Evaluation of machine learning models as decision aids for anesthesiologists.

Machine Learning (ML) models have been developed to predict perioperative clinical parameters. The objective of this study was to determine if ML models can serve as decision aids to improve anesthesiologists' prediction of peak intraoperative glucose values and postoperative opioid requirements. A web-based tool was used to present actual surgical case and patient information to 10 practicing anesthesiologists. They were asked to predict peak glucose levels and post-operative opioid requirements for 100 surgical patients with and without presenting ML model estimations of peak glucose and opioid requirements. The accuracies of the anesthesiologists' estimates with and without ML estimates as reference were compared. A questionnaire was also sent to the participating anesthesiologists to obtain their feedback on ML decision support. The accuracy of peak glucose level estimates by the anesthesiologists increased from 79.0 ± 13.7% without ML assistance to 84.7 ± 11.5% (< 0.001) when ML estimates were provided as reference. The accuracy of opioid requirement estimates increased from 18% without ML assistance to 42% (p < 0.001) when ML estimates were provided as reference. When ML estimates were provided, predictions of peak glucose improved for 8 out of the 10 anesthesiologists, while predictions of opioid requirements improved for 7 of the 10 anesthesiologists. Feedback questionnaire responses revealed that the anesthesiologist primarily used the ML estimates as reference to modify their clinical judgement. ML models can improve anesthesiologists' estimation of clinical parameters. ML predictions primarily served as reference information that modified an anesthesiologist's clinical estimate.

Circumplex Model of Affect: A Measure of Pleasure and Arousal During Virtual Reality Distraction Analgesia.

OBJECTIVE: Immersive virtual reality (VR) distraction provides clinically effective pain relief and increases subjective reports of "fun" in medical settings of procedural pain. The goal of this study was to better describe the variable of "fun" associated with VR distraction analgesia using the circumplex model (pleasure/arousal) of affect. MATERIALS AND METHODS: Seventy-four healthy volunteers (mean age, 29 years; 37 females) received a standardized, 18-minute, multimodal pain sequence (alternating thermal heat and electrical stimulation to distal extremities) while receiving immersive, interactive VR distraction. Subjects rated both their subjective pain intensity and fun using 0-10 Graphic Rating Scales, as well as the pleasantness of their emotional valence and their state of arousal on 9-point scales. RESULTS: Compared with pain stimulation in the control (baseline, no VR) condition, immersive VR distraction significantly reduced subjective pain intensity (P < 0.001). During VR distraction, compared with those reporting negative affect, subjects reporting positive affect did so more frequently (41 percent versus 9 percent), as well as reporting both greater pain reduction (22 percent versus 1 percent) and fun scores (7.0 ± 1.9 versus 2.4 ± 1.4). Several factors-lower anxiety, greater fun, greater presence in the VR environment, and positive emotional valence-were associated with subjective analgesia during VR distraction. CONCLUSIONS: Immersive VR distraction reduces subjective pain intensity induced by multimodal experimental nociception. Subjects who report less anxiety, more fun, more VR presence, and more positive emotional valence during VR distraction are more likely to report subjective pain reduction. These findings indicate VR distraction analgesia may be mediated through anxiolytic, attentional, and/or affective mechanisms.