Background: Healthcare workers face multiple, interlinked occupational health risks—burnout, post-COVID-19 sequelae (Long COVID), and extended medical leave. These outcomes often share predictors, contribute to each other, and, together, impact workforce capacity. Yet, existing tools typically address them in isolation. Objective: The objective of this study to develop and deploy an integrated, explainable artificial intelligence (AI) framework that predicts these three outcomes using the same structured occupational health dataset, enabling unified workforce risk monitoring. Methods: We analyzed data from 1244 Romanian healthcare professionals with 14 demographic, occupational, lifestyle, and comorbidity features. For each outcome, we trained a separate predictive model within a common framework: (1) a lightweight transformer neural network with hyperparameter optimization, (2) a transformer with multi-head attention, and (3) a stacked ensemble combining transformer, XGBoost, and logistic regression. The data were SMOTE-balanced and evaluated on held-out test sets using Accuracy, ROC-AUC, and F1-score, with 10,000-iteration bootstrap testing for statistical significance. Results: The stacked ensemble achieved the highest performance: ROC AUC = 0.70 (burnout), 0.93 (Long COVID), and 0.93 (extended leave). The F1 scores were >0.89 for Long COVID and extended leave, whereas the performance gains for burnout were comparatively modest, reflecting the multidimensional and heterogeneous nature of burnout as a binary construct. The gains over logistic regression were statistically significant (p < 0.0001 for Long COVID and extended leave; p = 0.0355 for burnout). The SHAP analysis identified overlapping top predictors—tenure, age, job role, cancer history, pulmonary disease, and obesity—supporting the value of a unified framework. Conclusions: We trained separate models for each occupational health risk but deployed them in a single, real-time web application. This integrated approach improves efficiency, enables multi-outcome workforce surveillance, and supports proactive interventions in healthcare settings.

Autosomal dominant polycystic kidney disease (ADPKD) is the most common genetic kidney disease, and it leads to end-stage renal disease (ESRD). The clinical manifestations of ADPKD are variable, with extreme differences observable in its progression, even among members of the same family with the same genetic mutation. In an age of new therapeutic options, it is important to identify patients with rapidly progressive evolution and the risk factors involved in the disease’s poor prognosis. As the pathophysiological mechanisms of the formation and growth of renal cysts have been clarified, new treatment options have been proposed to slow the progression to end-stage renal disease. Furthermore, in addition to the conventional factors (PKD1 mutation, hypertension, proteinuria, total kidney volume), increasing numbers of studies have recently identified new serum and urinary biomarkers of the disease’s progression, which are cheaper and more easily to dosing from the early stages of the disease. The present review discusses the utility of new biomarkers in the monitoring of the progress of ADPKD and their roles in new therapeutic approaches.

Introduction: The pathophysiology of preeclampsia is represented by placental ischemia and the release of angiogenic factors. Recent research suggests that using the value of the sFtl-1/PIGF ratio is more accurate for monitoring angiogenic activity. The aim of this study consists in assessing the clinical utility of the sFtl-1/PIGF ratio in determining the diagnosis and severity of preeclampsia. Material and Methods: In our study a descriptive and prospective plan was used for analyzing the specific value of the sFtl-1/PIGF ratio in women with preeclampsia and in women with gestational hypertension, depending on the gestational age and severity. Results: The study included 59 women with preeclampsia and 25 women with gestational hypertension. The mean value of the sFtl-1/PIGF ratio of pregnant women with preeclampsia was 209.2 pg/mL, while in the gestational hypertension group, the mean value of the sFtl-1/PIGF ratio was 46.08 pg/mL. The difference between the value of the sFtl-1/PIGF ratio of the group with preeclampsia and the gestational hypertension group was > 67 (pg/mL), with a sensitivity of 86.44% and a specificity of 92.00%. Significant differences were found between the median values of the sFtl-1/PIGF ratio in pregnant women with severe preeclampsia in the early-onset subgroup compared to those in the late-onset subgroup (307 pg/mL, and 98 pg/mL, respectively, p = 0.009 < α = 0.05). Conclusions: The sFtl-1/PIGF ratio may be an alternative method for diagnosing preeclampsia and it can provide data about this condition’s severity.

