Exploring Artificial Intelligence in Orthopedic Surgery: A Review of Perception, Decision, and Execution Systems

No prior work had resolved the full scope of how machine learning integrates across the entire surgical workflow. That uncertainty drove the need for a structured analysis of current technological capabilities. Prior research has shown that digital tools are increasingly common in operating rooms. However, the literature remained fragmented regarding how these systems interact during complex procedures. This gap motivated a systematic look at the evolution of surgical support technologies. It was already known that traditional methods often lack the precision offered by modern computational models. Researchers previously focused on isolated components rather than the holistic surgical process. This review addresses the need to synthesize disparate findings into a unified framework for future development.

This review aims to provide a comprehensive analysis of artificial intelligence applications within the field of orthopedic surgery. The authors seek to organize recent technological advancements into a clear, logical framework. By focusing on three core domains, the study addresses the complexity of modern surgical support systems. The researchers intend to map the evolution of these tools from basic models to advanced, adaptive architectures. This work clarifies how different systems interact to improve surgical precision and patient safety. The motivation stems from the need to synthesize a large volume of recent literature into actionable insights. The authors aim to identify the main challenges that currently hinder the translation of these technologies into clinical settings. Finally, the review provides a roadmap to guide future research toward more integrated and effective surgical assistance.

The review approach involved a systematic synthesis of 89 recent academic publications. Investigators organized these findings using a structured perception-decision-execution framework to categorize various technological applications. This methodology allowed for the identification of patterns across distinct surgical domains. The authors evaluated the progression from basic models to advanced architectures within each category. By mapping these developments, the team assessed the current state of clinical translation. The design focused on highlighting the mutuality between different system types. Researchers performed a qualitative assessment of the literature to identify pivotal challenges. This approach provides a comprehensive overview of the field without relying on original experimental data.

The literature reveals that perception systems have evolved from basic convolutional neural network models to sophisticated transformer architectures. These advanced systems now support multi-modal data fusion and enable uncertainty quantification for better surgical accuracy. Decision systems have moved past rigid rule-based methods toward data-driven models that facilitate continuous outcome optimization. These models provide improved surgical planning and more accurate risk prediction for patients. Execution systems have transitioned from passive navigation tools to active robotic assistance with real-time adaptive capabilities. The synthesis of 89 studies confirms that these technological advancements are becoming increasingly integrated into the surgical workflow. The findings demonstrate that current innovations are shifting toward more autonomous and responsive support systems. This analysis confirms that the field is moving toward a more holistic integration of digital tools.

The authors propose that closed-loop surgical assistance represents the primary trajectory for upcoming technological advancements. They suggest that current limitations in clinical translation must be addressed to realize the full potential of these tools. The synthesis indicates that integrating perception, decision, and execution systems will improve patient outcomes. Researchers highlight that moving beyond passive navigation is necessary for achieving real-time adaptive capabilities. The review implies that data-driven models will continue to replace rigid rule-based planning methods. Authors emphasize the importance of multi-modal data fusion for enhancing surgical accuracy. The findings suggest that future innovations should prioritize seamless interaction between different system domains. This work provides a roadmap to guide the transition of these technologies into standard clinical practice.