Search

Machine Learning (ML) has extended its use in several domains to support complex analyses of data. The medical field, in which significant quantities of data are continuously generated, is one of the domains that can benefit from the application of ML pipelines to solve specific problems such as diagnosis, classification, disease detection, segmentation, assessment of organ functions, etc. However, while health professionals are experts in their domain, they can lack programming and theoretical skills regarding ML applications. Therefore, it is necessary to train health professionals in using these paradigms to get the most out of the application of ML algorithms to their data. In this work, we present a platform to assist non-expert users in defining ML pipelines in the health domain. The system’s design focuses on providing an educational experience to understand how ML algorithms work and how to interpret their outcomes and on fostering a flexible architecture to allow the evolution of the available components, algorithms, and heuristics.

This special issue features four invited papers from the 2023 edition of the MSc. and PhD. thesis contests, organized by CLEI, the Latin American Center for Computing Studies. CLEI's mission includes promoting the scientific growth of all computing fields across Latin America. To recognize these advancements and foster the region's graduate programs, CLEI has been hosting the Latin American Master Thesis Contest (CLTM) annually since 1993 and the Doctoral Thesis Contest (CLTD) since 2016. Both contests are held in conjunction with the Latin American Computing Conference (CLEI conference). The 2023 conference took place in La Paz, Bolivia, and received numerous high-quality submissions for both the MSc. and PhD. contests. Post-conference, the authors of the best works were invited to submit original, unpublished papers to the CLEIej journal. These submissions went through another evaluation round, adhering to the journal's standard review process.

Test-driven development (TDD) is an agile practice of writing test code before production code, following three stages: red, green, and refactor. In the red stage, the test code is written; in the green stage, the minimum code necessary to make the test pass is implemented, and in the refactor stage, improvements are made to the code. This practice is widespread across the industry, and various studies have been conducted to understand its benefits and impacts on the software development process. Despite its popularity, TDD studies often focus on the technical aspects of the practice, such as the external/internal quality of the code, productivity, test smells, and code comprehension, rather than the context in which it is practiced. In this paper, we present a systematic literature review using Scopus, Web of Science, and Google Scholar that focuses on the TDD practice and the influences that lead to the introduction of test smells/anti-patterns in the test code. The findings suggest that organizational structure influences the testing strategy. Additionally, there is a tendency to use test smells and TDD anti-patterns interchangeably, and test smells negatively impact code comprehension. Furthermore, TDD styles and the relationship between TDD practice and the generation of test smells are frequently overlooked in the literature.

Machine Learning allows facing complex tasks related to data analysis with big datasets. This Artificial Intelligence branch allows not technical contexts to get benefits related to data processing and analysis. In particular, in medicine, medical professionals are increasingly interested in Machine Learning to identify patterns in clinical cases and make predictions regarding health issues. However, many do not have the necessary programming or technological skills to perform these tasks. Many different tools focus on developing Machine Learning pipelines, from libraries for developers and data scientists to visual tools for experts or platforms to learn. However, we have identified some requirements in the medical context that raise the need to create a customized platform adapted to end-user found in this context. This work describes the design process and the first version of KoopaML, an ML platform to bridge the data science gaps of physicians while automatizing Machine Learning pipelines. The platform is focused on enhanced interactivity to improve the engagement of physicians while still providing all the benefits derived from the introduction of Machine Learning pipelines in medical departments, as well as integrated ongoing training during the use of the tool’s features.

Science, Technology, Engineering, and Mathematics (STEM) degrees represent a future employment scenario with low unemployment rates due to the high demand for qualified personnel. However, the STEM sector also represents an educational field marked by horizontal segregation and the gender gap. Different factors play a role in deciding which higher education studies to pursue. From a theoretical and empirical approach, this study aims to identify which factors are associated with the gender gap in the STEM higher education sector. Furthermore, as a research question, it is proposed: are the factors identified at a theoretical and empirical level associated with the gender gap in the STEM higher education sector the same? The empirically validated questionnaire “Questionnaire with university students on STEM studies in Higher Education” (QSTEMHE) was applied to the student community of public and private universities in Spain in 2021, using simple random probability sampling to answer the research question and objective. A final sample of 2101 participants of different genders belonging to different branches of knowledge was obtained. The data analysis was carried out using qualitative methodology and the phenomenological method, following different stages. Firstly, a theoretical conceptual map of the main factors identified in the literature and their authors was composed. Secondly, an empirical conceptual map has been designed with the factors identified in the narratives of the study participants. Finally, these maps were complemented with a SWOT analysis based on the participants' discourses. As a result, it has been observed that there are extrinsic and intrinsic factors and that social constructs and gender stereotypes strongly influence the perception of men, women, and professions and the masculinisation and feminisation of these. Outreach interventions should be proposed from the institutional educational spheres to alleviate existing biases about studies and professions.

