Background: The collaborative clinical simulation (CCS) model is a structured method for the development and assessment of clinical competencies through small groups working collaboratively in simulated environments. From 2016 onward, the CCS model has been applied successfully among undergraduate and graduate medical students from the Universidad de Talca, Chile; the Universität de Barcelona, Spain; and the Universidad de Vic-Manresa, Spain. All the templates for building the clinical cases and the assessment instruments with CCS were printed on paper. Considering the large number of CCS sessions and the number of participating students that are required throughout the medical degree curriculum, it is impossible to keep an organized record when the instruments are printed on paper. Moreover, with the COVID-19 pandemic, web platforms have become important as safe training environments for students and medical faculties; this new educational environment should include the consolidation and adaptation of didactic sessions that create and use available virtual cases and use different web platforms. Objective: The goal of this study is to describe the design and development of a web platform that was created to strengthen the CCS model. Methods: The design of the web platform aimed to support each phase of the CCS by incorporating functional requirements (ie, features that the web platform will be able to perform) and nonfunctional requirements (ie, how the web platform should behave) that are needed to run collaborative sessions. The software was developed under the Model-View-Controller architecture to separate the views from the data model and the business logic. Results: MOSAICO is a web platform used to design, perform, and assess collaborative clinical scenarios for medical students. MOSAICO has four modules: educational design, students’ collaborative design, collaborative simulation, and collaborative debriefing. The web platform has three different user profiles: academic simulation unit, teacher, and student. These users interact under different roles in collaborative simulations. MOSAICO enables a collaborative environment, which is connected via the internet, to design clinical scenarios guided by the teacher and enables the use of all data generated to be discussed in the debriefing session with the teacher as a guide. The web platform is running at the Universidad de Talca in Chile and is supporting collaborative simulation activities via the internet for two medical courses: (1) Semiology for third-year students (70 students in total) and (2) Medical Genetics for fifth-year students (30 students in total). Conclusions: MOSAICO is applicable within the CCS model and is used frequently in different simulation sessions at the Universidad de Talca, where medical students can work collaboratively via the internet. MOSAICO simplifies the application and reuse of clinical simulation scenarios, allowing its use in multiple simulation centers. Moreover, its applications in different courses (ie, a large part of the medical curriculum) support the automatic tracking of simulation activities and their assessment.

Urease, a pivotal enzyme in nitrogen metabolism, plays a crucial role in various microorganisms, including the pathogenic Helicobacter pylori. Inhibiting urease activity offers a promising approach to combating infections and associated ailments, such as chronic kidney diseases and gastric cancer. However, identifying potent urease inhibitors remains challenging due to resistance issues that hinder traditional approaches. Recently, machine learning (ML)-based models have demonstrated the ability to predict the bioactivity of molecules rapidly and effectively. In this study, we present ML models designed to predict urease inhibitors by leveraging essential physicochemical properties. The methodological approach involved constructing a dataset of urease inhibitors through an extensive literature search. Subsequently, these inhibitors were characterized based on physicochemical properties calculations. An exploratory data analysis was then conducted to identify and analyze critical features. Ultimately, 252 classification models were trained, utilizing a combination of seven ML algorithms, three attribute selection methods, and six different strategies for categorizing inhibitory activity. The investigation unveiled discernible trends distinguishing urease inhibitors from non-inhibitors. This differentiation enabled the identification of essential features that are crucial for precise classification. Through a comprehensive comparison of ML algorithms, tree-based methods like random forest, decision tree, and XGBoost exhibited superior performance. Additionally, incorporating the “chemical family type” attribute significantly enhanced model accuracy. Strategies involving a gray-zone categorization demonstrated marked improvements in predictive precision. This research underscores the transformative potential of ML in predicting urease inhibitors. The meticulous methodology outlined herein offers actionable insights for developing robust predictive models within biochemical systems.

