The future of simulation-based medical education: Adaptive simulation utilizing a deep multitask neural network.

BACKGROUND: In resuscitation medicine, effectively managing cognitive load in high-stakes environments has important implications for education and expertise development. There exists the potential to tailor educational experiences to an individual's cognitive processes via real-time physiologic measurement of cognitive load in simulation environments. OBJECTIVE: The goal of this research was to test a novel simulation platform that utilized artificial intelligence to deliver a medical simulation that was adaptable to a participant's measured cognitive load. METHODS: The research was conducted in 2019. Two board-certified emergency physicians and two medical students participated in a 10-minute pilot trial of a novel simulation platform. The system utilized artificial intelligence algorithms to measure cognitive load in real time via electrocardiography and galvanic skin response. In turn, modulation of simulation difficulty, determined by a participant's cognitive load, was facilitated through symptom severity changes of an augmented reality (AR) patient. A postsimulation survey assessed the participants' experience. RESULTS: Participants completed a simulation that successfully measured cognitive load in real time through physiological signals. The simulation difficulty was adapted to the participant's cognitive load, which was reflected in changes in the AR patient's symptoms. Participants found the novel adaptive simulation platform to be valuable in supporting their learning. CONCLUSION: Our research team created a simulation platform that adapts to a participant's cognitive load in real-time. The ability to customize a medical simulation to a participant's cognitive state has potential implications for the development of expertise in resuscitation medicine.

Intravenous Haloperidol Versus Ondansetron for Cannabis Hyperemesis Syndrome (HaVOC): A Randomized, Controlled Trial.

STUDY OBJECTIVE: Little is known about the cause or optimal treatment of hyperemesis in habitual cannabis users. Anecdotal evidence supports the use of haloperidol over traditional antiemetics for this newly recognized disorder. We compare haloperidol with ondansetron for cannabis hyperemesis syndrome. METHODS: We randomized cannabis users with active emesis to either haloperidol (with a nested randomization to either 0.05 or 0.1 mg/kg) or ondansetron 8 mg intravenously in a triple-blind fashion. The primary outcome was the reduction from baseline in abdominal pain and nausea (each measured on a 10-cm visual analog scale) at 2 hours after treatment. Although the trial allowed for crossover, the primary analysis used only the first treatment period because few subjects crossed over. RESULTS: We enrolled 33 subjects, of whom 30 (16 men, aged 29 years [SD 11 years] using 1.5 g/day [SD 0.9 g/day] since age 19 years [SD 2 years]) received at least 1 treatment (haloperidol 13, ondansetron 17). Haloperidol at either dose was superior to ondansetron (difference 2.3 cm [95% confidence interval 0.6 to 4.0 cm]; P=.01), with similar improvements in both pain and nausea, as well as less use of rescue antiemetics (31% versus 59%; difference -28% [95% confidence interval -61% to 13%]) and shorter time to emergency department (ED) departure (3.1 hours [SD 1.7] versus 5.6 hours [SD 4.5]; difference 2.5 hours [95% confidence interval 0.1 to 5.0 hours]; P=.03). There were 2 return visits for acute dystonia, both in the higher-dose haloperidol group. CONCLUSION: In this clinical trial, haloperidol was superior to ondansetron for the acute treatment of cannabis-associated hyperemesis. The efficacy of haloperidol over ondansetron provides insight into the pathophysiology of this now common diagnosis in many EDs.

Toward Dynamically Adaptive Simulation: Multimodal Classification of User Expertise Using Wearable Devices.

Simulation-based training has been proven to be a highly effective pedagogical strategy. However, misalignment between the participant's level of expertise and the difficulty of the simulation has been shown to have significant negative impact on learning outcomes. To ensure that learning outcomes are achieved, we propose a novel framework for adaptive simulation with the goal of identifying the level of expertise of the learner, and dynamically modulating the simulation complexity to match the learner's capability. To facilitate the development of this framework, we investigate the classification of expertise using biological signals monitored through wearable sensors. Trauma simulations were developed in which electrocardiogram (ECG) and galvanic skin response (GSR) signals of both novice and expert trauma responders were collected. These signals were then utilized to classify the responders' expertise, successive to feature extraction and selection, using a number of machine learning methods. The results show the feasibility of utilizing these bio-signals for multimodal expertise classification to be used in adaptive simulation applications.

Hair cannabinoid concentrations in emergency patients with cannabis hyperemesis syndrome.

