The Use of Artificial Intelligence and Machine Learning in Surgery: A Comprehensive Literature Review

Abstract

Interest in the use of artificial intelligence (AI) and machine learning (ML) in medicine has grown exponentially over the last few years. With its ability to enhance speed, precision, and efficiency, AI has immense potential, especially in the field of surgery. This article aims to provide a comprehensive literature review of artificial intelligence as it applies to surgery and discuss practical examples, current applications, and challenges to the adoption of this technology. Furthermore, we elaborate on the utility of natural language processing and computer vision in improving surgical outcomes, research, and patient care.

Deep Learning Applications in Surgery: Current Uses and Future Directions

“…Within neurosurgery, surgical phase recognition is beginning to gain traction as a method to improve neurosurgical workflow, identify critical structures, prevent potential complications, and refine surgical training. 2,48,49 As deep computer vision techniques become increasingly validated and applied in laparoscopic general surgery, the surgical community's mounting interest and confidence in the technology has paved the way for application in neurosurgery. 14,24,50 Surgical phase recognition can aid neurosurgical procedures by identifying critical structures to prevent injury to structures such as the carotid artery or pituitary stalk in pituitary surgeries.…”

“…In a 2021 study, Lou et al applied deep learning image analysis to eyelid morphology to analyze the features before and after blepharoplastosis surgery, involving eyelid length, corneal area measurements, and postoperative eyelid contour symmetry. 2,53 The regions of interest were processed through the Attention Recurrent Residual Convolutional Neural Network based on the deep learning technique used for semantic medical image segmentation called U-Net (R2U-Net). 56 The output showed an intraclass correlation coefficient between manual and automated measurements of the margin reflex distance of operated eyes in a range from .934 to .971 (P > .001), supporting its potential application for automating the assessment of eyelid features to streamline timeconsuming manual measurements.…”

“…The field of AI in a broad sense encompasses the mechanism by which machines can be trained to mimic a human brain and its capabilities, through sets of rules dictated by an algorithm. 1,2 Machine learning (ML) is an application of AI for the development of a program in which the system learns and improves automatically as it provides an output. ML uses observations on the data to identify potential patterns and improve decision-making, allowing the system to learn experientially and self-improve without explicit programming or other human intervention.…”

Ethical, Legal, and Financial Considerations of Artificial Intelligence in Surgery

“…3,4 While AI has the potential to optimize and transform many aspects of surgical decision-making, as with all new technologies, there are barriers and pitfalls to its integration and acceptance in the surgical field. 5,6 Although AI-assisted surgery and surgical planning are gaining momentum and credibility, the relative novelty and perceived inaccessibility of the technology have hindered widespread adoption. 7 AI can be a powerful aid to decision-making across many fields and industries but can only perform as well as the data available will allow and cannot be treated as infallible or omniscient.…”

“…3,4 While AI has the potential to optimize and transform many aspects of surgical decision-making, as with all new technologies, there are barriers and pitfalls to its integration and acceptance in the surgical field. 5,6…”