Search

BACKGROUND: Postoperative hypotension is associated with adverse outcomes, but intraoperative prediction of postanaesthesia care unit (PACU) hypotension is not routine in anaesthesiology workflow. Although machine learning models may support clinician prediction of PACU hypotension, clinician acceptance of prediction models is poorly understood. METHODS: We developed a clinically informed gradient boosting machine learning model using preoperative and intraoperative data from 88 446 surgical patients from 2015 to 2019. Nine anaesthesiologists each made 192 predictions of PACU hypotension using a web-based visualisation tool with and without input from the machine learning model. Questionnaires and interviews were analysed using thematic content analysis for model acceptance by anaesthesiologists. RESULTS: The model predicted PACU hypotension in 17 029 patients (area under the receiver operating characteristic [AUROC] 0.82 [95% confidence interval {CI}: 0.81–0.83] and average precision 0.40 [95% CI: 0.38–0.42]). On a random representative subset of 192 cases, anaesthesiologist performance improved from AUROC 0.67 (95% CI: 0.60–0.73) to AUROC 0.74 (95% CI: 0.68–0.79) with model predictions and information on risk factors. Anaesthesiologists perceived more value and expressed trust in the prediction model for prospective planning, informing PACU handoffs, and drawing attention to unexpected cases of PACU hypotension, but they doubted the model when predictions and associated features were not aligned with clinical judgement. Anaesthesiologists expressed interest in patient-specific thresholds for defining and treating postoperative hypotension. CONCLUSIONS: The ability of anaesthesiologists to predict PACU hypotension was improved by exposure to machine learning model predictions. Clinicians acknowledged value and trust in machine learning technology. Increasing familiarity with clinical use of model predictions is needed for effective integration into perioperative workflows.

Background Modern medical education requires frequent competency assessment. The Accreditation Council for Graduate Medical Education (ACGME) provides a descriptive framework of competencies and milestones but does not provide standardized instruments to assess and track trainee competency over time. Entrustable professional activities (EPAs) represent a workplace-based method to assess the achievement of competency milestones at the point-of-care that can be applied to anesthesiology training in the United States. Methods Experts in education and competency assessment were recruited to participate in a 6-step process using a modified Delphi method with iterative rounds to reach consensus on an entrustment scale, a list of EPAs and procedural skills, detailed definitions for each EPA, a mapping of the EPAs to the ACGME milestones, and a target level of entrustment for graduating US anesthesiology residents for each EPA and procedural skill. The defined EPAs and procedural skills were implemented using a website and mobile app. The assessment system was piloted at 7 anesthesiology residency programs. After 2 months, faculty were surveyed on their attitudes on usability and utility of the assessment system. The number of evaluations submitted per month was collected for 1 year. Results Participants in EPA development included 18 education experts from 11 different programs. The Delphi rounds produced a final list of 20 EPAs, each differentiated as simple or complex, a defined entrustment scale, mapping of the EPAs to milestones, and graduation entrustment targets. A list of 159 procedural skills was similarly developed. Results of the faculty survey demonstrated favorable ratings on all questions regarding app usability as well as the utility of the app and EPA assessments. Over the 2-month pilot period, 1636 EPA and 1427 procedure assessments were submitted. All programs continued to use the app for the remainder of the academic year resulting in 12,641 submitted assessments. Conclusions A list of 20 anesthesiology EPAs and 159 procedural skills assessments were developed using a rigorous methodology to reach consensus among education experts. The assessments were pilot tested at 7 US anesthesiology residency programs demonstrating the feasibility of implementation using a mobile app and the ability to collect assessment data. Adoption at the pilot sites was variable; however, the use of the system was not mandatory for faculty or trainees at any site.

Background Cannabis legalization may contribute to an increased frequency of chronic use among patients presenting for surgery. At present, it is unknown whether chronic cannabis use modifies the risk of postoperative nausea and vomiting (PONV). Methods This study was a retrospective cohort study conducted at 2 academic medical centers. Twenty-seven thousand three hundred eighty-eight adult ASA 1–3 patients having general anesthesia for non-obstetric, non-cardiac procedures and receiving postoperative care in the Post Anesthesia Care Unit (PACU) were analyzed in the main dataset, and 16,245 patients in the external validation dataset. The main predictor was patient reported use of cannabis in any form collected during pre-anesthesia evaluation and recorded in the chart. The primary outcome was documented PONV of any severity prior to PACU discharge, including administration of rescue medications in PACU. Relevant clinical covariates (risk factors for PONV, surgical characteristics, administered prophylactic antiemetic drugs) were also recorded. Results 10.0% of patients in the analytic dataset endorsed chronic cannabis use. Using Bayesian Additive Regression Trees (BART), we estimated that the relative risk for PONV associated with daily cannabis use was 1.19 (95 CI% 1.00–1.45). The absolute marginal increase in risk of PONV associated with daily cannabis use was 3.3% (95% CI 0.4–6.4%). We observed a lesser association between current, non-daily use of cannabis (RR 1.07, 95% CI 0.94–1.21). An internal validation analysis conducted using propensity score adjustment and Bayesian logistic modeling indicated a similar size and magnitude of the association between cannabis use and PONV (OR 1.15, 90% CI 0.98–1.33). As an external validation, we used data from another hospital in our care system to create an independent model that demonstrated essentially identical associations between cannabis use and PONV. Conclusions Cannabis use is associated with an increased relative risk and a small increase in the marginal probability of PONV.

Purpose of review The purpose of this review is to describe recent developments and current trends in training anesthesiologists in out-of-operating room anesthesia (OORA). Recent findings In the United States, the Accreditation Council for Graduate Medical Education recently updated its training requirements to include a mandatory 2-week rotation in OORA for anesthesiology residents. This likely reflects the continuing expansion of anesthesia services in the out-of-operating room (OOR) environment as well as the increasing complexity of OOR procedures and medical acuity of patients in these settings. In the United Kingdom, the Royal College of Anaesthetists has rigorous and progressively complex requirements for trainees in 'non-theater' anesthesia experience as they move through the four stages of training. A variety of educational strategies and a well-validated six-step process for curriculum development are described in this review. Summary This review will provide useful models for training directors needing to design and implement OOR rotations for their trainees.