The development of an opioid sparing anesthesia protocol for pediatric ambulatory tonsillectomy and adenotonsillectomy surgery-A quality improvement project.

Pain management following pediatric tonsillectomy and adenotonsillectomy surgery is challenging and traditionally involves perioperative opioids. However, the recent national opioid shortage compelled anesthesiologists at Bellevue Surgery Center to identify an alternative perioperative analgesic regimen that minimizes opioids yet provides effective pain relief. We assembled an interdisciplinary quality improvement team to trial a series of analgesic protocols using the Plan-Do-Study-Act cycle. Initially, we replaced intraoperative morphine and acetaminophen (M/A protocol) with intraoperative dexmedetomidine and preoperative ibuprofen (D/I protocol). However, when results were not favorable, we rapidly transitioned to intraoperative ketorolac and dexmedetomidine (D/K protocol). The following measures were evaluated using statistical process control chart methodology and interpreted using Shewhart's theory of variation: maximum pain score in the postanesthesia care unit, postoperative morphine rescue rate, postanesthesia care unit length of stay, total anesthesia time, postoperative nausea and vomiting rescue rate, and reoperation rate within 30 days of surgery. There were 333 patients in the M/A protocol, 211 patients in the D/I protocol, and 196 patients in the D/K protocol. With the D/I protocol, there were small increases in maximum pain score and postanesthesia care unit length of stay, but no difference in morphine rescue rate or total anesthesia time compared to the M/A protocol. With the D/K protocol, postoperative pain control and postanesthesia care unit length of stay were similar compared to the M/A protocol. Both the D/I and D/K protocols had reduced nausea and vomiting rescue rates. Reoperation rates were similar between groups. In summary, we identified an intraoperative anesthesia protocol for pediatric tonsillectomy and adenotonsillectomy surgery utilizing dexmedetomidine and ketorolac that provides effective analgesia without increasing recovery times or reoperation rates.

Explainable machine-learning predictions for the prevention of hypoxaemia during surgery.

Although anaesthesiologists strive to avoid hypoxemia during surgery, reliably predicting future intraoperative hypoxemia is not currently possible. Here, we report the development and testing of a machine-learning-based system that, in real time during general anaesthesia, predicts the risk of hypoxemia and provides explanations of the risk factors. The system, which was trained on minute-by-minute data from the electronic medical records of over fifty thousand surgeries, improved the performance of anaesthesiologists when providing interpretable hypoxemia risks and contributing factors. The explanations for the predictions are broadly consistent with the literature and with prior knowledge from anaesthesiologists. Our results suggest that if anaesthesiologists currently anticipate 15% of hypoxemia events, with this system's assistance they would anticipate 30% of them, a large portion of which may benefit from early intervention because they are associated with modifiable factors. The system can help improve the clinical understanding of hypoxemia risk during anaesthesia care by providing general insights into the exact changes in risk induced by certain patient or procedure characteristics.