Jamhuriya University of Science and Technology

This study investigates the determinants of trade openness in Somalia by examining how the agricultural sector and key macroeconomic factors-including foreign direct investment (FDI), exchange rates, and trade integration-jointly influence trade performance. Drawing on classical and modern trade theories, such as comparative advantage, export performance, and endogenous growth, the study employs annual data spanning 1990-2020 and applies an Autoregressive Distributed Lag (ARDL) model with an Error Correction Mechanism (ECM) to capture both short- and long-run dynamics. The stationarity of the series is assessed using the Augmented Dickey-Fuller (ADF), Phillips-Perron (PP), and KPSS tests. The long-run results indicate that agricultural exports significantly enhance trade openness, highlighting the central role of the agricultural sector in promoting Somalia's integration into international markets. In contrast, FDI inflows exhibit a negative long-term effect, suggesting that investments are often directed to non-trade-oriented sectors, limiting their contribution to trade performance. Short-run dynamics reveal that export growth and exchange-rate stability are crucial for trade performance, whereas exchange-rate volatility can impede trade flows. Comprehensive diagnostic tests confirm the model's robustness and stability. These findings underscore the importance of strengthening agricultural export capacity, maintaining macroeconomic stability, and strategically allocating FDI to trade-enhancing sectors to improve Somalia's participation in global markets.

Introduction:Childhood anaemia remains a major public health problem in Ghana, with marked regional and socioeconomic disparities. Conventional regression may not fully capture complex, non-linear relationships among biological, maternal, and household factors. We used supervised machine learning to predict anaemia among children aged 6-59 months using nationally representative survey data. Methods:We analysed the 2022 Ghana Demographic and Health Survey, including de facto children aged 6-59 months with valid haemoglobin and complete covariates (weighted N = 3,382). Anaemia was defined as altitude-adjusted haemoglobin <11.0 g/dL. Twenty-one predictors were included. Data were split into training (80%) and testing (20%) sets using stratified sampling. Six models (logistic regression, decision tree, random forest, gradient boosting, support vector machine, and artificial neural network) were tuned via grid search with 10-fold cross-validation. Results:The weighted prevalence of childhood anaemia was 48.95% (n = 1,655). Gradient boosting showed the best overall discrimination (AUC = 0.72; F1 = 68.99%; accuracy = 66.27%). Support vector machine and logistic regression achieved the highest sensitivity (recall = 72.73% and 71.74%). Random forest showed overfitting (100% training accuracy; test accuracy = 65.23%). Decision tree and neural network performed poorly (AUC = 0.57 and 0.63). Key predictors across models and SHAP were child age, malaria status, maternal anaemia, region, and household wealth (with feature rankings varying by algorithm). Conclusion:Machine learning models achieved moderate predictive performance for childhood anaemia in Ghana. Gradient boosting provided the strongest discrimination, while support vector machine and logistic regression offered higher sensitivity for screening. However, these sensitivities imply that approximately 28-30% of anaemic children may be missed, which should be considered when applying these models in public health screening. Identified determinants support targeted, malaria-integrated nutrition and maternal-child interventions in high-risk groups.

Abstract This study investigates automatic dialect identification for the Somali language, focusing on its two primary dialects: MAXAA TIRI and MAAY. Somali exhibits substantial dialectal variation, which poses challenges for natural language processing (NLP) applications in low-resource settings. To support dialect-aware NLP research, we construct and manually annotate a dataset of 8947 Somali text samples collected from heterogeneous sources, including social media, news outlets, blogs, and formal documents. The study evaluates a range of traditional machine learning and deep learning models, including Naive Bayes, Support Vector Machines (SVM), and Bidirectional Long Short-Term Memory (BiLSTM) networks, for dialect classification. Experimental results show that Naive Bayes and BiLSTM achieve high classification performance under controlled evaluation settings. To mitigate overfitting and source bias, we apply source-aware data splitting, duplicate removal, and ablation analyses. However, results should be interpreted in light of dataset construction constraints, including expert-assisted translation for portions of the MAAY data. This work contributes a linguistically validated Somali dialect dataset and provides empirical insights into the effectiveness of machine learning and deep learning approaches for dialect identification in low-resource contexts.