Background: Pan-drug-resistant (PDR) Acinetobacterinfections are an escalating ICU threat, demanding both patient-level triage and facility-wide forecasting. Objective: The aim of this study was to build a dual-scale AI framework that (i) predicts PDR status at infection onset and (ii) forecasts hospital-level PDR burden through 2027. Methods: We retrospectively analyzed 270 Acinetobacter infection episodes (2020–2024) with 65 predictors spanning demographics, timelines, infection type, resistance-class flags, and a 25-drug antibiogram. TabTransformer and XGBoost were trained on 2020–2023 episodes (n = 210), evaluated by stratified 5-fold CV, and externally tested on 2024 episodes (n = 60). Metrics included AUROC, AUPRC, accuracy, and recall at 90% specificity; AUROC was optimism-corrected via 0.632 + bootstrap and DeLong-tested for drift. SHAP values quantified feature impact. Weekly PDR incidence was forecast with an attention–LSTM model retrained monthly (200 weekly origins, 4-week horizon) and benchmarked against seasonal-naïve, Prophet, and SARIMA models (MAPE and RMSE). Quarterly projections (TFT-lite) extended forecasts to 2027. Results: The CV AUROC was 0.924 (optimism-corrected 0.874); an ensemble of TabTransformer + XGBoost reached 0.958. The 2024 AUROC fell to 0.586 (p < 0.001), coinciding with a PDR prevalence drop (75→38%) and three covariates with PSIs > 1.0. Isotonic recalibration improved the Brier score from 0.326 to 0.207 and yielded a net benefit equivalent to 26 unnecessary isolation-days averted per 100 ICU admissions at a 0.20 threshold. SHAP highlighted Ampicillin/Sulbactam resistance, unknown acquisition mode, and device-related infection as dominant drivers. The attention–LSTM achieved a median weekly MAE of 0.10 (IQR: 0.028–0.985) vs. 1.00 for the seasonal-naïve rule, outperforming it on 48.5% of weeks and surpassing Prophet and SARIMA (MAPE = 6.2%, RMSE = 0.032). TFT-lite projected a ≥ 25% PDR tipping point in 2025 Q1 with a sustained rise in 2027. Conclusions: The proposed framework delivers explainable patient-level PDR risk scores and competitive 4-week and multi-year incidence forecasts despite temporal drift, supporting antimicrobial stewardship and ICU capacity planning. Shrinkage and bootstrap correction were applied to address the small sample size (EPV = 2.1), which poses an overfitting risk. Continuous recalibration and multi-center validation remain priorities.

Background: Lumbar disc herniation (LDH) has a substantial impact on health-related quality of life (HRQoL), mainly through pain, reduced mobility, and functional limitations. To better reflect these outcomes, we utilized the SF-36 survey, a well-established tool commonly used in both clinical and population research. The purpose was twofold: to evaluate HRQoL and to explore the main factors linked with activity limitation in a community-based group of Romanian patients. Methods: This cross-sectional study included 120 participants with LDH who completed the SF-36 questionnaire. Internal consistency was high (Cronbach’s α = 0.922). Descriptive statistics, Chi-square tests, t-tests, and multivariate regressions were performed using SPSS 18.0. Results: Of the respondents, 53.3% were female and 58.4% were over 60 years old. While 55% reported good or very good health, 26.7% had severe Daily Activity Limitation (DAL) based on the SF-36 physical function score, and 62.5% scored in the poorer range (33–45) of the Physical and Emotional Status (PES) composite derived from the SF-36. Female sex and age over 60 were each associated with nearly a twofold-higher risk of moderate-to-severe DAL (OR = 2.20, 95% CI: 1.04–4.65), while reporting severe or very severe pain increased this risk more than fourfold (OR = 4.64, 95% CI: 1.89–24.21). Conclusions: In patients with LDH, poor self-rated health, older age, female sex, and high pain intensity were significantly associated with reduced functional capacity. The SF-36 proved to be a valuable tool for identifying vulnerable subgroups that require targeted rehabilitation and psychosocial support. From a public health perspective, these findings also support the use of SF-36 in community screening and in guiding resource allocation for multidisciplinary rehabilitation programs.

Background and Objectives: Healthcare-associated infections (HAIs) are a major cause of morbidity and mortality and can lead to serious long-term consequences, increased hospital length stay, higher rates of antibiotic resistance, and additional financial costs. The study aim was to highlight important aspects related to the level of knowledge of HAIs, risk factors for HAI and methods of preventing HAIs among nurses from urban hospitals in the North-East of Romania. Materials and Methods: We conducted a cross-sectional study on the level of knowledge of HAI problems among medical personnel (nurses). The study group consisted of 288 nurses who responded online to a questionnaire. Results: Multivariate analysis suggested that 45.5% of the value of the knowledge score of prevention and limitation of HAIs could be determined by the answers to the questions regarding the importance of the nurse role, professional experience, and training. Moreover 84.6% of the knowledge score could be determined by the answers to the questions regarding the assessment of the importance of factors related to lack of medical personnel, professional burnout, insufficient knowledge and staff training, inefficient team, poor collaboration within departments, stressful work environment, staff health status, multiple tasks at work (p = 0.038). While 50% of the knowledge score could be explained by responses regarding personal problems related to daily activity; physical and mental health status; and physical, psychological, and social components (p = 0.038). Conclusions: Our study highlighted aspects of the level of knowledge regarding HAIs among nurses, an issue that plays a key role in hospital management. Overall, the knowledge score for the prevention and limitation of HAIs was higher in nurses/females aged over 40 and in nurses with more than 15 years of experience.