Case scenario generators for trauma surgery simulation utilizing autoregressive language models.

Trauma is the leading cause of death in adults under the age of 45 and the fourth leading cause of death in the United States. Effective delivery of trauma care centers on being well versed in the Advanced Trauma Life Support (ATLS) protocol, which requires high levels of clinical experience. Often this comes from having been exposed to the many permutations of common types of injuries as well as exposed to rarer scenarios, but with potential harm to patients. Case scenarios, which are sequential representations of clinical events, can help trainees receive clinical exposure without harming patients. However authoring case scenarios requires domain expertise, wide experience, and the ability to intelligently respond to inputs, and as such is currently an arduous task. Autoregressive generative models trained on large amounts of clinical data, such as the National Trauma Data Bank (NTDB), pose a possible solution to overcome the cost of authorship while providing broad and accessible clinical experience to trainees. We have developed a Trauma AI model composed of an autoregressive generative model based on the transformer architecture for generating potential case scenario combined with an out-of-domain detection for filtering out less plausible scenarios. The GPT2 model is trained on 1.1 million case scenarios derived from the NTDB data. We demonstrate that Trauma AI is capable of generating realistic case scenarios that encode the ATLS protocol as a latent feature of the sequence of provider interventions, including scenarios that do not have any parallels in the original dataset. We also present an unsupervised means of filtering out unrealistic sequences by identifying out-of-domain sequences, and demonstrate that this improves the realism of the generated case scenarios.

A novel agent-based, evolutionary model for expressing the dynamics of creative open-problem solving in small groups.

Understanding the process of producing creative responses to open-ended problems solved in small groups is important for many modern domains, like health care, manufacturing, education, banking, and investment. Some of the main theoretical challenges include characterizing and measuring the dynamics of responses, relating social and individual aspects in group problem solving, incorporating soft skills (e.g., experience, social aspects, and emotions) to the theory of decision making in groups, and understanding the evolution of processes guided by soft utilities (hard-to-quantify utilities), e.g., social interactions and emotional rewards. This paper presents a novel theoretical model (TM) that describes the process of solving open-ended problems in small groups. It mathematically presents the connection between group member characteristics, interactions in a group, group knowledge evolution, and overall novelty of the responses created by a group as a whole. Each member is modeled as an agent with local knowledge, a way of interpreting the knowledge, resources, social skills, and emotional levels associated to problem goals and concepts. Five solving strategies can be employed by an agent to generate new knowledge. Group responses form a solution space, in which responses are grouped into categories based on their similarity and organized in abstraction levels. The solution space includes concrete features and samples, as well as the causal sequences that logically connect concepts with each other. The model was used to explain how member characteristics, e.g., the degree to which their knowledge is similar, relate to the solution novelty of the group. Model validation compared model simulations against results obtained through behavioral experiments with teams of human subjects, and suggests that TMs are a useful tool in improving the effectiveness of small teams.

Linking the Divergent and Convergent Processes of Collaborative Creativity: The Impact of Expertise Levels and Elaboration Processes.

We examined the impact of task-relevant expertise level in groups on the idea sharing and elaboration process and on idea development. Participants were assigned to low, heterogeneous, and high expertise groups and were asked to generate ideas for the development of a new sport. Following two asynchronous divergent ideation phases using an electronic discussion board for ideational exchanges, groups completed a synchronous convergent discussion phase in which they selected and refined their ideas for a new sport. The number of ideas and their novelty during the divergent phase did not influence the outcome of the convergent phase. However, consistent with our theoretical model final product novelty was influenced by the number and novelty of the replies in the divergent phase. Although group expertise level was associated with various performance outcomes in the divergent ideation phase, it did not impact the novelty of the final product. Low expertise groups demonstrated the most novelty in the divergent phase. Final product novelty was also associated with sports words used in discussions during the convergent phase.

Neural dynamics of idea generation and the effects of priming.

Idea generation is a fundamental attribute of the human mind, but the cognitive and neural mechanisms underlying this process remain unclear. In this paper, we present a dynamic connectionist model for the generation of ideas within a brainstorming context. The key hypothesis underlying the model is that ideas emerge naturally from itinerant attractor dynamics in a multi-level, modular semantic space, and the potential surface underlying this dynamics is itself shaped dynamically by task context, ongoing evaluative feedback, inhibitory modulation, and short-term synaptic modification. While abstract, the model attempts to capture the interplay between semantic representations, working memory, attentional selection, reinforcement signals, and modulation. We show that, once trained on a set of contexts and ideas, the system can rapidly recall stored ideas in familiar contexts, and can generate novel ideas by efficient, multi-level dynamical search in both familiar and unfamiliar contexts. We also use a simplified continuous-time instantiation of the model to explore the effect of priming on idea generation. In particular, we consider how priming low-accessible categories in a connectionist semantic network can lead to the generation of novel ideas. The mapping of the model onto various regions and modulatory processes in the brain is also discussed briefly.

Network capacity analysis for latent attractor computation.

Attractor networks have been one of the most successful paradigms in neural computation, and have been used as models of computation in the nervous system. Recently, we proposed a paradigm called 'latent attractors' where attractors embedded in a recurrent network via Hebbian learning are used to channel network response to external input rather than becoming manifest themselves. This allows the network to generate context-sensitive internal codes in complex situations. Latent attractors are particularly helpful in explaining computations within the hippocampus--a brain region of fundamental significance for memory and spatial learning. Latent attractor networks are a special case of associative memory networks. The model studied here consists of a two-layer recurrent network with attractors stored in the recurrent connections using a clipped Hebbian learning rule. The firing in both layers is competitive--K winners take all firing. The number of neurons allowed to fire, K, is smaller than the size of the active set of the stored attractors. The performance of latent attractor networks depends on the number of such attractors that a network can sustain. In this paper, we use signal-to-noise methods developed for standard associative memory networks to do a theoretical and computational analysis of the capacity and dynamics of latent attractor networks. This is an important first step in making latent attractors a viable tool in the repertoire of neural computation. The method developed here leads to numerical estimates of capacity limits and dynamics of latent attractor networks. The technique represents a general approach to analyse standard associative memory networks with competitive firing. The theoretical analysis is based on estimates of the dendritic sum distributions using Gaussian approximation. Because of the competitive firing property, the capacity results are estimated only numerically by iteratively computing the probability of erroneous firings. The analysis contains two cases: the simple case analysis which accounts for the correlations between weights due to shared patterns and the detailed case analysis which includes also the temporal correlations between the network's present and previous state. The latter case predicts better the dynamics of the network state for non-zero initial spurious firing. The theoretical analysis also shows the influence of the main parameters of the model on the storage capacity.