Iuliu Fulga

Background: Interrupted time-series studies have not shown a consistent increase in suicide mortality during COVID-19, but civil mortality registries cannot ascertain SARS-CoV-2 infection individually. We evaluated pandemic-related change in suicide mortality and the feasibility of integrating infection ascertainment into medico-legal surveillance. Methods: We analysed 395 suicide deaths in Galați and Brăila counties, Romania (January 2018–December 2024), where mandatory forensic autopsy ensures exhaustive ascertainment. The pre-specified primary analysis was seasonally adjusted segmented Poisson regression in January 2018–December 2022 with an onset in March 2020; the period 2023–2024 was excluded as incompletely ascertained. Changepoint detection and unadjusted period comparisons were descriptive. Infection was classified as laboratory-confirmed (documented ante-mortem RT-PCR) or possible/probable (compatible autopsy findings); no post-mortem testing was performed. Results: The level change at onset was not significant (IRR 1.29, 95% CI 0.80–2.08; p = 0.302), nor was the slope change (IRR 1.01, 95% CI 0.98–1.04; p = 0.639); power was 80% only against IRR ≥ 1.98. Posterior probabilities were 0.85 for any increase and 0.035 for a doubling. The unadjusted comparison (6.00 vs. 4.62 deaths/month; IRR 1.30, 95% CI 1.04–1.63) was descriptive; no changepoint coincided with onset. Among 140 deaths in 2020–2021, 34 (24.3%) met ascertainment criteria, 21 (15.0%) laboratory-confirmed. Conclusions: The data exclude a doubling of suicide mortality but not a modest increase: a regional surveillance signal, not a causal finding. Infection ascertainment proved feasible within routine medico-legal investigation, yielding a reproducible framework for other registries, an Eastern European series for future meta-analyses, and a proof-of-concept for a standing forensic surveillance capacity adaptable to future epidemics.

Artificial intelligence (AI) is increasingly being integrated into medical practice, offering promising tools to improve diagnostic accuracy and clinical efficiency. In the field of breast pathology, AI applications, particularly those based on deep learning (DL) and machine learning (ML), are emerging as decision-support tools in both diagnostic and prognostic workflows. This review provides a comprehensive overview of current AI-based approaches, with a focus on their clinical utility in tumor detection, histological classification, biomarker assessment, and prediction of treatment response. In addition to summarizing available AI platforms, the review critically examines their level of clinical validation, regulatory status, and integration into routine practice. Key challenges are also discussed. Overall, AI is expected to play an increasingly important role in supporting pathologists and advancing precision medicine in breast cancer management.

