Deep Learning Model for Automated Trainee Assessment During High-Fidelity Simulation.

PROBLEM: Implementation of competency-based medical education has necessitated more frequent trainee assessments. Use of simulation as an assessment tool is limited by access to trained examiners, cost, and concerns with interrater reliability. Developing an automated tool for pass/fail assessment of trainees in simulation could improve accessibility and quality assurance of assessments. This study aimed to develop an automated assessment model using deep learning techniques to assess performance of anesthesiology trainees in a simulated critical event. APPROACH: The authors retrospectively analyzed anaphylaxis simulation videos to train and validate a deep learning model. They used an anaphylactic shock simulation video database from an established simulation curriculum, integrating a convenience sample of 52 usable videos. The core part of the model, developed between July 2019 and July 2020, is a bidirectional transformer encoder. OUTCOMES: The main outcome was the F1 score, accuracy, recall, and precision of the automated assessment model in analyzing pass/fail of trainees in simulation videos. Five models were developed and evaluated. The strongest model was model 1 with an accuracy of 71% and an F1 score of 0.68. NEXT STEPS: The authors demonstrated the feasibility of developing a deep learning model from a simulation database that can be used for automated assessment of medical trainees in a simulated anaphylaxis scenario. The important next steps are to (1) integrate a larger simulation dataset to improve the accuracy of the model; (2) assess the accuracy of the model on alternative anaphylaxis simulations, additional medical disciplines, and alternative medical education evaluation modalities; and (3) gather feedback from education leadership and clinician educators surrounding the perceived strengths and weaknesses of deep learning models for simulation assessment. Overall, this novel approach for performance prediction has broad implications in medical education and assessment.

An exploration of the reflow technique for the fabrication of an in vitro microvascular system to study occlusive clots.

Embolic ischemia and pulmonary embolism are health emergencies that arise when a particle such as a blood clot occludes a smaller blood vessel in the brain or the lungs, and restricts flow of blood downstream of the vessel. In this work, the reflow technique (Wang et al. Biomed. Microdevices 2007, 9, 657) was adapted to produce a microchannel network that mimics the occlusion process. The technique was first revisited and a simple geometrical model was developed to quantitatively explain the shapes of the resulting microchannels for different reflow parameters. A critical modification was introduced to the reflow protocol to fabricate nearly circular microchannels of different diameters from the same master, which is not possible with the traditional reflow technique. To simulate the phenomenon of occlusion by clots, a microchannel network with three generations of branches with different diameters and branching angles was fabricated, into which fibrin clots were introduced. At low constant pressure drop (ΔP), a clot blocked a branch entrance only partially, while at higher ΔP, the branch was completely blocked. Instances of simultaneous blocking of multiple channels by clots, and the consequent changes in the flow rates in the unblocked branches of the network, were also monitored. This work provides the framework for a systematic study of the distribution of clots in a network, and the rate of dissolution of embolic clots upon the introduction of a thrombolytic drug into the network.