Iron deficiency anemia (IDA) continues to pose one of the most significant challenges in maternal health, affecting nearly 40% of pregnant women worldwide according to the World Health Organization (2023).  Despite advances in obstetric screening, conventional diagnostic methods such as complete blood count (CBC) tests often fail to detect early or latent stages of anemia due to physiological changes associated with pregnancy.  This study introduces a robust machine learning framework integrating Extreme Gradient Boosting (XGBoost), and Conditional Tabular Generative Adversarial Networks (CTGAN) for the early detection of IDA in pregnant women. Our approach addresses the class imbalance inherent in clinical datasets and incorporates trimester-specific hematological adaptations.  Using 3,944 anonymized clinical records from ASA Hospital Sarajevo (January–July 2025), we evaluated model performance across hematological features commonly used in obstetric care. The optimized model achieved a precision of 100%, recall of 65.2%, specificity of 100%, and an AUC-ROC of 0.8686. Comparative analysis against conventional CBC screening, which reached only 40.5% sensitivity, demonstrated significant improvement in detection reliability. These findings demonstrate the potential of AI-enhanced diagnostics to support early detection of IDA in pregnant women, reduce missed diagnoses, and strengthen clinical decision-making. Further multi-center validation and integration of additional biomarkers are recommended to confirm generalizability.

Objective: Expenditures for drugs are increasingly burdening already insufficient funds for health protection. This is especially evident in less developed European countries such as Bosnia and Herzegovina. The question is whether such analyses can help save funds for financing treatment for diseases, with an emphasis on a more rational choice of drug for appropriate indication, whereby clinical complications of hypertension would be prevented and patients would have quality of their lives improved. Aim: Focus of research has been set on analysis of use of antihypertensive drugs in Bosnia and Herzegovina in the time-period January 2013–March 2015. Use of all drugs for treatment of hypertension in that time-period in the country has been shown in an unbiased manner. Methods: The study is designed as retrospective-prospective comparative research of use of antihypertensive drugs in BiH in a certain time-period. Data are collected from relevant drug utilisation database which has been established in Bosnia and Herzegovina since 2013. Results: We have calculated financial expenditure for prescribed antihypertensives in the time- period of 2013, 2014 and Q1 2015. Use of antihypertensives at the country level for this time-period is BAM 200,242,218. At the country level, physicians are most often opting for combination therapy: ACE inhibitors + diuretics (20.2%) and ACE inhibitors + Ca channel antagonists (18.0%). Conclusion: In this research, it has been shown that modern drugs are used for treatment of hypertension in Bosnia and Herzegovina. These drugs are used in the same order as they are prescribed in developed countries.

Objective: to determine ascites and serum sodium significance in short term mortality prediction in patients with advanced liver cirrhosis. Methods: a cohort of 115 cirrhotic patients referred to our Department were followed up for 6 months in non-transplant settings. The c index equivalent to the area under the receiver operating curve (ROC) was calculated and compared to estimate the short-term prognostic accuracy of the following parameters: ascites, serum sodium and MELD score. Results: in patients with a MELD score less than 21, ascites and low serum sodium (c index 0,687, p<0 0,001 and 0,748, p<0,001 respectively) showed better prognostic accuracy and were independent predictors of mortality. For MELD scores above 21, only MELD was an independent mortality prognostic factor (c index 0,710, p<0,001). Conclusion: in our study, sample ascites and low serum sodium help identify patients with advanced liver disease who are at high risk of mortality despite low MELD scores. These parameters should be considered as additional prognostic parameters that could improve available treatment options and outcomes in this group of patients.