Prediction of short-term mortality in patients with acute decompensation of liver cirrhosis could be improved. We aimed to develop and validate two machine learning (ML) models for predicting 28-day and 90-day mortality in patients hospitalized with acute decompensated liver cirrhosis. We trained two artificial neural network (ANN)-based ML models using a training sample of 165 out of 290 (56.9%) patients, and then tested their predictive performance against Model of End-stage Liver Disease-Sodium (MELD-Na) and MELD 3.0 scores using a different validation sample of 125 out of 290 (43.1%) patients. The area under the ROC curve (AUC) for predicting 28-day mortality for the ML model was 0.811 (95%CI: 0.714- 0.907; p < 0.001), while the AUC for the MELD-Na score was 0.577 (95%CI: 0.435–0.720; p = 0.226) and for MELD 3.0 was 0.600 (95%CI: 0.462–0.739; p = 0.117). The area under the ROC curve (AUC) for predicting 90-day mortality for the ML model was 0.839 (95%CI: 0.776- 0.884; p < 0.001), while the AUC for the MELD-Na score was 0.682 (95%CI: 0.575–0.790; p = 0.002) and for MELD 3.0 was 0.703 (95%CI: 0.590–0.816; p < 0.001). Our study demonstrates that ML-based models for predicting short-term mortality in patients with acute decompensation of liver cirrhosis perform significantly better than MELD-Na and MELD 3.0 scores in a validation cohort.

Introduction: Peritoneal lymphangiomatosis is a rare benign lymphatic disorder with diagnostic and therapeutic challenges. It may mimic peritoneal carcinomatosis or mesothelioma, often requiring histological confirmation. Management options are limited, and long-term data on targeted therapies, including sirolimus, remain scarce. Case Presentation: We present the case of a 45-year-old woman with a history of surgically corrected atrial septal defect, who developed progressive abdominal distension and dysuria in May 2014. Abdominal ultrasound and contrast-enhanced abdominal computed tomography revealed diffuse ascites, peritoneal thickening, and cystic changes. Diagnostic uncertainty led to an exploratory laparotomy in May 2015, where histopathology confirmed peritoneal lymphangiomatosis. After failed conservative management including dietary modification, diuretic therapy, and repeated paracenteses, she was started on sirolimus 2 mg/day in August 2016. Her serum trough levels were maintained between 5 and 15 ng/mL. She achieved a Karnofsky Performance Score of 100% (indicating full functional capacity) within 2 months and has remained in complete clinical and radiologic remission for over 8 years. Diabetes mellitus type 2 was diagnosed during follow-up and is well controlled with insulin therapy. Conclusion: This case underscores the difficulty of diagnosing peritoneal lymphangiomatosis and highlights the transformative potential of sirolimus therapy. To our knowledge, this is one of the longest documented remissions of peritoneal lymphangiomatosis under mechanistic target of rapamycin (mTOR) inhibition.

The aim of the current research was to investigate the association between plasma endocan levels and metabolic control parameters, as well as to evaluate its predictive value for clinical complications in patients with type 2 diabetes mellitus (DMT2). A total of 100 DMT2 patients participated in this prospective observational study. Plasma endocan levels were significantly elevated in DMT2 patients with HbA1c > 7% (1.38 ± 0.33 vs 0.68 ± 0.23 ng/mL; P < 0.0001), compared to patients with HbA1c ≤ 7%. Patients with plasma endocan concentrations >1.10 ng/mL (median value of 1.10 ng/mL) demonstrated significantly higher levels of metabolic parameters: body mass index (BMI), HbA1c (%), fasting glucose level, LDL cholesterol, total cholesterol, triglycerides, along with significantly lower HDL cholesterol levels. Furthermore, patients with plasma endocan levels >1.10 ng/mL were found to have an increased risk for the following complications: retinopathy (relative risk [RR]: 2.7500; 95% confidence interval [CI]: 1.2150–6.2244; P = 0.0152, nephropathy (RR: 2.0952; 95% CI: 1.2294–3.5710; P = 0.0065), neuropathy (RR: 1.9945; 95% CI: 1.2025–3.3081; P = 0.0075), angina pectoris (RR: 2.4881; 95% CI: 1.0865–5.6979; P = 0.0311, hypertension (RR: 1.1372; 95% CI: 1.0060–1.2856; P = 0.0398), cardiomyopathy (RR: 2.6190; 95% CI: 1.1507–5.9612; P = 0.0218), myocardial infarction (RR: 9.4286; 95% CI: 1.2742–69.7697; P = 0.0280) and stroke (RR: 4.4638; 95% CI: 1.3765–14.4758; P = 0.0127). Correlation analysis revealed that plasma endocan levels were positively correlated with HbA1c (%) (r = 0.856, P < 0.0001), fasting glucose level (r = 0.631, P < 0.0001), LDL (r = 0.347, P = 0.0004), cholesterol (r = 0.282, P = 0.0045), and triglycerides (r = 0.366, P = 0.0002). Conversely, plasma endocan levels were negatively correlated with HDL cholesterol (r = −0.429, P < 0.0001). In conclusion, higher plasma endocan levels were strongly associated with poor metabolic control in DMT2 patients and exhibited significant predictive value for both microvascular and macrovascular complications.

Summary: Researchers in Bosnia and Herzegovina face systemic barriers to publishing, including scarce funding and weak institutional support. Limited mentorship and low research literacy increase vulnerability to predatory journals and conferences. Fragmented academic and healthcare systems hinder collaboration and international visibility. Financial constraints and APC costs divert high‐quality local research away from mainstream journals. Practical reforms should focus on research support offices, regional collaborations, and improved promotion criteria.