning, computer vision, and robotic-assisted surgery, have the potential to optimize clinical workflows and improve patient outcomes. However, challenges such as data integration, ethical concerns, and regulatory barriers must be addressed to ensure AI's safe and effective implementation. This review aims to analyze the current applications, benefits, limitations, and future directions of AI in thoracic surgery. Methods: This review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive literature search was performed using PubMed, Scopus, Web of Science, and Cochrane Library for studies published up to January 2025. Relevant articles were selected based on predefined inclusion and exclusion criteria, focusing on AI applications in thoracic surgery, including diagnostics, robotic-assisted surgery, intraoperative guidance, and postoperative care. A risk of bias assessment was conducted using the Cochrane Risk of Bias Tool and ROBINS-I for non-randomized studies. Results: Out of 279 identified studies, 36 met the inclusion criteria for qualitative synthesis, highlighting AI's growing role in diagnostic accuracy, surgical precision, intraoperative guidance, and postoperative care in thoracic surgery. AI-driven imaging analysis and radiomics have improved pulmonary nodule detection, lung cancer classification, and lymph node metastasis prediction, while robotic-assisted thoracic surgery (RATS) has enhanced surgical accuracy, reduced operative times, and improved recovery rates. Intraoperatively, AI-powered image-guided navigation, augmented reality (AR), and real-time decision-support systems have optimized surgical planning and safety. Postoperatively, AI-driven predictive models and wearable monitoring devices have enabled early complication detection and improved patient follow-up. However, challenges remain, including algorithmic biases, a lack of multicenter validation, high implementation costs, and ethical concerns regarding data security and clinical accountability. Despite these limitations, AI has shown significant potential to enhance surgical outcomes, requiring further research and standardized validation for widespread adoption. Conclusions: AI is poised to revolutionize thoracic surgery by enhancing decision-making, improving patient outcomes, and optimizing surgical workflows. However, widespread adoption requires addressing key limitations through multicenter validation studies, standardized AI frameworks, and ethical AI governance. Future research should focus on digital twin technology, federated learning, and explainable AI (XAI) to improve AI interpretability, reliability, and accessibility. With continued advancements and responsible integration, AI will play a pivotal role in shaping the next generation of precision thoracic surgery.

Keywords: artificial intelligence; digital twin; explainable AI (XAI); intraoperative guidance; machine learning; postoperative care; radiomics; robotic-assisted surgery; surgical innovation; thoracic surgery.

Figure 1

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flowchart illustrating the study selection process for this review. The chart details the number of studies identified through database searches, screened for relevance, and assessed for eligibility, leading to the final inclusion of 36 studies in the qualitative synthesis.

Figure 2

The role of artificial intelligence (AI) across different phases of thoracic surgery. In the preoperative phase, AI enhances imaging through radiomics, assists in risk stratification, and supports 3D modeling for surgical planning. During the intraoperative phase, AI-driven robotic-assisted surgery, augmented reality (AR) navigation, and AI-guided decision support improve surgical precision and efficiency. In the postoperative phase, AI-based monitoring systems, predictive analytics for complications, and electronic health record (EHR)-based risk stratification contribute to enhanced recovery and long-term patient management. This figure illustrates the integration of AI throughout the surgical pathway to optimize patient outcomes and clinical decision-making.

Figure 3

The role of AI in the early diagnosis of thoracic pathologies, particularly lung cancer. The process begins with patient data collection and imaging, including CT, MRI, PET scans, genomic biomarkers, and electronic health records (EHRs). AI-driven analysis is then applied to extract radiomics features, recognize patterns through machine learning, and interpret imaging using deep learning models. Finally, AI-based risk stratification assists in pulmonary nodule classification, lung cancer detection, and disease progression prediction, supporting early intervention and personalized treatment planning. This framework enhances diagnostic accuracy, facilitates early detection, and improves clinical decision-making in thoracic oncology.

Figure 4

The role of AI in lung cancer staging, integrating multimodal data analysis with predictive modeling. The process begins with multimodal data collection, incorporating CT, PET, and MRI imaging, pathology and biomarker assessments, and electronic health records (EHRs). AI-driven analysis then applies deep learning for tumor classification, radiomics for tumor size and spread assessment, and AI-enhanced lymph node detection to refine staging accuracy. Finally, AI-based decision support assists in TNM staging classification, metastasis prediction, and personalized treatment guidance, improving precision in diagnosis, prognosis, and therapeutic planning for lung cancer patients.

Figure 5

The role of AI in optimizing oncological therapies through a structured three-step process. The first step involves patient data collection and biomarker analysis, integrating genomic and molecular profiling, histopathological assessments, and radiomics-based imaging analysis. AI-driven models then facilitate therapy optimization, predicting responses to chemotherapy, immunotherapy, and radiotherapy, aiding in personalized treatment selection. Finally, AI enhances therapy administration and patient monitoring, including adaptive radiation therapy, AI-guided drug development, and remote monitoring for treatment-related toxicities. This framework enables a more precise, efficient, and personalized approach to cancer treatment, improving patient outcomes and minimizing adverse effects.

Figure 6

The intraoperative role of AI in robotic-assisted thoracic surgery, illustrating AI’s impact on imaging, decision support, and surgical execution. AI enhances intraoperative imaging through real-time augmented visualization and 3D reconstruction. In decision support, AI provides predictive analytics, real-time risk assessment, and tumor margin identification. Finally, AI refines surgical execution by improving robotic precision, instrument tracking, and hybrid robotic–manual techniques, contributing to greater accuracy and patient safety.