Eric Poitras

Technology-Rich Tools to Support Self-Regulated Learning and Performance in Medicine

Medical students’ metacognitive and self-regulatory behaviors are examined as they diagnose patient cases using BioWorld, a technology rich learning environment. BioWorld offers an authentic problem-based environment where students solve clinical cases and receive expert feedback. We evaluate the effectiveness of key features in BioWorld (the evidence table and visualization maps) to see whether they promote metacognitive monitoring and evaluation. Learning outcomes were assessed through novice/expert comparisons in relation to diagnostic accuracy, confidence, and case summaries. More specifically we examined how diagnostic processes and learning outcomes were refined or improved through practice at solving a series of patient cases. The results suggest that, with practice, medical students became more expert-like in the processes involved in making crucial clinical decisions. The implications of these findings for the design of features embedded within BioWorld that foster key metacognitive and self-regulatory processes are discussed.

The role of regulation in medical student learning in small groups

Computer supported collaborative problem based learning in medicine can lead to high levels of metacognition.High co-regulation in problem based learning co-occurs with levels of Interactive Social Presence.Co-regulatory actions that activate the discussion and metacognitive acts of planning. This study examines the role of regulatory processes in medical students as they learn to deliver bad news to patients in the context of an international web-based problem based learning environment (PBL). In the PBL a medical facilitator and students work together to examine video cases on giving bad news and share their perspectives on what was done effectively and what could be done differently. We examine how regulation occurs within this collaboration. A synchronous computer-supported collaborative learning environment (CSCL) facilitated peer discussion at a distance using a combination of tools that included video-conferencing, chat boxes, and a shared whiteboard to support collaborative engagement. We examine regulation along a continuum, spanning from self- to co-regulation, in situations where medical students learn how to manage their own emotions and adapt their responses to patient reactions. We examine the nature of the discourse between medical students and facilitators to illustrate the conditions in which metacognitive, co-regulation and social emotional activities occur to enhance learning about how to communicate bad news to patients.

Modeling Metacognitive Activities in Medical Problem-Solving with BioWorld

Medical diagnostic reasoning is ill-defined and complex, requiring novice physicians to monitor and control their problem-solving efforts. Self-regulation is critical for effective medical problem-solving, helping individuals progress towards a correct diagnosis through a series of actions that informs subsequent ones. BioWorld is a computer-based learning environment designed to support novices in developing medical diagnostic reasoning as they receive feedback in the context of solving virtual cases. The system provides tools that scaffold learners in their requisite cognitive and metacognitive activities. Novices attain higher levels of competence as the system dynamically assesses their performance against expert solution paths. Dynamic assessment in this system relies on a novice-expert overlay and it is used to develop feedback when novices request help. When help-seeking occurs, help is provided by the tutoring module which applies a set of pre-defined rules based on the context of the learner’s activity. The system also provides cumulative feedback by comparing the novice solution with an expert solution following completion of the case. This chapter covers the essential design guidelines of this scaffolding approach to metacognitive activities in problem-solving within the domain of medical education. Specifically, we review recent advances in modeling metacognition through online measures, including concurrent think-aloud protocols, video-screen captures, and log-file entries. Educational data mining techniques are outlined with the goals of capturing metacognitive activities as they unfold throughout problem solving, and guiding the design of scaffolding tools in order to promote higher levels of competence in novices.

Co-regulation and knowledge construction in an online synchronous problem based learning setting

Learning to monitor and regulate one’s learning in an academic setting is a task that all students must engage in. Learning in “group” situations requires both self- and co-regulation. This research examines a case study of a small group of medical student interactions during an on-line problem based learning activity (PBL) where students learn to co-regulate their performance as they construct their understanding of how best to communicate bad news to patients. This paper introduces an approach for analyzing the group discourse to understand how collective knowledge building facilitates co-regulation. A mixed method analysis was used to analyze the case study data. A qualitative data analysis of verbal interactions was conducted to examine co-regulatory episodes. Collective knowledge building was examined by analyzing the group discourse for indicators of co-regulatory processes. The study follows two quantitative analyses: a frequency count analysis of types of questions asked by facilitators and students; and a sequential pattern mining for patterns of co-occurrences of learners’ discourse and co-regulation.

