Background: Depression constitutes a major public health issue, being one of the leading causes of the burden of disease worldwide. The risk of depression is determined by both genetic and environmental factors. While genetic factors cannot be altered, the identification of potentially reversible environmental factors is crucial in order to try and limit the prevalence of depression. Aim: A cross-sectional, questionnaire-based study on a sample from the multicultural region of Thrace in northeast Greece was designed to assess the potential association of depression with several sociodemographic characteristics, lifestyle, and health status. The study employed four machine learning (ML) methods to assess depression: logistic regression (LR), support vector machine (SVM), XGBoost, and neural networks (NNs). These models were compared to identify the best-performing approach. Additionally, a genetic algorithm (GA) was utilized for feature selection and SHAP (SHapley Additive exPlanations) for interpreting the contributions of each employed feature. Results: The XGBoost classifier demonstrated the highest performance on the test dataset to predict depression with excellent accuracy (97.83%), with NNs a close second (accuracy, 97.02%). The XGBoost classifier utilized the 15 most significant risk factors identified by the GA algorithm. Additionally, the SHAP analysis revealed that anxiety, education level, alcohol consumption, and body mass index were the most influential predictors of depression. Conclusions: These findings provide valuable insights for the development of personalized public health interventions and clinical strategies, ultimately promoting improved mental well-being for individuals. Future research should expand datasets to enhance model accuracy, enabling early detection and personalized mental healthcare systems for better intervention.

: Main causes of death in Greece are cardiovascular diseases (CVDs), malignant neoplasms, respiratory diseases, and road traffic crashes. To assess the population health status, monitor health systems, and adjust policies, national population-based health surveys are recommended. The previous health surveys that were conducted in Greece were restricted to specific regions or high-risk groups. : This paper presents the design and methods of the Greek Health Examination Survey EMENO (National Survey of Morbidity and Risk Factors). The primary objectives are to describe morbidity (focusing on CVD, respiratory diseases, and diabetes), related risk factors, as well as health care and preventive measures utility patterns in a random sample of adults living in Greece. : The sample was selected by applying multistage stratified random sampling on 2011 Census. Trained interviewers and physicians made home visits. Standardized questionnaires were administered; physical examination, anthropometric and blood pressure measurements, and spirometry were performed. Blood samples were collected for lipid profile, glucose, glycated hemoglobin, and transaminases measurements. The survey was conducted from May 2013 until June 2016. : In total, 6006 individuals were recruited (response rate 72%). Of these, 4827 participated in at least one physical examination, 4446 had blood tests, and 3622 spirometry, whereas 3580 provided consent for using stored samples for future research (3528 including DNA studies). Statistical analysis has started, and first results are expected to be submitted for publication by the end of 2018. : EMENO comprises a unique health data resource and a bio-resource in a Mediterranean population. Its results will provide valid estimates of morbidity and risk factors’ prevalence (overall and in specific subdomains) and health care and preventive measures usage in Greece, necessary for an evidence-based strategy planning of health policies and preventive activities.

Introduction: Vaccination against SARS-CoV-2 and the prevalence of Omicron variants have reduced the risk of the severe clinical progress of COVID-19. However, the risk of breakthrough infections has increased, and early administration of an effective antiviral treatment is significant in order to prevent the severe progression of COVID-19 in vulnerable patients with comorbidities. Patients and methods: Adults with confirmed SARS-CoV-2 infection were included in a matched-pair retrospective study based on age, gender, comorbidities and vaccination status. They were divided into two groups: group A (n = 200) consisted of outpatients at increased risk of severe clinical progress who were treated with nirmatrelvir/ritonavir and group B (n = 200) consisted of non-hospitalized patients who did not receive antiviral treatment. Demographic data, clinical outcome (death, intubation), days of hospitalization, time for recovery, adverse events and treatment compliance were reported. Results: The median age (75.24 ± 13.12 years in the study group and 76.91 ± 14.02 years in the comparison group) and the proportion of males (59% vs. 60.5%, respectively) were similar between the two groups. A total of 6.5% of patients in group A and 10.5% in group B were unvaccinated against SARS-CoV-2. Three patients from group A (1.5%) and one hundred eleven (55.5%) from group B required hospitalization. The duration of hospitalization (3 days vs. 10 days in group B, p < 0.001) and the total time needed for recovery (5 days vs. 9 days, p < 0.001) was shorter in the study group. A rebound of SARS-CoV-2 infection within 8–12 days after diagnosis was documented in 6.5% of patients in group A and 8% of patients in group B. Conclusion: Oral treatment with nirmatrelvir/ritonavir in high-risk non-hospitalized patients was safe and effective in preventing the severe clinical progress of COVID-19 pneumonia. Early administration of antiviral agents in vulnerable outpatients combined with a full vaccination scheme is significant in order to avoid hospitalization and severe clinical outcomes.

