scholarly journals Putting the ghost in the machine: exploring human-machine hybrid virtual patient systems for health professional education

Author(s):  
David Topps ◽  
Michelle L Cullen ◽  
Nishan Sharma ◽  
Rachel H Ellaway

Background: Virtual patient authoring tools provide a simple means of creating rich and complex online cases for health professional students to explore. However, the responses available to the learner are usually predefined, which limits the utility of virtual patients, both in terms of replayability and adaptability. Using artificial intelligence or natural language processing is expensive and hard to design. This project description lays out an alternative approach to making virtual patients more adaptable and interactive. Methods: Using OpenLabyrinth, an open-source educational research platform, we modified the interface and functionality to provide a human-computer hybrid interface, where a human facilitator can interact with learners from within the online case scenario. Using a design-based research approach, we have iteratively improved our case designs, workflows and scripts and interface designs. The next step is to robustly test this new functionality in action. This report describes the piloting and background as well as the rationale, objectives, software development implications, learning designs, and educational intervention designs for the planned study. Results: The costs and time required to modify the software were much lower than anticipated. Facilitators have been able to handle text input from multiple concurrent learners. Learners were not discouraged waiting for the facilitator to respond. Discussion: The implementation and use of this new technique seems very promising and there are a great many ways in which it might be used for training and assessment purposes. This report also explores the provisional implications arising from the study so far.

2016 ◽  
Author(s):  
David Topps ◽  
Michelle L Cullen ◽  
Nishan Sharma ◽  
Rachel H Ellaway

Background: Virtual patient authoring tools provide a simple means of creating rich and complex online cases for health professional students to explore. However, the responses available to the learner are usually predefined, which limits the utility of virtual patients, both in terms of replayability and adaptability. Using artificial intelligence or natural language processing is expensive and hard to design. This project description lays out an alternative approach to making virtual patients more adaptable and interactive. Methods: Using OpenLabyrinth, an open-source educational research platform, we modified the interface and functionality to provide a human-computer hybrid interface, where a human facilitator can interact with learners from within the online case scenario. Using a design-based research approach, we have iteratively improved our case designs, workflows and scripts and interface designs. The next step is to robustly test this new functionality in action. This report describes the piloting and background as well as the rationale, objectives, software development implications, learning designs, and educational intervention designs for the planned study. Results: The costs and time required to modify the software were much lower than anticipated. Facilitators have been able to handle text input from multiple concurrent learners. Learners were not discouraged waiting for the facilitator to respond. Discussion: The implementation and use of this new technique seems very promising and there are a great many ways in which it might be used for training and assessment purposes. This report also explores the provisional implications arising from the study so far.


2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Inga Hege ◽  
Isabel Kiesewetter ◽  
Martin Adler

Abstract Background The ability to compose a concise summary statement about a patient is a good indicator for the clinical reasoning abilities of healthcare students. To assess such summary statements manually a rubric based on five categories - use of semantic qualifiers, narrowing, transformation, accuracy, and global rating has been published. Our aim was to explore whether computer-based methods can be applied to automatically assess summary statements composed by learners in virtual patient scenarios based on the available rubric in real-time to serve as a basis for immediate feedback to learners. Methods We randomly selected 125 summary statements in German and English composed by learners in five different virtual patient scenarios. Then we manually rated these statements based on the rubric plus an additional category for the use of the virtual patients’ name. We implemented a natural language processing approach in combination with our own algorithm to automatically assess 125 randomly selected summary statements and compared the results of the manual and automatic rating in each category. Results We found a moderate agreement of the manual and automatic rating in most of the categories. However, some further analysis and development is needed, especially for a more reliable assessment of the factual accuracy and the identification of patient names in the German statements. Conclusions Despite some areas of improvement we believe that our results justify a careful display of the computer-calculated assessment scores as feedback to the learners. It will be important to emphasize that the rating is an approximation and give learners the possibility to complain about supposedly incorrect assessments, which will also help us to further improve the rating algorithms.