Background: Suicide is a leading cause of preventable death, yet machine learning (ML) analyses of forensic (medico-legal) suicide data are scarce and, to our knowledge, absent for Romania. Population-based forensic registries offer exhaustive, autopsy-confirmed coverage that is structurally distinct from clinical or civil death-registration data. We applied supervised and unsupervised ML to a complete regional medico-legal suicide registry to profile the method of death and to identify latent victim subgroups of preventive relevance. Methods: We analysed 395 consecutive suicide deaths (Galați and Brăila counties, ≈750,000 inhabitants; 2018–2024). Two supervised classifiers—L2-regularised logistic regression (LR) and random forest (RF, 200 trees)—were trained to discriminate hanging from other methods, using eleven sociodemographic and clinical predictors, and evaluated by 10-fold stratified cross-validation. Given severe class imbalance, the area under the ROC curve (AUC) was the primary metric. Model hyperparameters were fixed a priori, and no class-imbalance correction was applied; both decisions are pre-specified and justified in the Methods. Robustness was assessed by stratified non-parametric bootstrap confidence intervals for the odds ratios, a tipping-point sensitivity analysis for the undocumented clinical fields, and Ward-linkage hierarchical clustering as an independent partitioning check. Predictor importance was quantified by out-of-bag (OOB) permutation importance and Spearman correlations. Unsupervised structure was assessed by K-means clustering (k = 2–7), with the optimal solution selected by the average silhouette coefficient and the elbow (WCSS) criterion. Reporting followed TRIPOD+AI and STROBE. Results: The study population was predominantly male (87.1%) and rural (73.2%), with a mean age of 54.1 years; hanging accounted for 94.2% of deaths—far above the European average (≈50%). RF achieved AUC = 0.865 ± 0.181 and LR AUC = 0.847 ± 0.192, both within the “excellent” discrimination band; sensitivity was very high (0.995–0.997) and specificity was limited (0.233–0.367), an expected consequence of imbalance. Prior suicide attempts (OOB importance 0.959; Spearman ρ = −0.549, p < 0.001; OR = 0.496, 95% CI 0.25–0.72) and the presence of a suicide note (importance 0.575; ρ = −0.439, p < 0.001; OR = 0.549, 95% CI 0.34–0.76) were the dominant predictors. K-means identified two well-separated clusters (silhouette = 0.707), and the partition was reproduced exactly by Ward-linkage hierarchical clustering (adjusted Rand index = 1.000). Cluster 2 (n = 19; 4.8%) was a clinically distinct, younger subgroup (42.4 vs. 54.7 years) characterised by prior attempts (57.9% vs. 0%), suicide notes (68.4% vs. 0%), higher psychiatric comorbidity (52.6% vs. 30.9%) and lower hanging proportion (36.8% vs. 97.1%)—an exploratory, hypothesis-generating profile of recurrent suicidal behaviour with documented prior contact with the medical or medico-legal system. The principal findings were stable across all plausible degrees of clinical under-documentation in the tipping-point sensitivity analysis. Conclusions: ML applied to a complete forensic suicide registry reproduced known regional epidemiology and, beyond classical statistics, isolated an exploratory but clinically coherent high-risk subgroup of direct relevance to the audit of structured post-attempt follow-up. This is, to our knowledge, the first ML study of Romanian forensic suicide data and supports integrating ML into medico-legal research and into the regional targeting and audit of existing post-attempt follow-up provision.

Optimizing drug administration remains a central challenge in the development of modern therapies, especially in the context of conditions that require spatiotemporal control of active substance release. In this context, hydrogels have been intensively investigated as polymeric platforms for drug delivery, through their three-dimensional hydrophilic structure, tunable properties, and compatibility with biological environments. This analysis presents an integrated approach to hydrogels used in drug administration, addressing the physicochemical fundamentals, the constitutive polymeric materials, and the mechanisms of response to relevant physiological stimuli. Recent experimental studies have been discussed, which highlight the use of hydrogels based on natural, synthetic, and hybrid polymers for controlled and targeted release, in correlation with various administration routes, including oral, injectable, transmucosal, and topical ones. Advanced functionalization strategies that allow adaptive responses to pH, temperature, glucose, enzymes, and reactive oxygen species are also analyzed. Furthermore, emerging directions integrating hydrogels with biosensors, microdevices, and wireless communication systems for real-time monitoring and on-demand release are highlighted. Overall, the analysis emphasizes the role of smart hydrogels as multifunctional platforms for complex therapeutic strategies while also underlining the current challenges associated with clinical translation and long-term performance.

The application of artificial intelligence in esophageal tumor pathology highlights the ongoing and significant transformative impact AI has in medicine. This article provides a comprehensive overview of AI technologies' current use in diagnosing and treating esophageal squamous cell carcinoma (ESCC). Through our research, we identified and meticulously analyzed 33 relevant academic papers and studies that contribute to this field. These papers encompass a broad spectrum of AI applications related to the management of esophageal squamous cell carcinoma. AI integration and deployment in both the diagnosis process and therapeutic interventions for tumors offer highly promising prospects, for example, in endoscopic procedures AI algorithm can process endoscopic images in real-time to identify abnormalities that may be missed by the human eye, it can highlight subtle changes such as color variations, small growths or tissue anomalies, which might go unnoticed due to fatigue, distraction or human limitations in perceiving fine details. AI technologies enhance medical practice precision and effectiveness by significantly reducing the likelihood of human errors and offering practical, innovative solutions. Consequently, AI confluence with medical practice not only increases diagnosis accuracy but also improves the overall efficiency of treating esophageal squamous cell carcinoma.

