Trends in Anesthesia Technology

Anesthesia is an ever-evolving field, with new techniques, technology, trends, and practices constantly emerging. In recent years, the introduction of automated technologies such as closed-loop anesthesia delivery systems (CLADS), monitoring technologies, and AI-powered clinical decision support systems has affected the direction of the future of the field. These trends call for more responsible development of anesthesia technology and healthcare technology more broadly, and push anesthesiologists to adapt to a changing landscape of medicine. 

To begin, “perioperative intelligence” technologies built upon machine learning models have the potential to improve patient care and resource allocation in surgery centers and hospitals. In the preoperative phase, machine learning models have proven effective at predicting negative surgery outcomes, such as mortality, hospital length of stay, and the need for intensive care postoperatively (3). Using these predictions, staff members can better allocate limited resources such as ICU beds. Intraoperatively, machine learning models can also forecast adverse situations, such as intraoperative hypotension or intraoperative bradycardia (1).  

Automation in the form of closed-loop anesthesia systems (CLADS) is expected to have a transformative impact on the field. Closed-loop anesthesia delivery systems work by managing an input value to produce a desired output value (4). For example, a ventilator that automatically adjusts minute ventilation in response to detected levels of end-tidal carbon dioxide is a type of CLADS (4). Currently, in the United States, there are yet to be any truly automated CLADS that have been approved for use in clinical settings (4). However, this reality is likely to change, as CLADS are undergoing extensive preclinical and clinical trials worldwide. In a multi-center, randomized controlled trials, CLADS outperformed manual operation when managing proprietary bispectral index and heart rate based on levels of propofol and fentanyl (3). The development of such technology and widespread interest suggests a future trend in anesthesiologists providing a more supervisory and emergency intervention role in the operating room. 

Clinical decision support systems (CDS) are another form of automation that is changing the role of anesthesiologists. CDS make recommendations based on evidence of best practice in various clinical settings, drawing on the healthcare data that was used to train the machine learning model (4). Unlike CLADS, CDS cannot directly provide care to patients and necessitates anesthesiologists to make the final clinical decision with input from the technology. That being said, this technology contributes to the trend of more data- and algorithm-based care in anesthesia. 

Finally, the expansion of telemedicine during the COVID-19 pandemic could help save time and lower healthcare costs related to anesthesia (3). In perioperative care, telemedicine is most routinely used to perform the preoperative patient assessment, including the pre-anesthesia physical exam (4). Electronic stethoscopes now allow providers to perform cardiopulmonary examinations and airway examinations remotely (3). In one study, Applegate and colleagues found that in-person and telemedicine airway examinations correlated with similar surgery outcomes (3). 

Incorporating automated technologies into perioperative care requires that these technologies are developed using sound data. Without diverse and medically accurate data sets, AI-based technologies run the risk of perpetuating existing biases within the healthcare system and providing inaccurate or out-of-context information to clinical providers (4). Furthermore, all healthcare staff members involved in perioperative care need to be trained and educated about best practices for incorporating these technologies to enhance the patient-physician relationship. 

References 

     

      1. Bellini V, Valente M, Gaddi AV, Pelosi P, Bignami E. Artificial intelligence and telemedicine in anesthesia: potential and problems. Minerva Anestesiol. 2022 Sep;88(9):729-734. doi: 10.23736/S0375-9393.21.16241-8. Epub 2022 Feb 14. PMID: 35164492. 

       

        1. John Doyle, D. et al. “Advances in anesthesia technology are improving patient care, but many challenges remain.” BMC Anesthesiology, vol. 18, no. 39, 2018. doi: 10.1186/s12871-018-0504-x 

         

          1. Schnetz, Michael. “Technology Innovations in Anesthesiology.” ASA Monitor, Oct 2021, vol. 85, pp. 18-20. doi: 10.1097/01.ASM.0000795156.20228.a6 

           

            1. Seger, Christian, and Maxime Cannesson. “Recent advances in the technology of anesthesia.” F1000Research vol. 9 F1000 Faculty Rev-375. 18 May. 2020, doi:10.12688/f1000research.24059.1