Author(s):  
Andrzej A Kononowicz ◽  
Luke Woodham ◽  
Carina Georg ◽  
Samuel Edelbring ◽  
Natalia Stathakarou ◽  
...  

2020 ◽  
Author(s):  
Jan Kiesewetter ◽  
Inga Hege ◽  
Michael Sailer ◽  
Elisabeth Bauer ◽  
Claudia Schulz ◽  
...  

BACKGROUND Learning with virtual patients is highly popular for fostering clinical reasoning in medical education. However, little learning with virtual patients is done collaboratively, despite the potential learning benefits of collaborative vs. individual learning. OBJECTIVE In this article, we describe the rationale behind the implementation of student collaboration in the CASUS virtual patient platform. METHODS The SimpleWebRTC library of andYet was used to implement the collaborative tool. It provided a basis for the conferencing platform and could be adapted to include features such as video communication and screensharing. An additional text chat was created based on the message protocol of the SimpleWebRTC library. We implemented a user interface for educators to set up and configure the collaboration. Educators can configure video, audio, and text-based chat communication, which are known to promote effective learning. RESULTS We tested the tool in a sample of 137 students working on virtual patients. The study results indicate that students successfully diagnosed 53% (SD = 26%) of the patients when working alone and 71% (SD= 20%) when collaborating using the tool (p < .05, eta2=.12). A usability questionnaire for the study sample shows a usability score of 82.16 (SD = 1.31), a B+ grade. CONCLUSIONS The approach provides a technical framework for collaboration that can be used with the CASUS virtual patient system. Additionally, the application programming interface is generic, so that the setup can also be used with other learning management systems. The collaborative tool helps students diagnose virtual patients and results in a good overall usability of CASUS. Using learning analytics, we are able to track students’ progress in content knowledge and collaborative knowledge and guide them through a virtual patient curriculum designed to teach both. More broadly, the collaborative tool provides an array of new possibilities for researchers and educators alike to design courses, collaborative homework assignments, and research questions for collaborative learning.


Author(s):  
Andrzej A Kononowicz ◽  
Luke Woodham ◽  
Carina Georg ◽  
Samuel Edelbring ◽  
Natalia Stathakarou ◽  
...  

2020 ◽  
Author(s):  
Tam ngoc Nguyen

We proposes a new scientific model that enables the ability to collect evidence, and explain the motivations behind people's cyber malicious/ethical behaviors. Existing models mainly focus on detecting already-committed actions and associated response strategies, which is not proactive. That is the reason why little has been done in order to prevent malicious behaviors early, despite the fact that issues like insider threats cost corporations billions of dollars annually, and its time to detection often lasts for more than a year.We address those problems by our main contributions of:+ A better model for ethical/malicious behavioral analysis with a strong focus on understanding people's motivations. + Research results regarding ethical behaviors of more than 200 participants, during the historic Covid-19 pandemic. + Novel attack and defense strategies based on validated model and survey results. + Strategies for continuous model development and integration, utilizing latest technologies such as natural language processing, and machine learning. We employed mixed-mode research approach of: integrating and combining proven behavioral science models, case studying of hackers, survey research, quantitative analysis, and qualitative analysis. For practical deployments, corporations may utilize our model in: improving HR processes and research, prioritizing plans based on the model's informed human behavioral metrics, better analysis in existing or potential cyber insider threat cases, generating more defense tactics in information warfare and so on.


BMJ Open ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. e043970
Author(s):  
Brittany Buffone ◽  
Ilena Djuana ◽  
Katherine Yang ◽  
Kyle J Wilby ◽  
Maguy S El Hajj ◽  
...  

