Artificial Intelligence-Supported Systems in Anesthesiology and Its Standpoint to Date—A Review
Artificial Intelligence-Supported Systems in Anesthesiology and Its Standpoint to Date—A Review作者机构：Department of Anaesthesia Sir Charles Gairdner Hospital Perth Australia
出 版 物：《Open Journal of Anesthesiology》 (麻醉学期刊（英文）)
年 卷 期：2023年第13卷第7期
页 面：140-168页
学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学]
主 题：Artificial Intelligence Anesthesiology Machine Learning Pharmacological Robot Mechanical Robot ChatGPT
摘 要：Artificial intelligence (AI) is the technique that enables computers to solve problems and perform tasks that traditionally require human intelligence. The availability of large amounts of medical data from electronic medical records and powerful modern microcomputers enables the development of AI in medicine. AI has proven its applicability in many different medical areas, such as drug discovery, diagnostic radiology and pathology, as well as interventional applications in cardiology and surgery. However, until today, AI is scarcely used in the clinical practice of anesthesiology. Although there has been a significant body of research published on AI applications for anesthesiology in the literature, the number of developed robot systems for commercial use or those ready for clinical trials remains limited. The limitations of AI systems are identified and discussed, which include incorrect medical data formatting, individual patient variability, the lack of ability of current AI systems, anesthesiologist inexperience in AI usage, system unreliability, unexplainable AI conclusions and strict regulations. In order to ensure anesthesiologists’ trust in AI systems and improve their implementation in daily practice, strict quality control of the systems and algorithms should be undertaken. Further, anesthesiology personnel should play an integral role in the development of AI systems before we are able to see more AI integration in clinical anesthesiology.
维普期刊数据库