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.

One Sentence Summary: We present a new machine learning based system called Prescience that provides interpretable real-time predictions to help anesthesiologists prevent hypoxemia during surgery.Abstract: Hypoxemia causes serious patient harm, and while anesthesiologists strive to avoid hypoxemia during surgery, anesthesiologists are not reliably able to predict which patients will have intraoperative hypoxemia. Using minute by minute EMR data from fifty thousand surgeries we developed and tested a machine learning based system called Prescience that predicts real-time hypoxemia risk and presents an explanation of factors contributing to that risk during general anesthesia. Prescience improved anesthesiologists' performance when providing interpretable hypoxemia risks with contributing factors. The results suggest that if anesthesiologists currently anticipate 15% of events, then with Prescience assistance they could anticipate 30% of events or an estimated additional 2.4 million annually in the US, a large portion of which may be preventable because they are attributable to modifiable factors. The prediction explanations are broadly consistent with the literature and anesthesiologists' prior knowledge. Prescience can also improve clinical understanding of hypoxemia risk during anesthesia by providing general insights into the exact changes in risk induced by certain patient or procedure characteristics. Making predictions of complex medical machine learning models (such as Prescience) interpretable has broad applicability to other data-driven prediction tasks in medicine.peer-reviewed)

Editor’s Perspective What We Already Know about This Topic What This Article Tells Us That Is New Background Complications in pediatric regional anesthesia are rare, so a large sample size is necessary to quantify risk. The Pediatric Regional Anesthesia Network contains data on more than 100,000 blocks administered at more than 20 children’s hospitals. This study analyzed the risk of major complications associated with regional anesthesia in children. Methods This is a prospective, observational study of routine clinical practice. Data were collected on every regional block placed by an anesthesiologist at participating institutions and were uploaded to a secure database. The data were audited at multiple points for accuracy. Results There were no permanent neurologic deficits reported (95% CI, 0 to 0.4:10,000). The risk of transient neurologic deficit was 2.4:10,000 (95% CI, 1.6 to 3.6:10,000) and was not different between peripheral and neuraxial blocks. The risk of severe local anesthetic systemic toxicity was 0.76:10,000 (95% CI, 0.3 to 1.6:10,000); the majority of cases occurred in infants. There was one epidural abscess reported (0.76:10,000, 95% CI, 0 to 4.8:10,000). The incidence of cutaneous infections was 0.5% (53:10,000, 95% CI, 43 to 64:10,000). There were no hematomas associated with neuraxial catheters (95% CI, 0 to 3.5:10,000), but one epidural hematoma occurred with a paravertebral catheter. No additional risk was observed with placing blocks under general anesthesia. The most common adverse events were benign catheter-related failures (4%). Conclusions The data from this study demonstrate a level of safety in pediatric regional anesthesia that is comparable to adult practice and confirms the safety of placing blocks under general anesthesia in children.