Background: The creation of computer-supported collaborative clinical cases is an area of educational research that has been widely studied. However, the reuse of cases and their sharing with other platforms is a problem, as it encapsulates knowledge in isolated platforms without interoperability. This paper proposed a workflow ecosystem for the collaborative design and distribution of clinical cases through web-based computing platforms that (1) allow medical students to create clinical cases collaboratively in a dedicated environment; (2) make it possible to export these clinical cases in terms of the Health Level 7 (HL7) Fast Healthcare Interoperability Resources (FHIR) interoperability standard; (3) provide support to transform imported cases into learning object repositories; and (4) use e-learning standards (eg, Instructional Management Systems Content Packaging [IMS-CP] or Sharable Content Object Reference Model [SCORM]) to incorporate this content into widely-used learning management systems (LMSs), letting medical students democratize a valuable knowledge that would otherwise be confined within proprietary platforms. Objective: This study aimed to demonstrate the feasibility of developing a workflow ecosystem based on IT platforms to enable the collaborative creation, export, and deployment of clinical cases. Methods: The ecosystem infrastructure for computer-supported collaborative design of standardized clinical cases consists of three platforms: (1) Mosaico, a platform used in the design of clinical cases; (2) Clavy, a tool for the flexible management of learning object repositories, which is used to orchestrate the transformation and processing of these clinical cases; and (3) Moodle, an LMS that is geared toward publishing the processed clinical cases and delivering their course deployment stages in IMS-CP or SCORM format. The generation of cases in Mosaico is exported in the HL7 FHIR interoperability standard to Clavy, which is then responsible for creating and deploying a learning object in Moodle. Results: The main result was an interoperable ecosystem that demonstrates the feasibility of automating the stages of collaborative clinical case creation, export through HL7 FHIR standards, and deployment in an LMS. This ecosystem enables the generation of IMS-CPs associated with the original Mosaico clinical cases that can be deployed in conventional third-party LMSs, thus allowing the democratization and sharing of clinical cases to different platforms in standard and interoperable formats. Conclusions: In this paper, we proposed, implemented, and demonstrated the feasibility of developing a standards-based workflow that interoperates multiple platforms with heterogeneous technologies to create, transform, and deploy clinical cases on the web. This achieves the objective of transforming the created cases into a platform for web-based deployment in an LMS.

The European–Latin American Consortium towards Eradication of Preventable Gallbladder Cancer, EULAT Eradicate GBC, is collecting high-quality data and samples in four Latin American countries with high gallbladder cancer incidence (Argentina, Bolivia, Chile, and Peru) to build a unique biorepository integrated into a tailored IT platform, to identify, validate, and functionally characterize new risk biomarkers, and to develop prediction models that integrate epidemiological and genetic–molecular risk factors. We decided to develop an application for electronic data collection to facilitate the retrieval of sociodemographic, clinical, lifestyle, dietary, and sample-related information from 15,000 Latin American study participants. The application EULAT eCollect will facilitate the work of study nurses, reduce time spent by participants, limit the use of paper and ink, minimize costs and errors associated with filling out written forms and subsequent digitisation, and support the monitoring of local recruitment rates and data quality. We describe in this article the design and implementation of the EULAT eCollect application, which started with the specification of functional and non-functional requirements, and ended with the implementation and validation of four separate application modules: Socio-Demographic Interview, Sample Information, Case Report Form, and Food-Frequency Questionnaire. We present both general and technical results, and our experience with the free and open-source software, Open Data Kit (ODK), which may be of interest for future related research projects, especially those on personalised cancer prevention carried out in low- and middle-income regions.

BACKGROUND Cardiac surgeries in Chile lack a national registry for systematic data collection and analysis, limiting insights into procedural outcomes and patient demographics. In response to this gap, we developed a web-based platform to support the documentation of high-complexity cardiac surgeries. OBJECTIVE Design, develop and implement a cardiac surgery data collection and analysis platform that conforms to international standards to support clinical decision-making and research initiatives. METHODS A web-based platform was developed using the Model-View-Controller (MVC) architecture, incorporating input from healthcare professionals and based on the fourth European Association for Cardio-Thoracic Surgery (EACTS) adult cardiac surgical database report. The platform captures over 160 clinical variables across 15 categories spanning pre-operative, intra-operative, and post-operative stages. RESULTS The most important result of this study is the creation of the first online platform for documenting cardiac surgeries in Chile. Since its implementation in 2014, the platform has documented over 4,800 cardiac surgeries, establishing it as the largest database for a single institution in Latin America. The platform offers real-time access to data, supports planning and resource allocation, and enables the systematic evaluation of clinical outcomes. Integrating the EURO SCORE II risk model facilitates a standardized mortality risk assessment. CONCLUSIONS The platform contributes to cardiac surgery data collection in Chile, enabling evidence-based clinical decision-making and public health planning. It has documented cardiac surgeries for 10 years and has become the official hospital registry tool. By 2025, its application will be extended to two more centers, with the expectation that it will soon become the national database of cardiac surgeries. Future developments should improve scalability, interoperability and data analysis to establish a national registry and further align Chilean cardiac surgery practices with international standards.