Mining case summaries in BioWorld

BioWorld is a computer-based learning environment that was designed to support novices in diagnosing medical diseases. In this study, we examine case summaries written in BioWorld. We explore the use of text classification techniques to mine case summaries written in BioWorld. In particular, we evaluate the accuracy of several text classification algorithms in Diagnosis Correctness and Novice-Expert Overlay Model (i.e., recognizing case summaries written by novice and expert physicians). Experimental results suggest that text classification is a promising approach for mining case summaries.

Towards Evaluating and Modelling the Impacts of Mobile-Based Augmented Reality Applications on Learning and Engagement

Mobile augmented reality applications are increasingly utilized as a medium for enhancing learning and engagement in history education. Although these digital devices facilitate learning through immersive and appealing experiences, their design should be driven by theories of learning and instruction. We provide an overview of an evidence-based approach to optimize the development of mobile augmented reality applications that teaches students about history. Our research aims to evaluate and model the impacts of design parameters towards learning and engagement. The research program is interdisciplinary in that we apply techniques derived from design-based experiments and educational data mining. We outline the methodological and analytical techniques as well as discuss the implications of the anticipated findings.

Person-Oriented Approaches to Profiling Learners in Technology-Rich Learning Environments for Ecological Learner Modeling

Technology-rich learning environments (TREs) provide opportunities for learners to engage in complex interactions involving a multitude of cognitive, metacognitive, and affective states. Understanding learners’ distinct learning progressions in TREs demand inquiry approaches that employ well-conceived theoretical accounts of these multiple facets. The present study investigated learners’ interactions with BioWorld, a TRE developed to guide students’ clinical reasoning through diagnoses of simulated patients. We applied person-oriented analytic methods to multimodal data including verbal protocols, questionnaires, and computer logs from 78 task solutions. Latent class analysis, clustering methods, and latent profile analysis followed by logistic regression analyses revealed that students’ clinical diagnosis ability was positively correlated with advanced self-regulated learning behaviors, high confidence and cognitive strategy use, critical attention to experts’ feedback, and their positive emotional responses to feedback. The study results have the potential to contribute to a theory-guided approach to designing TREs with a data-driven assessment of multidimensional growth. Building on the study results, we introduce and discuss an ecological learner model for assessing multidimensional learner traits which can be used to design a TRE for adaptive scaffolding.

Supporting diagnostic reasoning by modeling help-seeking

Help-seeking is considered an important metacognitive strategy. For learners to benefit from help-seeking, they need to be engaged in effective search behaviors. Maladaptive search behaviors can lead to negative learning outcomes; thus, if learners are cognizant of such behaviors, they can engage in effective help-seeking leading to achieve better learner outcomes. To foster effective help-seeking, we need to better understand the behaviors learners engage in when seeking help. In this study, we examined help-seeking behaviors of learners, in relation to what learners examined in an online library embedded within BioWorld. The library tool is a resource provides information about diseases, diagnostic tests and medical terms. This paper reports the model search behaviors pertaining to the medical topics searched in the library. The findings have implications for developing scaffolding prompts that can encourage effective search behaviors.

Using the metahistoreasoning tool training module to facilitate the acquisition of domain-specific metacognitive strategies

Learning through historical inquiry requires that students engage in domain-specific metacognitive strategies. For example, students need to be aware that causes of historical events are often unknown or uncertain and they need strategies for resolving such ambiguity. In this paper, we provide an overview of the theoretical, instructional, and empirical foundations of the MetaHistoReasoning Tool Training Module. This computer-based learning environment is designed to facilitate the acquisition of metacognitive strategies that are critical in learning through historical inquiry. We review findings pertaining to (1) the classes of self-explanations generated and (2) the accuracy of categorizations made by students. We discuss these findings in terms of developing an artificial pedagogical agent capable of appropriately delivering instructional explanations and effectively prompting self-explanations.

Towards examining learner behaviors in a medical intelligent tutoring system: A Hidden Markov Model approach

In BioWorld, a medical intelligent tutoring system, novice physicians are tasked with diagnosing virtual patient cases. Although we are often interested in considering whether learners diagnosed the case correctly or not, we cannot discount the actions that learners take to arrive at a final diagnosis. Thus, the consideration of the sequence of actions becomes important. In this preliminary study, we propose a line of research to investigate learner actions involved in diagnosing virtual patient cases using Hidden Markov Models.