LI Peiyi 1,2,3 , CAI Jianwen 1,2 , ZHU Tao 1,3 , LI Weimin 4,5,6
  • 1. Department of Anesthesiology, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
  • 2. Laboratory of Anesthesia and Critical Care Medicine, National-Local Joint Engineering Research Centre of Translational Medicine of Anesthesiology, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
  • 3. The Research Units of West China (2018RU012)-Chinese Academy of Medical Sciences, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
  • 4. Department of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
  • 5. Institute of Respiratory Health, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
  • 6. State Key Laboratory of Respiratory Health and Multimorbidity, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
LI Weimin, Email: weimi003@scu.edu.cn
Artificial intelligence; Perioperative period; Qualitative research; Systematic review
10.7507/1672-2531.202405012
Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables References Cited by

Objective To systematically review the qualitative research on the obstacles and promoting factors of artificial intelligence implementation in the real perioperative world. Methods Computer searches were conducted on PubMed, CINAHL, Scopus, Web of Science, ACM Digital Library, Cochrane Library, CNKI, WanFang Data, and VIP databases to collect perioperative studies related to the clinical application of artificial intelligence. The search period was from database establishment until December 31, 2023. Based on the SPIDER model, the quality of the included literature was evaluated using the JBI Epidemiological Scale. The NASSS framework was used to integrate and analyze the qualitative factors discovered during the implementation of the perioperative artificial intelligence system, and a problem item pool was established. Results A total of 22 articles were included, and perioperative stakeholders mainly focused on perioperative artificial intelligence technology users such as anesthesiologists, anesthesiologists, and surgeons. The field of perioperative artificial intelligence services mainly focused on robot surgery. The JBI evaluation score was 4-8 points. The NASSS implementation factor framework consisted of 7 core themes and 18 secondary items. Conclusion It is undeniable that perioperative artificial intelligence has a positive impact on the prognosis, medical quality, and efficiency of surgical patients. However, its clinical application will face influences from adopters, organizational structures, social culture, and other aspects, which will ultimately affect its implementation effect. The existing qualitative research on the influencing factors of perioperative artificial intelligence systems in clinical implementation has problems such as limited quantity, moderate quality, and lack of scientific research based on a systematic implementation factor framework. Conducting scientific and standardized application research will have a guiding effect on the future use of perioperative artificial intelligence and is expected to improve its final service effectiveness.