Patricia Díaz

Background: Vitamin D deficiency is a significant risk factor for several chronic conditions. This study aims to predict vitamin D deficiency levels in a private database, collected from the southern part of Loja-Ecuador using a graphical web interface tool based on artificial intelligence algorithms. Methods: Two databases were processed using ML training models: SVM, Random Forest (RF), Linear Regression (LR). (i) Private data collection was undertaken on 465 patients from a local university, where vitamin D levels were measured through a blood sample collection to calculate the concentration of 25-hydroxy vitamin D in plasma and determine it by enzyme-linked immunosorbent assay, and (ii) public data collection was obtained from the FigShare database. Then, a survey was conducted from April 2022 to June 2023, identifying 157 variables, 18 of which were used for ML training models. Results: Vitamin D deficiency levels in private patients reached 18.10 ng/mL and 20.42 ng/mL in the public. The RF algorithm achieved (87.73%) accuracy, the SVM (80.0%), and LR (70.70%). RF was selected as the best performance model for web application design in binary levels classification: deficiency (Class 0) indicates vitamin D levels below 15 ng/mL, and sufficiency (Class 1) indicates vitamin D levels above 15 ng/mL. Conclusions: The “VITA-D” web application was used to monitor and predict vitamin D levels and deficiency factor risk based on clinical and sociodemographic data, providing an efficient and cost-effective alternative to traditional vitamin D testing methods.

Background: Hypovitaminosis D may be common in tropical countries and is linked to disorders of phospho-calcium metabolism, rickets, muscle pain, immune system deficiencies, and increased susceptibility to microbial infections.Objective: To assess the prevalence of hypovitaminosis D in apparently healthy university workers in Loja, Ecuador.Methods: A cross-sectional study was completed in a private Ecuadorian university from May 2023 to September 2023, involving 440 participants. Data were gathered using a structured questionnaire created to assess risk factors influencing vitamin D levels. Serum 25-hydroxyvitamin D (25-OH)D concentrations were measured utilizing immunoenzymatic methods. Altered states (insufficiency or deficiency) of vitamin D were defined with serum values p < 0.05. Where possible, odds ratios (OR) were calculated using logistic regression.Results: The sample consisted of 60.9% faculty members and 39.1% administrative staff; 42.7% were men and 57.3% were women, with an average age of 41.9 ± 7.6 years. Only 2.7% of participants were aged 60 years or older. The mean serum 25-(OH)D concentration was 19.5 ± 6.8 ng/mL. Altered 25-(OH)D levels were found in 93.4% of participants, with 94.0% showing decreased serum 25-(OH)D concentrations and 1.6% displaying deficiency states. Hypovitaminosis D was associated with sex (OR = 2.40; 95% CI: 1.3–5.57; p < 0.05) and sunscreen use (OR = 0.36; 95% IC: 0.13–0.99; p < 0.05).Conclusion: Hypovitaminosis D was almost universal among the apparently healthy university workers studied. The findings suggest that both sex and sunscreen use may independently or jointly contribute to hypovitaminosis D in these individuals. Further studies will be required to clarify this interplay.

Algunos trabajadores mantienen estilos de vida no saludables que los hace propensos a tener un alto riesgo de diabetes tipo 2 (DT2). El presente estudio tuvo como objetivo evaluar el riesgo de DT2 (RDT2) en personal administrativo y docente de una universidad ecuatoriana y factores asociados. Estudio de corte transversal que evaluó el RDT2 según FINDRISC. Se consideró RDT2 alto si la puntuación ≥12 puntos. Se analizaron aspectos sociodemográficos, hábitos nocivos y saludables; se midieron el índice de masa corporal (IMC), el perímetro abdominal (PA) y la tensión arterial (TA). Se evaluaron las razones de prevalencia bruta (RPB) y ajustada (RPA) para identificar factores asociados con RDT2. De 311 participantes, edad media de 41,02 años (DE 10,1), 58,2% mujeres y 41,8% hombres. La prevalencia de RDT2 elevada fue mayor en mujeres respecto a varones (38,1% frente a 32,3%) y aumentó en mayores de 40 años [RPA 1.55 (1.11-2.15)], personas casadas [RPA 1.49 (1.07-2.05)], aquellos con actividad física moderada o menor [RPA 1.55 (1.11-2.15)], y en aquellos con PA elevado [RPA 2,41 (1,33 - 4,36)]. La edad, la baja actividad física y el PA, fueron factores asociados con una mayor prevalencia de RDT2. Se deben promover estilos de vida saludables, para incrementar la actividad física y disminuir el PA en trabajadores, para reducir el riesgo de DT2. Palabras claves: Diabetes Mellitus tipo 2, Estilos de Vida, Factores de Riesgo, Salud Laboral