Latent Variable Models (LVMs) propose to model the dynamics of neural populations by capturing low-dimensional structures that represent features involved in neural activity. Recent LVMs are based on deep learning methodology where a deep neural network is trained to reconstruct the same neural activity given as input and as a result to build the latent representation. Without taking past or future activity into account such a task is non-causal. In contrast, the task of forecasting neural activity based on given input extends the reconstruction task. LVMs that are trained on such a task could potentially capture temporal causality constraints within its latent representation. Forecasting has received less attention than reconstruction due to recording challenges such as limited neural measurements and trials. In this work, we address modeling neural population dynamics via the forecasting task and improve forecasting performance by including a prior, which consists of pairwise neural unit interaction as a multivariate dynamic system. Our proposed model---Additive, Multiplicative, and Adaptive Graph Neural Network (AMAG)---leverages additive and multiplicative message-passing operations analogous to the interactions in neuronal systems and adaptively learns the interaction among neural units to forecast their future activity. We demonstrate the advantage of AMAG compared to non-GNN based methods on synthetic data and multiple modalities of neural recordings (field potentials from penetrating electrodes or surface-level micro-electrocorticography) from four rhesus macaques. Our results show the ability of AMAG to recover ground truth spatial interactions and yield estimation for future dynamics of the neural population.

Endotracheal Intubation is a lifesaving procedure in which a tube is passed through the mouth into the trachea (windpipe) to maintain an open airway and facilitate artificial respiration. It is a complex psychomotor skill, which requires significant training and experience to prevent complications. The current methods of training, including manikins and cadaver, have limitations in terms of their availability for early medical professionals to learn and practice. These training options also have limitations in terms of presenting high risk/ difficult intubation cases for experts to mentally plan their approach in high-risk scenarios prior to the procedure. In this paper, we present the design considerations and challenges of AirwayVR: virtual reality-based simulation trainer for intubation training for two different target audience (medical professionals) with two different objectives. The first one is to use AirwayVR as an introductory platform to learn and practice intubation in virtual reality for novice learners (Medical students and residents). The second objective is to utilize this technology as a Just-in-time training platform for experts to mentally prepare for a complex case prior to the procedure.

Endotracheal Intubation is a lifesaving procedure in which a tube is passed through the mouth into the trachea (windpipe) to maintain an open airway and facilitate artificial respiration. It is a complex psychomotor skill, which requires significant training and experience to prevent complications. The current methods of training, including manikins and cadaver, have limitations in terms of their availability for early medical professionals to learn and practice. These training options also have limitations in terms of presenting high risk/difficult intubation cases for experts to mentally plan their approach in high-risk scenarios prior to the procedure. In this demo, we present AirwayVR: virtual reality-based simulation trainer for intubation training. Our goal is to utilize virtual reality platform for intubation skills training for two different target audience (medical professionals) with two different objectives. The first one is to use AirwayVR as an introductory platform to learn and practice intubation in virtual reality for novice learners (Medical students and residents). The second objective is to utilize this technology as a Just-in-time training platform for experts to mentally prepare for a complex case prior to the procedure.

Endotracheal intubation is a procedure in which a tube is passed through the mouth into the trachea (windpipe) to maintain an airway and provide artificial respiration. This lifesaving procedure, utilized in many clinical situations, requires complex psychomotor skills. Healthcare providers need significant training and experience to acquire skills necessary for a quick and atraumatic endotracheal intubation to prevent complications. However, medical professionals have limited training platforms and opportunities to be trained on this procedure. In this poster, we present a virtual reality-based simulation trainer for intubation training. This VR based intubation trainer provides an environment for healthcare professionals to assimilate these complex psychomotor skills while also allowing a safe place to practice swift and atraumatic intubation. User survey results are presented demonstrating that VR is a promising platform to train medical professionals effectively for this procedure.