Learning pathways composed of core subjects with features of reducing cognitive load have better learning outcomes.

BACKGROUND: Changing the course duration or timing of subjects in learning pathways would influence medical students' learning outcomes. Curriculum designers need to consider the strategy of reducing cognitive load and evaluate it continuously. Our institution underwent gradual curricular changes characterized by reducing cognitive load since 2000. Therefore, we wanted to explore the impact of this strategy on our previous cohorts. METHODS: This cohort study explored learning pathways across academic years of more than a decade since 2000. Eight hundred eighty-two medical students between 2006 and 2012 were included eventually. Learning outcomes included an average and individual scores of subjects in different stages. Core subjects were identified as those where changes in duration or timing would influence learning outcomes and constitute different learning pathways. We examined whether the promising learning pathway defined as the pathway with the most features of reducing cognitive load has higher learning outcomes than other learning pathways in the exploring dataset. The relationship between features and learning outcomes was validated by learning pathways selected in the remaining dataset. RESULTS: We found nine core subjects, constituting four different learning pathways. Two features of extended course duration and increased proximity between core subjects of basic science and clinical medicine were identified in the promising learning pathway 2012, which also had the highest learning outcomes. Other pathways had some of the features, and pathway 2006 without such features had the lowest learning outcomes. The relationship between higher learning outcomes and cognitive load-reducing features was validated by comparing learning outcomes in two pathways with and without similar features of the promising learning pathway. CONCLUSION: An approach to finding a promising learning pathway facilitating students' learning outcomes was validated. Curricular designers may implement similar design to explore the promising learning pathway while considering potential confounding factors, including students, medical educators, and learning design of the course.

Using machine learning to identify key subject categories predicting the pre-clerkship and clerkship performance: 8-year cohort study.

BACKGROUND: Medical students need to build a solid foundation of knowledge to become physicians. Clerkship is often considered the first transition point, and clerkship performance is essential for their development. We hope to identify subjects that could predict the clerkship performance, thus helping medical students learn more efficiently to achieve high clerkship performance. METHODS: This cohort study collected background and academic data from medical students who graduated between 2011 and 2019. Prediction models were developed by machine learning techniques to identify the affecting features in predicting the pre-clerkship performance and clerkship performance. Following serial processes of data collection, data preprocessing before machine learning, and techniques and performance of machine learning, different machine learning models were trained and validated using the 10-fold cross-validation method. RESULTS: Thirteen subjects from the pre-med stage and 10 subjects from the basic medical science stage with an area under the ROC curve (AUC) >0.7 for either pre-clerkship performance or clerkship performance were found. In each subject category, medical humanities and sociology in social science, chemistry, and physician scientist-related training in basic science, and pharmacology, immunology-microbiology, and histology in basic medical science have predictive abilities for clerkship performance above the top tertile. Using a machine learning technique based on random forest, the prediction model predicted clerkship performance with 95% accuracy and 88% AUC. CONCLUSION: Clerkship performance was predicted by selected subjects or combination of different subject categories in the pre-med and basic medical science stages. The demonstrated predictive ability of subjects or categories in the medical program may facilitate students' understanding of how these subjects or categories of the medical program relate to their performance in the clerkship to enhance their preparedness for the clerkship.

Challenges and Future Directions of Big Data and Artificial Intelligence in Education.

We discuss the new challenges and directions facing the use of big data and artificial intelligence (AI) in education research, policy-making, and industry. In recent years, applications of big data and AI in education have made significant headways. This highlights a novel trend in leading-edge educational research. The convenience and embeddedness of data collection within educational technologies, paired with computational techniques have made the analyses of big data a reality. We are moving beyond proof-of-concept demonstrations and applications of techniques, and are beginning to see substantial adoption in many areas of education. The key research trends in the domains of big data and AI are associated with assessment, individualized learning, and precision education. Model-driven data analytics approaches will grow quickly to guide the development, interpretation, and validation of the algorithms. However, conclusions from educational analytics should, of course, be applied with caution. At the education policy level, the government should be devoted to supporting lifelong learning, offering teacher education programs, and protecting personal data. With regard to the education industry, reciprocal and mutually beneficial relationships should be developed in order to enhance academia-industry collaboration. Furthermore, it is important to make sure that technologies are guided by relevant theoretical frameworks and are empirically tested. Lastly, in this paper we advocate an in-depth dialog between supporters of "cold" technology and "warm" humanity so that it can lead to greater understanding among teachers and students about how technology, and specifically, the big data explosion and AI revolution can bring new opportunities (and challenges) that can be best leveraged for pedagogical practices and learning.

Applying DNA computation to intractable problems in social network analysis.

From ancient times to the present day, social networks have played an important role in the formation of various organizations for a range of social behaviors. As such, social networks inherently describe the complicated relationships between elements around the world. Based on mathematical graph theory, social network analysis (SNA) has been developed in and applied to various fields such as Web 2.0 for Web applications and product developments in industries, etc. However, some definitions of SNA, such as finding a clique, N-clique, N-clan, N-club and K-plex, are NP-complete problems, which are not easily solved via traditional computer architecture. These challenges have restricted the uses of SNA. This paper provides DNA-computing-based approaches with inherently high information density and massive parallelism. Using these approaches, we aim to solve the three primary problems of social networks: N-clique, N-clan, and N-club. Their accuracy and feasible time complexities discussed in the paper will demonstrate that DNA computing can be used to facilitate the development of SNA.

Developing a medical image content repository for e-learning.

The integration of medical informatics and e-learning systems could provide many advanced applications including training, knowledge management, telemedicine, etc. Currently, both the domains of e-learning and medical image have sophisticated specifications and standards. It is a great challenge to bring about integration. In this paper, we describe the development of a Web interface for searching and viewing medical images that are stored in standard medical image servers. With the creation of a Web solution, we have reduced the overheads of integration. We have packaged Digital Imaging and Communications in Medicine (DICOM) network services as a component that can be used via a Web server. The Web server constitutes a content repository for searching, editing, and storing Web-based medical image content. This is a simple method by which the use of Picture Archiving and Communication System (PACS) can be extended. We show that the content repository can easily interact and integrate with a learning system. With the integration, the user can easily generate and assign medical image content for e-learning. A Web solution might be the simplest way for system integration. The demonstration in this paper should be useful as a method of expanding the usage of medical information. The construction of a Web-based repository and integrated with a learning system may be also applicable to other domains.