Cancer is a leading cause of death globally, claiming millions of lives each year. Despite the availability of numerous anticancer drugs, the need for new treatment options remains essential. Many current therapies come with significant toxicity, lead to various side effects, or do not consistently deliver the expected therapeutic results. Purines and pyrimidines are fundamental building blocks of nucleic acids and play crucial roles in cellular metabolism and signaling. Recent advances in medicinal chemistry have led to the development and synthesis of various derivatives that exhibit selective cytotoxic effects against cancer cells while minimizing toxicity to healthy tissues. Purine and pyrimidine scaffolds, due to their well-established biological roles and structural versatility, have emerged as key pharmacophoric fragments in anticancer drug discovery. In recent years, the rational design of hybrid molecules incorporating these heterocycles has shown promise in overcoming drug resistance, improving target selectivity, and enhancing pharmacological profiles. Purine and pyrimidines scaffolds hold significant potential as foundations for novel antitumor drugs, with established representatives in cancer treatment, including 5-fluorouracil, cladribine, capecitabine, and several others. In addition, the article discusses the challenges and future developments of purine and pyrimidine derivatives and hybrid molecules as antitumor drugs and emphasizes the need for continued research to optimize their effectiveness and reduce side effects. Overall, the innovative use of these compounds represents a major advance in targeted cancer therapy and holds promise for improving the therapeutic efficacy of malignant diseases.

Wound healing is a complex, tightly regulated process essential for maintaining skin barrier function. Chronic wounds, often complicated by biofilm-forming bacteria and elevated oxidative stress, pose significant challenges in clinical management. The rise of antibiotic-resistant bacteria has further exacerbated the problem, limiting therapeutic options and complicating wound treatment. Traditional wound care approaches frequently fail to provide real-time accurate insights into wound status, leading to delayed or suboptimal treatments. Recent advancements in modern and smart wound dressings, which integrate various biosensors, different new drug delivery systems, and wireless communication technology, offers promising solutions for monitoring wound progression over time. These innovations enable early detection of adverse events such as bacterial infections and inflammation, facilitating more effective, on-demand treatment. This review highlights the current state of antibiotic-embedded wound dressings, discusses their limitations, and explores the potential of next-generation wound dressings incorporating microelectronic sensors for real-time monitoring and adaptive therapeutic responses to support healing and combat antimicrobial resistance.

Background: Cardiogenic shock (CS) is a life-threatening complication of ST-elevation myocardial infarction (STEMI) and remains the leading cause of in-hospital mortality, with rates ranging from 5 to 10% despite advances in reperfusion strategies. Early identification and timely intervention are critical for improving outcomes. This study investigates the utility of machine learning (ML) models for predicting the risk of CS during the early phases of care—prehospital, emergency department (ED), and cardiology-on-call—with a focus on accurate triage and prioritization for urgent angiography. Results: In the prehospital phase, the Extra Trees classifier demonstrated the highest overall performance. It achieved an accuracy (ACC) of 0.9062, precision of 0.9078, recall of 0.9062, F1-score of 0.9061, and Matthews correlation coefficient (MCC) of 0.8140, indicating both high predictive power and strong generalization. In the ED phase, the support vector machine model outperformed others with an ACC of 78.12%. During the cardiology-on-call phase, Random Forest showed the best performance with an ACC of 81.25% and consistent values across other metrics. Quadratic discriminant analysis showed consistent and generalizable performance across all early care stages. Key predictive features included the Killip class, ECG rhythm, creatinine, potassium, and markers of renal dysfunction—parameters readily available in routine emergency settings. The greatest clinical utility was observed in prehospital and ED phases, where ML models could support the early identification of critically ill patients and could prioritize coronary catheterization, especially important for centers with limited capacity for angiography. Conclusions: Machine learning-based predictive models offer a valuable tool for early risk stratification in STEMI patients at risk for cardiogenic shock. These findings support the implementation of ML-driven tools in early STEMI care pathways, potentially improving survival through faster and more accurate decision-making, especially in time-sensitive clinical environments.