ObjectivesThe global distribution of health professionals and associated training programmes is wide but prior study has demonstrated reported scholarship of teaching and learning arises from predominantly Western perspectives.DesignWe conducted a document analysis to examine authorship of recent publications to explore current international representation.Data sourcesThe table of contents of seven high-impact English-language health professional education journals between 2008 and 2018 was extracted from Embase.Eligibility criteriaThe journals were selected according to highest aggregate ranking across specific scientific impact indices and stating health professional education in scope; only original research and review articles from these publications were included for analysis.Data extraction and synthesisThe table of contents was extracted and eligible publications screened by independent reviewers who further characterised the geographic affiliations of the publishing research teams and study settings (if applicable).ResultsA total 12 018 titles were screened and 7793 (64.8%) articles included. Most were collaborations (7048, 90.4%) conducted by authors from single geographic regions (5851, 86%). Single-region teams were most often formed from countries in North America (56%), Northern Europe (14%) or Western Europe (10%). Overall lead authorship from Asian, African or South American regions was less than 15%, 5% and 1%, respectively. Geographic representation varied somewhat by journal, but not across time.ConclusionsDiversity in health professional education scholarship, as marked by nation of authors’ professional affiliations, remains low. Under-representation of published research outside Global North regions limits dissemination of novel ideas resulting in unidirectional flow of experiences and a concentrated worldview of teaching and learning.


2018 ◽  
Vol 2018 ◽  
pp. 1-7 ◽  
Author(s):  
Zalika Klemenc-Ketis ◽  
Branka Cagran ◽  
Dejan Dinevski

Introduction. A “virtual patient” is defined as a computer program which simulates real patients’ cases. The aim of this study was to determine whether the inclusion of virtual patients affects the level of factual knowledge of family medicine students at the undergraduate level. Methods. This was a case-controlled prospective study. The students were randomly divided into experimental (EG: N=51) and control (CG: N=48) groups. The students in the EG were asked to practice diagnosis using virtual patients instead of the paper-based clinical cases which were solved by the students in the CG. The main observed variable in the study was knowledge of family medicine, determined by 50 multiple choice questions (MCQs) about knowledge of family medicine. Results. There were no statistically significant differences in the groups’ initial knowledge. At the final assessment of knowledge, there were no statistically significant differences between the groups, but there was a statistically significant difference between their initial and final knowledge. Conclusions. The study showed that adding virtual patient cases to the curriculum, instead of paper clinical cases, did not affect the level of factual knowledge about family medicine. Virtual patients can be used, but a significant educational outcome is not expected.


2015 ◽  
Vol 41 (1) ◽  
Author(s):  
Samantha Adams ◽  
François De Kock

Orientation: Organisations compete fiercely to recruit the best graduates, because they consider them a rich source of future talent. In the recruitment literature, it has become increasingly important to understand the factors that influence graduate applicant intentions. Research purpose: Drawing on the theory of planned behaviour (TPB), we tested a model proposing that applicant intention is a function of their attitude towards applying, beliefs about referent other’s expectations (subjective norms) and perceived behavioural control with respect to this behaviour.Motivation for the study: The study was motivated by the need to shed light on graduate applicants’ decisions to apply to an organisation of their choice. Research approach, design and method: The study used a quantitative design to test hypotheses that attitudes towards behaviour, norms and control beliefs would influence intention to apply. We surveyed prospective job seekers (N = 854) studying at a South African university about their beliefs regarding the job application process. Main findings: Structural equation modelling showed reasonable fit of the proposed model to the survey data. Latent variable analysis demonstrated that perceived behavioural control and subjective norm explained intention to apply. With the combination of all three variables, only attitude towards applying did not play a significant role in the prediction of intention to apply, which is contrary to previous research. Practical/managerial implications: The findings highlight the role of salient control beliefs in the application process. Efforts by universities and organisations to affect intentions to apply may potentially benefit from focusing on support services that could enhance feelings of control and minimise perceived obstacles. Recruiters could focus on control to increase potential recruitment pools. Contribution/value-add: The study contributes to the recruitment literature in three ways. Firstly, TPB is shown to be a useful framework to explain graduate applicants’ intention to apply, as this theoretical model found empirical support. In doing so, the present study advances our understanding of how graduates’ intentions to apply are formed. Secondly, the results showed that applicants’ control and normative beliefs dominate when considering applying. Lastly, the study results open up interesting avenues for future research on applicant intentions.


Sign in / Sign up

Export Citation Format

Share Document