Iranian
Biomedical Journal
Volume 28 - Supplementary
IBJ 2024, 28 - Supplementary: 372-372 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Jalalkamali E, Moradimajd P, Jalalkamali P, Aligholizadeh M, Sarkhosh M, AkbarPour P, et al . Impact of Artificial Intelligence on the Prevention of Medical Errors in Anesthesia. IBJ 2024; 28 :372-372
URL: http://ibj.pasteur.ac.ir/article-1-4811-en.html
URL: http://ibj.pasteur.ac.ir/article-1-4811-en.html
Elnaz Jalalkamali * 
, Parisa Moradimajd , Parinaz Jalalkamali , Maryam Aligholizadeh , Maryam Sarkhosh , Parisa AkbarPour , Siavash Sangi , Alireza Jalalkamali
, Parisa Moradimajd , Parinaz Jalalkamali , Maryam Aligholizadeh , Maryam Sarkhosh , Parisa AkbarPour , Siavash Sangi , Alireza Jalalkamali
Abstract:
Introduction: The impact of artificial intelligence (AI) on preventing medical errors in anesthesia is a critical area of research. Medical errors during anesthesia administration can have severe consequences, including patient harm or death. AI can mitigate these risks by enhancing decision-making, monitoring and preventing errors. This study aimed to explore the impact of AI on preventing medical errors in anesthesia.
Search Strategy: A comprehensive literature search was conducted using PubMed, Embase, Cochrane, and CINAHL databases with the MeSH terms "Artificial Intelligence", "Anesthesia", "Medical Errors", and "Patient Safety" from January 1, 2010, to December 31, 2023. Inclusion criteria encompassed peer-reviewed studies focusing on AI applications in anesthesia and their impact on error prevention, excluding non-English studies, case reports, and studies lacking quantitative data. Data extraction included study characteristics, AI applications, error types, and outcomes. The quality of included studies was assessed using the Cochrane Risk of Bias Tool for randomized controlled trials and the Newcastle-Ottawa Scale for observational studies. The systematic review followed the PRISMA guidelines.
Results: The initial search yielded 1,247 articles, of which 28 met the inclusion criteria. AI-based decision support systems, automated monitoring, and predictive analytics were found to significantly reduce medication errors, dosing errors, and adverse events during anesthesia administration. AI-assisted monitoring systems improved the detection of physiological changes and facilitated timely interventions. Additionally, AI-powered clinical decision support tools enhanced adherence to evidence-based guidelines and protocols, minimizing human errors.
Conclusion and Discussion: Integrating AI technologies in anesthesia practice has demonstrated promising results in reducing medical errors and improving patient safety. However, adopting AI in anesthesia requires understanding anesthesiologists' attitudes towards these technologies. AI tools and hardware technologies have the potential to revolutionize anesthesia practice by aiding in decision-making and addressing clinical issues proactively. However, further research is needed to address data quality, algorithm bias, and user acceptance challenges. Interdisciplinary collaboration between clinicians, data scientists, and ethicists is crucial to ensure responsible and practical implementation of AI in anesthesia.
Search Strategy: A comprehensive literature search was conducted using PubMed, Embase, Cochrane, and CINAHL databases with the MeSH terms "Artificial Intelligence", "Anesthesia", "Medical Errors", and "Patient Safety" from January 1, 2010, to December 31, 2023. Inclusion criteria encompassed peer-reviewed studies focusing on AI applications in anesthesia and their impact on error prevention, excluding non-English studies, case reports, and studies lacking quantitative data. Data extraction included study characteristics, AI applications, error types, and outcomes. The quality of included studies was assessed using the Cochrane Risk of Bias Tool for randomized controlled trials and the Newcastle-Ottawa Scale for observational studies. The systematic review followed the PRISMA guidelines.
Results: The initial search yielded 1,247 articles, of which 28 met the inclusion criteria. AI-based decision support systems, automated monitoring, and predictive analytics were found to significantly reduce medication errors, dosing errors, and adverse events during anesthesia administration. AI-assisted monitoring systems improved the detection of physiological changes and facilitated timely interventions. Additionally, AI-powered clinical decision support tools enhanced adherence to evidence-based guidelines and protocols, minimizing human errors.
Conclusion and Discussion: Integrating AI technologies in anesthesia practice has demonstrated promising results in reducing medical errors and improving patient safety. However, adopting AI in anesthesia requires understanding anesthesiologists' attitudes towards these technologies. AI tools and hardware technologies have the potential to revolutionize anesthesia practice by aiding in decision-making and addressing clinical issues proactively. However, further research is needed to address data quality, algorithm bias, and user acceptance challenges. Interdisciplinary collaboration between clinicians, data scientists, and ethicists is crucial to ensure responsible and practical implementation of AI in anesthesia.
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
IBJ is a member of Committee on Publication Ethics (COPE)
and follows its guidelines |
The articles of this journal are licensed under
a Creative Commons Attribution-NonDerivatives 4.0 International License. .png) |
 IBJ is owned and published by Pasteur Institute of Iran |