OBJECTIVES: Cannabis hyperemesis syndrome is characterized by bouts of protracted vomiting in regular users of cannabis. We wondered whether this poorly understood condition is idiosyncratic, like motion sickness or hyperemesis gravidarum, or the predictable dose-response effect of prolonged heavy use. METHODS: Adults with an emergency department visit diagnosed as cannabis hyperemesis syndrome, near-daily use of cannabis for ≥6 months, and ≥2 episodes of severe vomiting in the previous year were age- and sex-matched to two control groups: RU controls (recreational users without vomiting), and ED controls (patients in the emergency department for an unrelated condition). Δ9-Tetrahydrocannabinol (THC), cannabinol (CBN), cannabidiol, and 11-nor-9-carboxy-THC concentrations in scalp hair were compared for subjects with positive urine THC. RESULTS: We obtained satisfactory hair samples from 46 subjects with positive urine THC: 16 cases (age 26.8 ± 9.2 years; 69% male), 16 RU controls and 14 ED controls. Hair cannabinoid concentrations were similar between all three groups (e.g. cases THC 220 [median; IQR 100,730] pg/mg hair, RU controls 150 [71,320] and ED controls 270 [120,560]). Only the THC:CBN ratio was different between groups, with a 2.6-fold (95%CI 1.3,5.7) lower age- and sex-adjusted ratio in cases than RU controls. Hair cannabidiol concentrations were often unquantifiably low in all subjects. CONCLUSIONS: Similar hair cannabinoid concentrations in recreational users with and without hyperemesis suggest that heavy use is necessary but not sufficient for hyperemesis cannabis. Our results underline the high prevalence of chronic heavy cannabis use in emergency department patients and our limited understanding of this plant's adverse effects.

OBJECTIF: Le syndrome d'hyperémèse cannabique se caractérise par des accès prolongés de vomissements chez les grands consommateurs de cannabis. La question était donc de savoir si ce trouble, peu compris encore, relève d'un état idiosyncrasique, comme le mal des transports ou l'hyperémèse gravidique, ou d'un effet de type dose-réponse prévisible chez les grands consommateurs de cannabis. MÉTHODE: Des adultes chez qui un diagnostic de syndrome d'hyperémèse cannabique a été posé au service des urgences (SU), qui faisaient un usage presque quotidien du cannabis depuis ≥ 6 mois et qui ont connu ≥ 2 épisodes de vomissements importants au cours de l'année précédente ont été appariés à deux groupes témoins selon l'âge et le sexe : des témoins faisant un usage récréatif du cannabis, sans vomissements (UR) et des témoins traités au SU (examinés pour des troubles non connexes). La teneur des cheveux en Δ9-tétrahydrocannabinol (THC), en cannabinol (CBN), en cannabidiol et en 11-nor-9-carboxy-THC a été comparée chez les sujets ayant obtenu des résultats positifs à l'égard du THC urinaire. RÉSULTATS: Des échantillons satisfaisants de cheveux ont été prélevés chez 46 sujets ayant obtenu des résultats positifs à l'égard du THC urinaire : 16 cas (âge : 26,8 ± 9,2 ans; sexe masculin : 69%), 16 témoins UR et 14 témoins SU. La teneur des cheveux en cannabinoïdes était comparable dans les trois groupes (cas : THC : 220 pg/mg de cheveux [médiane; écart interquartile : 100­730]; témoins UR : 150 [71­320] et témoins SU : 270 [120­560]). Seul le rapport THC/CBN différait entre les groupes : il était 2,6 fois (IC à 95% : 1,3­5,7) inférieur dans les cas (rapport rajusté selon l'âge et le sexe) que chez les témoins UR. La teneur des cheveux en cannabidiol était souvent non quantifiable, et ce, chez tous les sujets. CONCLUSION: Le fait que la teneur des cheveux en cannabinoïdes était comparable chez les utilisateurs faisant un usage récréatif du cannabis, tant chez ceux qui souffraient d'hyperémèse que chez ceux qui en étaient exempts, donne à penser qu'il y a un usage nécessairement abusif de la drogue mais non suffisant pour causer l'hyperémèse cannabique. Les résultats font ressortir la forte prévalence d'un usage excessif et prolongé du cannabis chez les patients traités au SU et le peu de connaissances que la communauté médicale a des effets indésirables de cette plante.