BackgroundZoonotic diseases at the human–animal–environment interface pose an increasing global health threat, necessitating integrated diagnostic strategies under the One Health framework.MethodologyThis structured narrative review synthesizes evidence linking One Health diagnostics to cross-sectoral collaboration, diagnostic capacity strengthening, data sharing, preparedness, and emerging technological innovations. Predefined search terms were used to conduct a targeted literature search in Google Scholar, PubMed, and Web of Science (WOS) to identify relevant literature on One Health diagnostics, zoonotic disease surveillance, pathogen detection, diagnostic preparedness, laboratory systems, governance, and emerging technologies. Studies considered eligible were research articles, reviews, case studies, policy documents, technical reports, and organizational guidelines published in English between 2010 and 2026. The literature was reviewed and summarized thematically across the following domains: laboratory systems for veterinary and public health, integrated surveillance, low-resource settings, technological innovation, data interoperability, and diagnostic preparedness.FindingsThe findings indicate that effective One Health diagnostics rely on coordinated efforts among the veterinary, public health, and environmental sectors, supported by international organizations and integrated surveillance systems. Technological advancements, including polymerase chain reaction, next-generation sequencing, metagenomics, artificial intelligence, geographic information systems, mobile health tools, biosensors, and point-of-care testing, have improved pathogen detection, real-time monitoring, field diagnostics, and outbreak prediction. However, major challenges persist, including inadequate adherence to standardized data-sharing principles, fragmented surveillance systems, limited infrastructure in low-resource settings, and insufficient interdisciplinary integration. Case studies of SARS, Ebola, Hendra virus, and COVID-19 demonstrate the practical benefits of collaborative approaches while also highlighting systemic barriers to implementation.ConclusionThis review highlights the need for improvements in governance, standardized data-sharing frameworks, sustainable investment in diagnostic capacity, and better integration of new technologies into surveillance systems. Adopting a One Health approach to diagnostics research will require coordination to achieve meaningful impact through policy innovation, global collaboration, laboratory strengthening, and enhanced capacity for the detection, response, and prevention of zoonotic and emerging infectious diseases.

Introduction and importance: Meckel’s diverticulum (MD) is the most common congenital anomaly of the gastrointestinal tract, resulting from incomplete obliteration of the vitelline duct. Although usually asymptomatic, it may rarely present as an umbilical lesion resembling an umbilical granuloma, creating diagnostic challenges in low-resource settings. Presentation of case: A 4-month-old Somali male infant presented with a persistent umbilical mass and mucous discharge. The lesion had previously been diagnosed as an umbilical granuloma and treated with silver nitrate without improvement. Examination showed a red granulation-like mass at the umbilicus. During surgical exploration, the lesion was found to be a narrow-based Meckel’s diverticulum connected to the ileum through a persistent vitelline duct. A wedge resection with end-to-end anastomosis was performed. The postoperative course was uneventful, and the infant remained well at 1-month follow-up. Clinical discussion: MD affects about 2% of the population and typically presents with bleeding, obstruction, or diverticulitis. Presentation as an umbilical lesion is extremely rare and occurs when the vitelline duct remains patent. Diagnosis often relies on imaging such as a Meckel scan, but none was done here due to presumed granuloma. Surgical resection is the treatment of choice when MD is identified intraoperatively. Conclusion: Persistent or atypical umbilical lesions that fail to respond to conservative treatment should raise suspicion for vitelline duct remnants, including MD. Early surgical evaluation is essential to avoid complications and ensure accurate diagnosis, particularly in resource-limited settings like Somalia.