Background/Objectives: In low-resource settings, diagnostic delays and limited specialist access worsen health inequalities, making hypertensive disorders of pregnancy (HDPs) defined by new-onset blood pressure ≥ 140/90 mmHg after 20 weeks of gestation, with or without proteinuria, a major cause of maternal morbidity and mortality. This study evaluated the diagnostic effectiveness of a rural-applicable clinical model for detecting HDPs in a real-world population from Hospital General San Felipe (Tegucigalpa, Honduras). Methods: A cross-sectional diagnostic accuracy study was conducted on 147 consecutive pregnant women in February 2025. Clinical documentation from the initial appointment defined HDP. We modeled HDP risk using penalized logistic regression and common factors such maternal age, gestational age, blood pressure, BMI, primary symptoms, semi-quantitative proteinuria, and medical history. Median imputation was utilized for missing numbers and stratified five-fold cross-validation assessed performance. We assessed AUROC, AUPRC, Brier score, calibration, and operational utility at a data-driven threshold. Results: Of patients, 27.9% (41/147) had HDP. The model had an AUROC of 0.614, AUPRC of 0.461 (cross-validation averages), and Brier score of 0.253. The threshold with the highest F1-score (0.474) had a sensitivity of 0.561, specificity of 0.679, positive predictive value of 0.404, and negative predictive value of 0.800. HDP had higher meaning systolic/diastolic/mean arterial pressure (130.7/82.9/98.9 vs. 120.5/76.1/90.9 mmHg) and ordinal proteinuria (0.59 vs. 0.36 units). Conclusions: The model had moderate but clinically meaningful discriminative performance using low-cost, commonly obtained variables, excellent calibration, and a good negative predictive value for first exclusion. These findings suggest modification of predictors, a larger sample size, and clinical usefulness assessment using decision curves and process outcomes, including quick referral and prophylaxis. This approach aligns with contemporary developments in the 2023–2025 European Society of Cardiology (ESC) and 2024 American Heart Association (AHA) guidelines, which emphasize earlier identification and risk-stratified management of hypertensive disorders during pregnancy as a cornerstone of women’s cardiovascular health.

This study evaluates, from a cost and entrepreneurial opportunity perspective, the viability of maintaining a university cluster composed of ten HP ProDesk 600 G1 nodes (40 cores, 60 GB RAM) versus contracting equivalent capacity on Amazon EC2 (C6i.2xlarge instances). A detailed total cost of ownership (TCO) model was developed, incorporating capital investment, maintenance, electricity (USD 0.22/kWh), internet connectivity (200 Mbps), and cloud tariffs under both On-Demand and three-year Savings Plan modalities. At 30% utilization, the local cluster achieves a unit cost of USD 0.025/core-hour, while EC2 ranges from USD 0.048 to 0.105/core-hour. Sensitivity curves indicate that the cloud only becomes cost-effective when utilization exceeds 65% or electricity surpasses USD 0.45/kWh. The analysis further explores implications for deep-tech startups, university spin-offs, and incubator programs: while the cloud provides elasticity and access to advanced hardware, it may erode early-stage margins. The study proposes a reproducible decision-making framework tailored to emerging innovation ecosystems in Latin America, highlighting the strategic value of hybrid infrastructures for balancing cost, flexibility, and regional value retention.

Background and Aims: Sarcopenia, a progressive loss of skeletal muscle mass and function, poses a growing public health challenge in low and middle‐income settings. We aimed to quantify its prevalence and identify sex‐specific risk factors among older adults attending a public outpatient clinic in Tegucigalpa, Honduras. Methods: In a hospital‐based, age‐stratified random sample, we enrolled 100 participants (73 women and 27 men; mean age = 69.7 ± 6.9 years) during July 2024. Possible sarcopenia and frailty were assessed using SARC‐F and FRAIL questionnaires, respectively. Body mass index was calculated under standardized conditions and mean arterial pressure (MAP) was derived from blood pressure measurements. Normality of continuous variables was evaluated with the Shapiro–Wilk test. Between‐sex differences were analyzed using Welch's t ‐test for continuous variables and χ ² test for categorical variables ( α = 0.05). Pearson's correlation was employed to assess associations between SARC‐F scores and clinical variables. Results: Possible sarcopenia (SARC‑F ≥ 4) was present in 48% of participants (95% CI = 38–58), while 40% met criteria for frailty. Women showed a significantly higher mean BMI than men (28.0 ± 5.7 kg m ⁻² vs. 24.9 ± 4.5 kg m ⁻² ; t = 2.8, p = 0.007) yet a comparable MAP (102 ± 13 mmHg vs. 99 ± 13 mmHg; p = 0.33). Frailty prevalence remained higher in women across all age strata (42.5% vs. 37.0%), although the sex difference was not statistically significant ( χ ² = 0.2, p = 0.9). SARC‑F scores correlated modestly with MAP ( r = 0.3, p = 0.003) but not with age ( r = 0.1, p = 0.3) or BMI ( r = 0.1, p = 0.4). Conclusions: Nearly half of older adults were at risk of sarcopenia and two‐fifths were frail, with women more affected. Elevated blood pressure was linked to functional decline.

Background/Objectives: Frailty is common in Latin America and the Caribbean, yet validated, low-cost screening tools based only on routine clinical data remain limited. We developed benchmarked interpretable machine learning models for frailty screening in older adults and assessed the added value of SARC-F beyond basic hemodynamic and anthropometric measures. Methods: In this cross-sectional pilot diagnostic modeling study, 100 older adults (mean age 69.8 ± 6.8 years; 73% women) from a tertiary care center were classified with the FRAIL scale. The primary endpoint was frail versus non-frail. Three logistic regression models were evaluated using stratified 5-fold cross-validation: Model A (age, sex, BMI, nutritional status, systolic and diastolic blood pressure), Model B (mean arterial pressure and pulse pressure), and Model C (Model A plus SARC-F). Decision tree and random forest were secondary comparators. Results: SARC-F was the only variable significantly associated with frailty category (p < 0.001). Models A and B showed near-chance discrimination (both AUC = 0.546), whereas Model C achieved an AUC of 0.921 (95% CI: 0.864–0.966), sensitivity of 0.812, specificity of 0.846, and F1-score of 0.821. SARC-F alone yielded an AUC of 0.942. In Model C, SARC-F was the dominant predictor (standardized OR 12.52, 95% CI: 8.90–23.91). Conclusions: Routine hemodynamic and anthropometric variables alone were inadequate for frailty discrimination. SARC-F captured most of the discriminative signal, supporting its use for frailty screening in resource-limited geriatric settings. Although the logistic regression pipeline was transparent and computationally inexpensive, external prospective validation is required.