Artificial Intelligence in Breast Cancer Diagnosis and Surgical Decision-Making: An Updated and Comprehensive Overview of Precision and Personalization in Current Evidence

摘要

Breast cancer (BC) surgery has been advanced through artificial intelligence (AI), which helps surgeons to gain more accurate results and apply surgical procedures. Despite the increasing focus on AI in BC management, there are knowledge gaps in the current understanding that can be readily identified from the existing works of literature. This narrative review aims to provide an update on the influencing role of AI technologies in precise and personalized clinical decision-making in BC surgery. We included articles published in English during the past 5 years from the major databases. Furthermore, this review used appropriate keywords with and without Boolean operators like "AND", "OR" and "NOT". We considered three major aspects for surgical practice: preoperative planning, intraoperative decision-making, and postoperative outcomes, while interpreting the studies. We found that AI-assisted BC surgery has advanced through the development of a new real-time, accurate tumor identifier, margin assessment, and robotic-assisted surgeries. Moreover, AI-based algorithms are gradually incorporated into the evaluation of the postoperative probability of reoccurrence, complications, and patient satisfaction. It is documented that integrating AI technologies into BC care is inevitable and set to expand further in all aspects. Furthermore, this review identified some major challenges in the algorithm and ethical aspects. The limitations, such as lack of external validation, integration barriers, and the "black box" nature of some AI models, remain unresolved. To fully utilize AI's capabilities, it is recommended that surgeons, AI developers, and policymakers collaborate on more advanced AI that is enhanced for personalized care by including patients' genetics, medical history, and lifestyle factors. Additionally, future prospective and exploratory cost-effective analysis studies are to be done.