This work proposes an approach based on Large Language Models (LLMs) for creating digital collections from free-text medical reports. The approach uses instruct LLMs to extract relevant clinical terms from these reports, as well as to catalog them using the extracted terms. The cataloged reports are then integrated into a digital collection management platform, enabling further curation by clinical experts. To confirm the feasibility of the approach, we used various models associated with DeepSeek, as well as a coding model developed by Alibaba, and the experimental Clavy reconfigurable collection management platform to handle the resulting collections. The preliminary evaluation results demonstrate the feasibility of the approach, even without relying on external services that could compromise data privacy in real-world scenarios, or on particularly expensive dedicated hardware.

The information produced during clinical practice is of unquestionable value from a didactic point of view. Thus, there is a need for methods to generate educational content from this information in an agile, effective, and automatable way. This paper proposes a method that transforms clinical cases coded in the HL7 clinical interoperability standard FHIR into educational content compliant with the IMS CP standard. To demonstrate the feasibility of the method, we describe an implementation using the collaborative clinical case design platform Mosaico as the FHIR case provider and the Clavy digital collection management platform to transform these FHIR cases into IMS CP e-Learning content, ready to be deployed in a Learning Management System (LMS).

Human activity recognition has increasingly received attention in recent years to track regular activities of people. Existing activity recognition approaches considerably contributed to the analysis of human behavior. However, they still confront numerous issues related to the variability of activities performed by people within dynamic environments. Generally, this variability renders the used training or ontology models with predefined activities unsuitable. Therefore, creating an activity recognition approach that is able to leverage dynamically new and unknown activities at runtime becomes important. In this paper, we propose a novel knowledge-driven activity recognition framework using smartphone. This framework envisions taking a knowledge-driven approach to reinforce the recognition accuracy and people's quality of life in the context of dynamic environments at runtime. More specifically, we propose an ontology-based context evolution along with a dynamic decision-making, so that new and unknown performed activities can be accurately recognized. Furthermore, we use a public activity recognition dataset to demonstrate the effectiveness of the proposed framework and show its advantage over a data-driven baselines in terms of accuracy. Experimental results reveal that our framework not only reinforces the accuracy, but also enables an effective activity learning when facing unknown activities at runtime.

In this paper, we describe how to transform unstructured free-text clinical corpora, made from reports written in natural language and complementary assets (e.g., medical images, laboratory results, etc.), into collections of digital objects compatible with Clavy, a tool for managing reconfigurable digital collections. It will allow healthcare experts to subsequently reorganize the resulting collections to adapt them to their specific needs. The transformation will be achieved through the use of MetaMap, a robust tool for mapping clinical texts into the UMLS (Unified Medical Language System) thesaurus. Thus, by processing reports with MetaMap, we will be able to extract a significant set of corpus-specific UMLS terms, grouped according to relevant semantic types, which will be used to support a preliminary organization of the resources in the Clavy collection. We illustrate the viability of the approach with the generation of a reconfigurable Clavy collection from the Indiana Chest X-ray corpus of radiology reports and images. On the basis of this case study, we also discuss the strengths and weaknesses of the approach proposed.

We applied the How People Learn framework (HPLf) in two different higher education contexts. On one hand, a first-year core course on Computer Technology, taught at the Computer Engineering Degree Program at Universitat Politècnica de València, Spain. On the other hand, two Food Chemistry related courses, taught at Universidad de las Américas Puebla, Mexico, as part of food engineering undergraduate and food science graduate programs. The goal of these works was to redesign studied courses at both universities from a lecture-based format to a "challenge-based" format by using Tablet PCs and digital ink. In order to support the studied approach, different ink-enabled software tools were utilized. Class sessions were enhanced through the usage of Classroom Presenter, a pen-based interaction system that supports the sharing of digital ink on slides between instructors and students. InkSurvey also allowed teachers to pose questions, receive instantly digital ink responses, and provide real-time formative feedback. Some other tools such as PDF Annotator and Ardesia helped instructors to review coursework and assignments and provide formative feedback as well. We studied our approach over the two last academic years by observing classes at both universities, obtaining selected student achievement indicators and conducting surveys with students and instructors.

Nowadays, there are multiple examples of technologies which can drive major positive changes in classroom settings. In particular, the flexibility of Tablet PCs and digital ink has the potential to achieve a wide range of educational goals and promote a more dynamic classroom environment. However, as the possibilities of these educational technologies grow, it seems necessary to consider their role by conceptualizing the knowledge they provide. In this work we propose an approach based on the use of conceptual maps to generate instructor guidelines for designing Tablet PC-based courses. Our approach combines the instructional domain with the technological one in order to offer practical guidelines to design and develop both lecture materials and active learning tasks, providing a systematic and flexible way to organize the teaching process in Tablet PC-based courses. The approach has been implemented in a pilot section during a first year Computer Engineering course with successful results.

The era of communication technology has now a great impact in our daily lives. Learning approaches are now evolving from traditional slide-based lectures into much more dynamic ones, where technology plays a key role in order to improve the studentspsila academic performance and engagement. In this paper, we propose a novel approach to develop interactive classroom environments supported by mobile tablet PC technology, which integrates formative assessment into classroom practices and provides immediate feedback to students. We describe practical guidelines to design and develop both lecture materials and active learning exercises in the context of this next-generation technology.

Nowadays, many universities have adopted Virtual Learning Environments for delivering and distributing educational resources. In the context of Computer Science (CS) courses, the use of these environments addresses several issues ranging from the application of instructional strategies to the selection of the most adequate learning platform. In this work, we propose an instructional approach to drive CS courses through virtual learning environments. The concept of driving a CS course adds a pedagogical value to the classical approach delivering educational resources. This pedagogical value is supported by applying instructional methods based on pedagogical patterns to design specific components of CS courses. The use of these pedagogical patterns helps to guide the deployment of Virtual Learning Environments (VLE) in CS courses enabling a connection between the course requirements and the VLE features. We have evaluated the proposed approach using an example of VLE called Poliformat. The evaluation focuses on the platform role as the road to drive Operating System courses during the 2005-06, 2006-07 and 2007-08 academic years. The evaluation results have contributed to a better understanding of how virtual learning environments can be used in CS courses and they confirm the benefits of applying instructional based approaches.

The rapid development and the complexity of elearning-based experiences require the use of methods and tools to evaluate them. The current work presentsan evaluation method based on a “quality assurance” model in order to represent the several phases in the implementation of an e-learning experience as well as the quality criteria to be checked. Two evaluation cases are used to describe the method application in the context of higher education and some techniques and mechanisms to check these cases in e-learning settings are reported.

This paper describes a framework which is based on the use of standard specifications that allow instructors the elaboration of benchmarks to evaluate e-learning platforms. The proposed framework is also based on a learning platform evaluation model that assumes three main areas of functionality of any learning platform: content, interaction, and management. It has been applied to compare the functionalities of two widespread LMS platforms that support SCORM specifications. The paper includes some evaluation experiences using a benchmark prototype which is implemented by means of a SCORM 1.2 package. These experiences reveal the lack of integration of educational standard specifications into current e-learning platforms, mainly in the interaction and management functionality areas