Background: While early risk stratification in STEMI is essential, the threat of cardiogenic shock (CS) persists after revascularization due to reperfusion injury and evolving instability. However, risk prediction in later phases—after revascularization—is less explored, despite its importance in guiding intensive care decisions. This study evaluates machine learning (ML) models for dynamic risk assessment in interventional cardiology and cardiac intensive care unit (CICU) phases, where timely detection of deterioration can guide treatment escalation. Methods: We retrospectively analyzed clinical and procedural data from 158 patients diagnosed with STEMI complicated by cardiogenic shock, treated between 2019 and 2022 at the Cardiology Department of the University Emergency Hospital of Bucharest, Romania. Machine learning models—Random Forest (RF), and Quadratic Discriminant Analysis (QDA)—were developed and tested specifically for the interventional cardiology and CICU phases. Model performance was evaluated using area under the receiver operating characteristic curve (ROC-AUC), accuracy (ACC), sensitivity, specificity, and F1-score. Results: In the interventional phase, RF and QDA achieved the highest accuracy, both reaching 87.50%. In the CICU, RF and QDA demonstrate the best performance, reaching ACCs of 0.843. QDA maintained consistent performance across phases. Relevant predictors included reperfusion strategy, TIMI flow before percutaneous coronary intervention (PCI), Killip class, creatinine, and Creatine Kinase Index (CKI)—all parameters routinely assessed in STEMI patients. These models effectively identified patients at risk for post-reperfusion complications and hemodynamic decline, supporting decisions regarding extended monitoring and ICU-level care. Conclusions: Predictive models implemented in advanced STEMI phases can contribute to dynamic, phase-specific risk reassessment and optimize CICU resource allocation. These findings support the integration of ML-based tools into post-PCI workflows, enabling earlier detection of clinical decline and more efficient deployment of intensive care resources. When combined with earlier-stage models, the inclusion of interventional and CICU phases forms a dynamic, end-to-end risk assessment framework. With further refinement, this system could be implemented as a mobile application to support clinical decisions throughout the STEMI care continuum.

Cutaneous squamous scell carcinoma (cSCC) is a frequent non-melanoma skin cancer that originates from keratinocytes with increased prevalence. cSCC can be either in situ, as in Bowen’s disease, or extended. Advanced age, accumulated sun exposure, light pigmentation, and prior skin cancer diagnosis are all significant risk factors for cSCC. Although most cSCCs can be treated surgically, some recur and metastasize, resulting in death. The role of immune status is not yet determined in the prognosis of these patients. Objective. Immunosuppressed patients are more likely to develop cSCC, which is often characterized by more aggressive, multifocal lesions. This study aimed to determine the risks of mortality in patients with cSCC and immunosuppression versus non immunosuppression and to compare variations in overall survival based on different clinical features. Method. We evaluated clinical cases of patients at “Sfantul Apostol Andrei” Emergency Hospital of Galati, Romania, from 1 March 2018 to 1 April 2024. Subjects in the trial had to be at least 18 years old and have a pathologically confirmed diagnosis of cutaneous head and neck squamous cell carcinoma (cHNSCC). We divided the patients into two different categories based on whether they had immunosuppression. Results. In this cohort of 68 subjects with cSCC, patients with immunosuppression had significantly lower overall survival, as well as lower three- and five-year survival rates compared with those without immunosuppression, even after adjustment for age, sex, stage, and previous surgical treatment. The median survival time for immunosuppressed individuals ranged from 11 to 21 months, varying based on their particular characteristics, and most critically, on the presence of other malignancies, while that of immunocompetent patients ranged from 18 to 51 months. In addition, immune-deficient patients with early-stage disease had a 21-month median survival rate that changed to11 months for advanced-stage cases. In a similar manner, immunocompetent patients with early-stage cancer had a significantly better median survival than those withadvancedstages,43 versus 18months. Our results indicate that immunosuppression is a distinct risk factors associated with a less favorable outcome in patients with cHNSCC.