Application of Machine Learning Algorithms in Automatic Anesthetic Drug Delivery Systems: A literature review

The dynamic advancements in artificial intelligence are enabling the integration of machine learning into medical practice. A significant challenge in modern anesthesiology is the need for precise, continuous adjustment of anesthetic drug doses in response to the patient's rapidly changing physiological state. Traditional manual methods of drug delivery often result in excessive variability in the depth of anesthesia and hemodynamic stability. Utilizing machine learning algorithms represents a modern, promising approach designed to enhance the overall quality and safety of anesthetic care. Aim of the study: The objective of this study is to review the current state of knowledge concerning machine algorithms in automated anesthetic drug delivery systems and to compare these with conventional administration methods, evaluating the benefits and limitations of each approach. Materials and methods: A review of selected literature in the PubMed, Google Scholar database was conducted, using the following keywords: “anesthetic drugs”, “machine learning”, “closed-loop system” “artificial intelligence” Conclusions: The review demonstrates that Machine Learning-driven Closed-Loop Anesthesia Delivery Systems (CLADS) offer superior stability of anesthetic depth and hemodynamic control compared to manual administration. The implementation of AI allows for the personalization of therapy and a significant reduction in drug and gas wastage, supporting the "Green Anesthesia" initiative. Furthermore, automation contributes to better long-term outcomes, such as reduced incidence of postoperative delirium and cognitive dysfunction. However, despite high autonomy, the "human-in-the-loop" paradigm remains essential due to technical artifacts and unforeseen surgical events. Future research should focus on regulatory standardization and the integration of multi-loop systems managing hypnosis, analgesia, and neuromuscular blockade simultaneously.