Purpose: The main objective of the study is to evaluate the effect of hyperthermic intraperitoneal chemotherapy (HIPEC) in the treatment of naïve ovarian cancer women undergoing complete or near-complete cytoreduction by assessing the overall survival, the disease-specific survival, and the disease-free survival. The secondary objective is the identification of prognostic indicators of survival and recurrence of these patients. Patients—Methods: Retrospective study of treatment in naïve women with locally advanced ovarian cancer treated with cytoreductive surgery (CRS) and HIPEC and compared with those who were treated with cytoreduction alone. Clinicopathologic variables were correlated to overall survival, disease-specific survival, and disease-free survival using Kaplan–Meier method, and the multivariate Cox proportional hazards regression models. Results: 5- and 10-year overall survival, disease-specific survival, and disease-free survival rates were significantly higher in patients treated with CRS and HIPEC. These patients were 67% less likely to die from any cause (adjusted hazard ratio, aHR = 0.33, p = 0.001), 75% less likely to die from cancer (aHR = 0.25, p = 0.003), and 46% less likely to develop recurrence (aHR = 0.54, p = 0.041) compared to patients treated with CRS alone. Moreover, the poor performance status (aHR = 2.96, p < 0.001), the serous carcinomas (aHR = 0.14, p = 0.007), and the morbidity (aHR = 6.87, p < 0.001) were identified as independent indicators of poor overall survival. The degree of differentiation (aHR = 8.64, p = 0.003) was identified as the independent indicator of disease-specific survival (aHR = 4.13, p = 0.002), while the extent of peritoneal carcinomatosis (aHR = 2.32, p < 0.001) as the independent indicator of disease-free survival. Conclusions: Treatment in naïve patients with locally advanced ovarian cancer undergoing CRS plus HIPEC appears to have improved overall, disease-specific, and disease-free survival.

As a result of social progress and improved living conditions, which have contributed to a prolonged life expectancy, the prevalence of strokes has increased and has become a significant phenomenon. Despite the available stroke treatment options, patients frequently suffer from significant disability after a stroke. Initial stroke severity is a significant predictor of functional dependence and mortality following an acute stroke. The current study aims to collect and analyze data from the hyperacute and acute phases of stroke, as well as from the medical history of the patients, in order to develop an explainable machine learning model for predicting stroke-related neurological deficits at discharge, as measured by the National Institutes of Health Stroke Scale (NIHSS). More specifically, we approached the data as a binary task problem: improvement of NIHSS progression vs. worsening of NIHSS progression at discharge, using baseline data within the first 72 h. For feature selection, a genetic algorithm was applied. Using various classifiers, we found that the best scores were achieved from the Random Forest (RF) classifier at the 15 most informative biomarkers and parameters for the binary task of the prediction of NIHSS score progression. RF achieved 91.13% accuracy, 91.13% recall, 90.89% precision, 91.00% f1-score, 8.87% FN_rate and 4.59% FP_rate. Those biomarkers are: age, gender, NIHSS upon admission, intubation, history of hypertension and smoking, the initial diagnosis of hypertension, diabetes, dyslipidemia and atrial fibrillation, high-density lipoprotein (HDL) levels, stroke localization, systolic blood pressure levels, as well as erythrocyte sedimentation rate (ESR) levels upon admission and the onset of respiratory infection. The SHapley Additive exPlanations (SHAP) model interpreted the impact of the selected features on the model output. Our findings suggest that the aforementioned variables may play a significant role in determining stroke patients’ NIHSS progression from the time of admission until their discharge.

OBJECTIVE: Modifications in E-cadherin (E-Cad) expression are associated with dedifferentiation, progression, metastases and poor prognosis in many types of tumors. The aim of the present study was to identify a potential association of the pre- and post-operative soluble E-Cad levels (sE-Cad) with the clinicopathological parameters of patients with gastric cancer. PATIENTS AND METHODS: Serum sE-Cad levels were determined in 99 gastric cancer patients and 78 healthy volunteers using ELISA. RESULTS: Levels of sE-Cad were significantly increased in gastric cancer patients compared with these levels in healthy controls (p < 0.001). For the evaluation of the diagnostic significance of sE-Cad the area under the receiver operating characteristic (ROC) curve (AUC) was 0.835, while the optimal cut-off point of 9.9 μg/mL was determined to classify gastric cancer patients, which yielded sensitivity of 72.7%, specificity of 80.8% and accuracy of 76.3%. Poor differentiation (p = 0.009) and the presence of distant metastases (p < 0.001) were the two significant independent prognostic determinants for high sE-Cad levels in multivariate linear regression analysis. The preoperative levels of sE-Cad also proved helpful in classifying patients according to the choice treatment (curative versus palliative) (AUC, 0.656); when the optimal cut-off point was set at 17.60 μg/mL, the sensitivity was 57%, the specificity was 83% and accuracy was 75%. Survival was shorter in patients with increased sE-Cad (median, 7 months vs 39 months, p = 0.0002), although multivariate Cox regression analysis demonstrated a marginal prognostic significance of sE-Cad for survival (adjusted HR = 1.68, 95% CI = 0.93 to 3.02, p = 0.072). CONCLUSIONS: Serum sE-Cad levels could be considered as a diagnostic and prognostic marker in gastric cancer patients as well as a tool to select a treatment approach. The prognostic value of sE-Cad on overall survival requires further study.