The development of science, technology, engineering, and mathematics (STEM) requires more qualified professionals in these fields. However, gender segregation in higher education in this sector is creating a gender gap that means that for some disciplines female representation does not even reach 30% of the total. In order to propose measures to address the phenomenon, it is necessary to understand the possible causes of this issue.A systematic literature review and mapping were carried out for the study, following the PRISMA guidelines and flowchart. The research questions to be answered were (RQ1) What studies exist on the gender gap in relation to the choice of higher education in the STEM field; and (RQ2) How do gender roles and stereotypes influence decision-making related to higher education? The review of peer-reviewed scientific articles, conferences texts, books and book chapters on the European education area was applied. A total of 4571 initial results were obtained and, after the process marked by the PRISMA flowchart, the final results were reduced to 26. The results revealed that gender stereotypes are strong drivers of the gender gap in general, and the Leaky Pipeline and Stereotype Threat in particular. To narrow the gender gap, it is necessary to focus on influences from the family, the educational environment, and the peer group, as well as from the culture itself. Positive self-concept, self-efficacy, self-confidence, and self-perception need to be fostered, so that the individual chooses their studies according to their goals.

The use of advanced algorithms and models such as Machine Learning, Deep Learning and other related approaches of Artificial Intelligence have grown in their use given their benefits in different contexts. One of these contexts is the medical domain, as these algorithms can support disease detection, image segmentation and other multiple tasks. However, it is necessary to organize and arrange the different data resources involved in these scenarios and tackle the heterogeneity of data sources. This work presents the CARTIER-IA platform: a platform for the management of medical data and imaging. The goal of this project focuses on providing a friendly and usable interface to organize structured data, to visualize and edit medical images, and to apply Artificial Intelligence algorithms on the stored resources. One of the challenges of the platform design is to ease these complex tasks in a way that non-AI-specialized users could benefit from the application of AI algorithms without further training. Two use cases of AI application within the platform are provided, as well as a heuristic evaluation to assess the usability of the first version of CARTIER-IA.

Open Education (OE) opens up learning opportunities to, potentially, every person in the world. Additionally, it allows teachers, researchers, and practitioners to find, share, reuse, and improve existing resources under a dependable legal framework. Aiming to spread and foster the introduction of open policies in Higher Education (HE) institutions, the gamified interactive learning experience Catch the Open! was developed. Catch the Open! targets HE educators who wish to learn, or who wish to deepen their existing knowledge, about OE and Open Educational Practices (OEP). Within the gamified learning experience, the user becomes an educator, Alex, the game character, who receives a task from the Rector: to investigate how to best include OE and OEP in teaching and learning practice within the institution. Alex proceeds to explore and gather information in a web-based 2D virtual HE institution where students, colleagues, and guest researchers will help her to develop a comprehensive understanding of OE and the practical application of OEP. The educational content within Catch the Open! is underpinned by an OE competences framework for HE educators, developed in a previous phase of the Erasmus+ OpenGame project. In this paper, the design process to link pedagogical and technological approaches, which results in the Catch the Open! gamified web-based interactive application, is presented as well as the application itself. Moreover, two phases of piloting with 153 HE educators from six different HE institutions are presented. The obtained findings showed that the gamified environment helped in learning about OE. On the other hand, learners also suggested several improvement aspects of the gamified environment, such as the length of finishing a learning mission while playing.

