Epstein, Richard H.

Interest in the potential applications of artificial intelligence in medicine, anesthesiology, and the world at large has never been higher. The Anesthesia Research Council steering committee formed an anesthesiologist artificial intelligence expert workgroup charged with evaluating the current state of artificial intelligence in anesthesiology, providing examples of future artificial intelligence applications and identifying barriers to artificial intelligence progress. The workgroup’s findings are summarized here, starting with a brief introduction to artificial intelligence for clinicians, followed by overviews of current and anticipated artificial intelligence–focused research and applications in anesthesiology. Anesthesiology’s progress in artificial intelligence is compared to that of other medical specialties, and barriers to artificial intelligence development and implementation in our specialty are discussed. The workgroup’s recommendations address stakeholders in policymaking, research, development, implementation, training, and use of artificial intelligence–based tools for perioperative care.

Interest in the potential applications of artificial intelligence in medicine, anesthesiology, and the world at large has never been higher. The Anesthesia Research Council steering committee formed an anesthesiologist artificial intelligence expert workgroup charged with evaluating the current state of artificial intelligence in anesthesiology, providing examples of future artificial intelligence applications and identifying barriers to artificial intelligence progress. The workgroup’s findings are summarized here, starting with a brief introduction to artificial intelligence for clinicians, followed by overviews of current and anticipated artificial intelligence–focused research and applications in anesthesiology. Anesthesiology’s progress in artificial intelligence is compared to that of other medical specialties, and barriers to artificial intelligence development and implementation in our specialty are discussed. The workgroup’s recommendations address stakeholders in policymaking, research, development, implementation, training, and use of artificial intelligence–based tools for perioperative care.

BACKGROUND: Peripheral nerve stimulation with a train-of-four (TOF) pattern can be used intraoperatively to evaluate the depth of neuromuscular block and confirm recovery from neuromuscular blocking agents (NMBAs). Quantitative monitoring can be challenging in infants and children due to patient size, equipment technology, and limited access to monitoring sites. Although the adductor pollicis muscle is the preferred site of monitoring, the foot is an alternative when the hands are unavailable. However, there is little information on comparative evoked neuromuscular responses at those 2 sites. METHODS: Pediatric patients undergoing inpatient surgery requiring NMBA administration were studied after informed consent. Electromyographic (EMG) monitoring was performed simultaneously in each participant at the hand (ulnar nerve, adductor pollicis muscle) and the foot (posterior tibial nerve, flexor hallucis brevis muscle). RESULTS: Fifty patients with a mean age of 3.0 ± standard deviation (SD) 2.9 years were studied. The baseline first twitch amplitude (T1) of TOF at the foot (12.46 mV) was 4.47 mV higher than at the hand ( P <.0001). The baseline TOF ratio (TOFR) before NMBA administration and the maximum TOFR after antagonism with sugammadex were not different at the 2 sites. The onset time until the T1 decreased to 10% or 5% of the baseline value (T1) was delayed by approximately 90 seconds (both P =.014) at the foot compared with the hand. The TOFR at the foot recovered (TOFR ≥0.9) 191 seconds later than when this threshold was achieved at the hand ( P =.017). After antagonism, T1 did not return to its baseline value, a typical finding with EMG monitoring, but the fractional recovery (maximum T1 at recovery divided by the baseline T1) at the hand and foot was not different, 0.81 and 0.77, respectively ( P =.68). The final TOFR achieved at recovery was approximately 100% and was not different between the 2 sites. CONCLUSIONS: Although this study in young children demonstrated the feasibility of TOF monitoring, interpretation of the depth of neuromuscular block needs to consider the delayed onset and the delayed recovery of TOFR at the foot compared to the hand. The delay in achieving these end points when monitoring the foot may impact the timing of tracheal intubation and assessment of adequate recovery of neuromuscular block to allow tracheal extubation (ie, TOFR ≥0.9).

All 36 physicians board-certified in both anesthesiology and clinical informatics as of January 1, 2016, were surveyed via e-mail, with 26 responding. Although most (25/26) generally expressed satisfaction with the clinical informatics boards, and view informatics expertise as important to anesthesiology, most (24/26) thought it unlikely or highly unlikely that substantial numbers of anesthesiology residents would pursue clinical informatics fellowships. Anesthesiologists wishing to qualify for the clinical informatics board examination under the practice pathway need to devote a substantive amount of worktime to informatics. There currently are options outside of formal fellowship training to acquire the knowledge to pass.