Conference Agenda

Language enables the transmission of information, ideas, and emotions; however, significant communication barriers persist for the deaf community in many everyday contexts. This paper presents a real-time software system for the translation of Honduran Sign Language (LESHO) based on computer vision and machine learning techniques. The proposed system relies on structured spatial representations extracted from anatomical landmarks of the hands and contextual body cues, rather than raw image data, enabling efficient and robust gesture recognition under real-time constraints. Gesture acquisition, feature extraction, and classification are integrated within a modular architecture implemented in Python using OpenCV, MediaPipe, and Scikit-learn. The system supports fixed-length landmark vectors for static gestures and temporal landmark sequences for dynamic gestures. Experimental evaluation on a multi-class dataset demonstrates high recognition accuracy and interactive response times on consumer-grade hardware. Overall, the results validate the effectiveness of landmark-based modeling for sign language recognition and highlight the system’s scalability for expanding vocabulary coverage and supporting inclusive communication in both face-to-face and technology-mediated environments.

Upper limb amputation has a major impact on quality of life; however, the cost of traditional prostheses is often beyond the reach of users in developing economies. Though 3D printing has enhanced accessibility, the commonly used material, PLA, is prone to degradation and also generates heat within the socket. This paper describes a single-subject case study concerning the development of a low-cost, thermally optimized transradial prosthesis made from Nylon PA12. The device was designed using a User-Centered Design approach and customized through 3D scanning and validated via Finite Element Analysis (FEA). Most importantly, material properties used in the simulation were not generic but experimentally characterized according to ASTM D638, ASTM D790, and ISO 868 standards. The simulation gave an FOS value greater than 3.0 for the critical load of 300 N. Additionally, flammability testing (ISO 11925-2) and thermographic analysis proved that the Nylon PA12 socket can be considered as safe self-extinguishing thermal insulation. Functional field tests indicated that the participant was able to manipulate industrial tools with a weight of up to 5 kg successfully. These preliminary findings indicate that experimentally characterized Nylon PA12 can be considered as an alternative material for affordable rehabilitation concerning mechanical durability and thermal comfort in low-resource settings.

The loss of an upper limb during childhood affects not only mobility but also the functional, social, and emotional development of children. In Honduras, the scarcity of growth-adjustable pediatric prostheses creates economic and healthcare challenges due to the need for frequent replacements as children grow. This project aimed to design a preliminary prototype of a transradial myoelectric prosthesis adjustable to pediatric growth, capable of interpreting EMG signals to operate a basic grasping mechanism. The methodology included three phases: study, development, and validation. Morphological analyses and the ELECTRE method defined technical specifications, while Human-Based Design supported decision validation through surveys with users and experts. The prototype was manufactured using 3D printing and incorporated an EMG-based activation algorithm. Preliminary validation tests with three subjects using 3D-printed residual limbs demonstrated accurate myoelectric response and effective adaptability of the modular adjustment system. These results indicate that, with further refinement and clinical validation, the device could provide an accessible solution for children with transradial amputation.

Data traceability in the health sector is fundamental to improving the quality and continuity of healthcare. The purpose of this review is to examine the progress of applications and methods applied to improve data traceability in this sector, recognising progress, challenges and possibilities for improvement. Methods: A study of 105 original articles from databases such as PubMed and Scopus was carried out, adding manual searches up to October 2025, of which 84 investigations met the inclusion requirements. The most analysed techniques included the application of blockchain, interoperability based on HL7 FHIR standards and embedded mobile solutions. Results: The incorporation of emerging technologies has shown evidence of increasing accuracy and access to patient information, decreasing administrative errors and facilitating clinical decision-making. However, challenges such as security, resistance to change and lack of universal standards persist. Conclusions: Effective implementation of applications and methodologies for data traceability in the healthcare sector depends on a collaborative approach between developers, healthcare providers and regulatory bodies. This will enable greater interoperability, optimisation of resources and confidence in the systems, benefiting both patients and professionals.

The use of clinical artificial intelligence (AI) models in healthcare systems has prompted concerns about algorithmic fairness, especially for marginalized populations who have been underrepresented in medical data. Simulated data reflecting rural Honduran demographics and illness incidence patterns is used to examine demographic and distributional biases in clinical prediction models. Gradient boosting (XGBoost) and neural network classifiers (Multilayer Perceptron with 3 hidden layers) were trained for cardiovascular risk prediction using synthetic clinical datasets generated by Monte Carlo simulation. Fairness metrics including equalized odds difference, demographic parity ratio, and calibration error assessed model performance discrepancies across protected factors like geographic location, socioeconomic status, and indigenous heritage. Sample reweighting, adversarial debiasing, and decision threshold optimization were evaluated. Baseline models showed significant performance differences, measuring AUROC differences of up to 0.089 between urban and remote rural populations (p < 0.001) and equalized odds differences reaching 0.15 across socioeconomic groupings. Adversarial debiasing reduced equalized odds differences by 62.4% while maintaining clinically acceptable discrimination (AUROC = 0.823) after mitigation. Sample reweighting increased demographic parity by 41.3% without degrading predictive performance. These findings demonstrate that clinical AI models developed without explicit fairness constraints can exacerbate existing healthcare disparities, and that simulation-based auditing frameworks combined with bias mitigation techniques can substantially enhance algorithmic equity while maintaining predictive utility. The findings recommend required algorithmic auditing measures before deployment in resource-limited healthcare settings.

Purpose: This systematic review of the literature aims to comprehensively analyze available studies on viral diseases, taking into account aspects related to prevention and transmission mechanisms, and providing relevant contributions to their mitigation. The following research questions were posed: 1) What are the main epidemiological manifestations in humans because of MPOX? 2) What risk factors and transmission mechanisms drive the spread of MPOX in vulnerable populations? 3) What prevention strategies have proven effective in controlling MPOX globally? Methods: The selection of articles followed the guidelines established by the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) method and took into account highly relevant databases such as Scopus, ScienceDirect, and Web of Science. Subsequently, exclusion and inclusion criteria were applied to 58 scientific articles, all published in English and classified as journal articles. Results: The results revealed a high concentration of publications in recent years, with 2024 standing out as the year with the highest number of studies, at 48.28%. The papers were published mainly in the United States (27.59%), Spain (12.07%) and China (12.07%). In terms of methodological approaches, 74.14% of the studies adopted a quantitative approach, followed by a qualitative approach (18.97%) and a mixed approach (6.90%). Conclusion: there has been a remarkable increase in scientific production on monkeypox, which highlights the importance of addressing this issue in future research, reinforcing prevention strategies, strengthening international cooperation and improving health systems to address future outbreaks of the disease.