Conference Agenda

The digitalization of Electronic Health Records (EHRs) in healthcare facilities with intermittent connectivity remains a technical and operational challenge. This study presents the design, implementation, and validation of an offline-first EHR architecture intended for resource-limited environments. The system was developed as a lightweight web application operating on a local server, enabling clinical data registration, storage, and management without permanent Internet connectivity, and incorporating deferred synchronization mechanisms compatible with HL7/FHIR-based structures.

The evaluation was conducted on a functional prototype through data integrity, security, access control, synchronization, and performance testing under load conditions, complemented by a Technology Acceptance Model (TAM)-based survey applied to 15 medical specialists.

Results demonstrated consistent data storage without record duplication, resistance to SQL injection attempts through parameterized queries, automatic synchronization without data loss under intermittent connectivity, and stable response times after the mass registration of 1,000 patients. Individual record synchronization averaged 5 ms, while batch updates of 1,050 records required 91 s. User acceptance results showed mean scores above 4.0/5 across most items, particularly regarding suitability for low-connectivity settings (M=4.67) and complementary implementation potential (M=4.73).

The findings indicate that the proposed architecture is technically feasible and operationally suitable for small and medium-sized healthcare facilities, providing a functional alternative for environments with connectivity and infrastructure constraints.

Childhood immunization is a cost-effective public health intervention to reduce morbidity and mortality in children under five years of age; however, in low- and middle-income countries there are coverage gaps that limit their impact. In Honduras, these gaps are challenging, so analytical approaches are needed to detect populations at risk of incomplete schemes. The study sought to identify the determinants of not fully vaccinated in children aged 12 to 23 months, develop predictive classification models and explain the contribution of each variable with SHAP values. The ENDESA/MICS 2019 was analyzed, including 1,711 children aged 12–23 months. The outcome was defined as not fully vaccinated, without BCG, three doses of Polio, three doses of Pentavalent and one of MMR. Logistic regression, decision trees, Random Forest and Gradient Boosting models were trained and compared, evaluating performance with AUC-ROC and Brier Score, and interpretability was examined with SHAP. The prevalence of non-vaccination was 19.3%. The best performance was Gradient Boosting (AUC-ROC = 0.694; Brier Score = 0.138). According to SHAP, the main determinants were the age of the child (|SHAP| = 0.41), possession of vaccination card (|SHAP| = 0.31) and maternal education (|SHAP| = 0.10). The department of Gracias a Dios had the highest prevalence of non-vaccination (51.8%). The findings indicate that machine learning with SHAP allows for the precise identification and prioritization of factors associated with incomplete vaccination schedules in Honduran children aged 12 to 23 months

Small devices have become important objects for monitoring health, giving new opportunities to measure pressure without touching. This paper looks at new studies about the accuracy and how well small devices work for viewing blood pressure in larger people. The way to search for words like "small devices" and "older people", using Scopus as a primary basis. The findings show that although small devices have promising practicality and ease, there are still problems with calibration accuracy and validation standards in elderly groups. This study indicates the need to join forces between engineers, doctors and healthcare leaders to ensure the safe and effective use of these portable technologies and the care of the elderly.

Diabetic retinopathy (DR) is one of the leading causes of vision loss worldwide, especially in regions with limited access to ophthalmological services. The aim of this study was to develop and evaluate a low-cost portable retinograph assisted by Deep Learning for early detection and severity classification of DR. The system integrates a portable device based on indirect ophthalmoscopy, 3D printing, and smartphone image acquisition, together with convolutional neural networks (CNNs) for automated analysis. A combined dataset from the Messidor, APTOS, and EyePACS databases, comprising approximately 49,430 retinal images, was used for training and validation. Image preprocessing, class balancing, and transfer learning techniques were applied using MobileNetV2 and DenseNet121 architectures, evaluated in binary and multiclass classification tasks. The results demonstrated that the prototype captured fundus images with sufficient quality for clinical visualization. In conclusion, the proposed system represents a feasible and accessible solution for DR screening in telemedicine and resource-limited settings.

Musculoskeletal disorders (MSDs) are one of the main work-related illnesses in the construction sector, where ergonomics is a challenge due to the handling of heavy loads, awkward postures, and repetitive movements. Regulating these risk factors is difficult, requiring improvements in assessment and control processes. The objective of this review is to determine how the assessment of ergonomic risk factors helps reduce the incidence of MSDs in this sector. The studies reviewed show that observational methodologies such as REBA are the most widely used in combination with other methods. Likewise, repetitive movements were the most common factor found in this review. This identification allows for the development of preventive and corrective measures, focusing on the implementation of improvements in the work environment, especially in buildings. Therefore, systematic ergonomic risk assessments are key tools in occupational health management, contributing to mitigating the incidence of MSDs in construction workers.

The main objective of this work was to develop a first-approximate method for determining the ideal amount of dry ice required to preserve biological samples below -5 °C during gamma irradiation processes in a self-shielded irradiator, ensuring their frozen state. To this end, four experiments were conducted in which the mass and spatial distribution of dry ice within a sample holder used in an irradiator were varied, and the temperature at the center of the holder was measured and recorded for approximately 30 hours. From this, the time during which the temperature remained below -5 °C was determined, and a linear model was constructed using least squares to relate mass to thermal preservation time. Furthermore, it was determined that mass and its distribution are crucial factors for improving thermal control in gamma irradiators.