United Nations Sustainable Development Goal 4 (SDG 4) focuses on education and seeks to promote inclusive, equitable, and quality education, providing opportunities for all. In this context, it seeks to promote intersectionality (gender and ethnicity) as a fundamental factor in education, and in science, technology, engineering, and mathematics (STEM) careers in particular. Similarly, it aims to support programs that include the gender gap in their studies to mitigate the lack of Indigenous women and/or students from native peoples in STEM careers. The objective of this work was to carry out a categorization of programs aimed at Indigenous students in their processes of access, retention, and follow-up in STEM careers, with the purpose of making visible the variety of approaches and programs that have been created in different regions of the world. A systematic review was conducted to analyze the programs, and the classical content analysis method of scientific production was employed. The main results of the analysis are classified into three main categories: the characteristics of the studies, the programs, and their results. In relation to the study's contribution, the aim is to generate knowledge and understanding of the programs identified to promote the inclusion of this underrepresented population in STEM education.

Although STEAM (science, technology, engineering, art, and math) and student-centered instruction are growing rapidly in popularity, their reach is not adequately distributed across diversity groups (including individuals of different genders, economic backgrounds, immigrant backgrounds, abilities, and races, among other characteristics). The CreaSTEAM project intends to address diversity gaps by developing STEAM-Labs, student-centered spaces that combine components of fab labs, media labs, and user labs to specifically target diversity gaps. This paper carried out an informal PRISMA systematic review of a collection of 124 worldwide STEAM diversity initiatives to gather data on existing best practices that will be used in the STEAM-Labs. The review studied the geographic distributions, organizational structures, founding years, and activity offerings of the initiatives, along with the dataset’s overall STEAM content area prevalence and diversity target area prevalence. STEM was the most common approach, and gender was the most common diversity target area. Since 2010 initiative creation has increased, with most growth in gender-focused initiatives.

Knowledge management is one of the key priorities of many organizations. They face different challenges in the implementation of knowledge management processes, including the transformation of tacit knowledge—experience, skills, insights, intuition, judgment and know-how—into explicit knowledge. Furthermore, the increasing number of information sources and services in some domains, such as healthcare, increase the amount of information available. Therefore, there is a need to transform that information in knowledge. In this context, learning ecosystems emerge as solutions to support knowledge management in a different context. On the other hand, the dashboards enable the generation of knowledge through the exploitation of the data provided from different sources. The model-driven development of these solutions is possible through two meta-models developed in previous works. Even though those meta-models solve several problems, the learning ecosystem meta-model has a lack of decision-making support. In this context, this work provides two main contributions to face this issue. First, the definition of a holistic meta-model to support decision-making processes in ecosystems focused on knowledge management, also called learning ecosystems. The second contribution of this work is an instantiation of the presented holistic meta-model in the healthcare domain.

There are different methods and techniques to carry out systematic reviews in order to address a set of research questions or getting the state of the art of a particular topic, but there is no a method to carry out a systematic analysis of research projects not only based on scientific publications. The main challenge is the difference between research projects and scientific literature. Research projects are a collection of information in different formats and available in different places. Even projects from the same funding call follow a different structure in most of the cases, despite there were some requirements that they should meet at the end of the funding period. Furthermore, the sources in which the scientific literature is available provide metadata and powerful search tools, meanwhile most of the research projects are not stored in public and accessible databases, or the databases usually do not provide enough information and tools to conduct a systematic search. For this reason, this work provides the guidelines to support systematics reviews of research projects following the method called Systematic Research Projects Review (SRPR). This methodology is based on the Kitchenham’s adaptation of the systematic literature review.

Business interactions are rarely taken into account in the early stages of development of software ecosystems in the health sector, which causes these kinds of solutions to stay as conceptual proposals or be rapidly discontinued after deployment. In the present paper, we describe our approach towards the exploitation of a technological ecosystem focused on learning and knowledge management processes to develop and enhance the caregiving competences of formal and informal caregivers, both at home and in care environments. The definition of the business process has been done using the Business Process Model and Notation (BPMN) standard, which allows to further include the business model in the definition of the data taxonomy.

Informal caregivers play an important role in healthcare systems in many countries. They have a high impact on reducing care costs related to dependent persons because their support prevents institutionalization. A technological ecosystem has been defined to support informal caregivers using psychoeducation techniques. This ecosystem should include a dashboard to support decision-making processes related to the wellbeing of patients and caregivers. A dashboard meta-model was used to obtain a concrete model for the presented context. This meta-model allows defining dashboards adapted to the users’ needs and specific data domains.