Search Results (44,817)

Deep learning is increasingly integrated into oral rehabilitation workflows, particularly in implant planning, prosthodontic design automation, and peri-implant diagnosis. However, reported performance is heterogeneous and difficult to compare across tasks, modalities, and validation designs. The goal of this study was to critically analyze deep learning architecture families applied to oral rehabilitation and to provide task-driven selection guidance supported by an evidence table reporting dataset characteristics, validation strategy, and performance metrics. A focused narrative review was conducted using transparent, database-specific search criteria (final n = 10 included studies), emphasizing implant planning (cone–beam computed tomography [CBCT]-based segmentation), prosthodontic design (intraoral scan [IOS]/mesh inputs), and peri-implant diagnosis (periapical/panoramic radiographs). Evidence certainty for each clinical task was assessed using GRADE-informed ratings (High/Moderate/Low/Very Low). Extracted variables included clinical task, imaging modality, dataset size, architecture, validation strategy (internal vs. internal + external), split level, ground truth protocol, and performance metrics. A structured computational and hardware feasibility analysis was conducted for each architecture family to support real-world deployment planning. Encoder–decoder networks (U-Net/nnU-Net) dominate CBCT segmentation for implant planning, while detection architectures (Faster R-CNN, YOLO) support implant localization and peri-implant assessment on radiographs. Generative models (3D GANs, transformer-based point-to-mesh networks) enable crown design from three-dimensional scans. Hybrid CNN–Transformer architectures show promise for multimodal CBCT–IOS fusion, though direct evidence from the included studies remains limited to a single study. External validation remains uncommon yet essential given the risk of domain shift. In conclusion, architecture selection should be anchored to task geometry (2D vs. 3D), artifact burden, and required clinical output type. Reporting standards should prioritize dataset transparency, validation rigor, multi-center external testing, and uncertainty-aware outputs. Full article

Background: Cervicofacial actinomycosis is an uncommon chronic bacterial infection that can mimic neoplasia or granulomatous disease because of its infiltrative presentation. Diagnosis is often delayed, particularly in pregnant patients in whom imaging and invasive procedures may be limited. Case report: A 25-year-old woman at 14 weeks of gestation presented with a multiple-fistulized cervical mass. The lesion was initially diagnosed as a cutaneous furuncle in a private dermatology practice and treated with topical therapy, resulting in only transient improvement. Two weeks later, multiple fistulizations developed, prompting consultation in the emergency department. ENT assessment and ultrasound raised suspicion of cervical actinomycosis versus fistulized tuberculous lymphadenitis. Considering the pregnancy, drainage of the collection was performed under local anesthesia and empiric antibiotic therapy with amoxicilin-clavulanic acid was started. Microbiological confirmation of Actinomyces (Schaalia) georgiae led to infectious disease evaluation that established a long-term antibiotic therapy while monitoring fetal safety. Progressive clinical improvement was observed, with complete resolution after three months. The pregnancy progressed without complications and fetal morphology remained normal under therapy. Conclusions: This case illustrates the diagnostic complexity of cervicofacial actinomycosis caused by A. georgiae during pregnancy, representing the first such report in the current literature, and emphasizes the need for a multidisciplinary approach. Full article

Background: Breast cancer-related lymphedema (BCRL) is one of the most debilitating long-term morbidities after axillary lymph node dissection (ALND), severely impairing quality of life through reduced mobility, independence, and chronic burden, especially in older women. Axillary reverse mapping (ARM) aims to preserve upper extremity lymphatics while maintaining oncologic safety. Evidence in older adult populations with long-term follow-up remains limited. Methods: This retrospective cohort study included 138 female patients (median age 72.5 years) undergoing ALND for invasive breast cancer between January 2018 and January 2024. Patients were divided into ARM (n = 72) and non-ARM (n = 66) groups. BCRL was graded 0–3 according to adapted International Society of Lymphology (ISL) criteria (2013 consensus document). Assessments were performed preoperatively and at 3, 6, 12, 24, 36, 48, and 60 months using blinded circumference measurements and bioimpedance spectroscopy. Results: Baseline characteristics were comparable. Mean follow-up was 46.5 ± 8.8 months. Clinically relevant BCRL (Grades 2–3) was dramatically lower in the ARM group (18.1% vs. 60.6%, p < 0.0001), while subclinical changes (Grade 1) were similar (31.9% vs. 27.3%, p = 0.55). Kaplan–Meier analysis showed significantly better clinically relevant lymphedema-free survival with ARM (log-rank p = 0.00019), with curve separation after 30–40 months—indicating a sustained long-term benefit for quality of life in this frail population. Recurrence rates were comparable (8.3% vs. 10.6%, p = 0.776). Multivariable Cox regression confirmed ARM as an independent protective factor (adjusted HR 0.22, 95% CI 0.11–0.44, p < 0.0001). Conclusions: In older women with breast cancer, ARM significantly reduces clinically relevant lymphedema—a major determinant of long-term quality of life—without compromising oncologic safety. These findings support the routine consideration of ARM during ALND to preserve upper-extremity function, mobility, and independence in this vulnerable population, thereby balancing aggressive oncologic treatment with enhanced long-term quality of life and reduced treatment-related morbidity. Full article

Background: Perioperative cardiovascular risk assessment remains challenging in non-cardiac surgery, particularly in older patients and those with multiple comorbidities. Traditional models rely largely on clinical history and may not fully reflect current cardiovascular functional status. This study aimed to derive and assess the apparent performance of a new composite score, PERFORM-CV, integrating clinical, laboratory, and echocardiographic data. Methods: We conducted a prospective two-center cohort study including 503 non-cardiac surgical patients with cardiovascular comorbidity. The Revised Cardiac Risk Index (Lee/RCRI) and the AUB-HAS2 index were calculated according to their original published definitions as raw point totals ranging from 0 to 6; without additional normalization. The PERFORM-CV score was derived from univariable and multivariable analyses, with continuous predictors dichotomized using ROC-derived thresholds. Results: Emergency admission, chronic heart failure, and elevated serum creatinine remained independently associated with in-hospital mortality. Lower left ventricular ejection fraction, lower mitral annular plane systolic excursion (MAPSE), lower hemoglobin, and atrial fibrillation also contributed to the final composite score. ROC analysis showed good discrimination for PERFORM-CV (AUC 0.852; 95% CI 0.806–0.897; p < 0.001), comparable to Lee/RCRI (AUC 0.860; 95% CI 0.818–0.901; p < 0.001) and higher than AUB-HAS2 (AUC 0.779; 95% CI 0.731–0.826; p < 0.001). Conclusions: PERFORM-CV showed good apparent discrimination in the derivation cohort and may complement established bedside risk tools by incorporating echocardiographic and laboratory data. The ROC-derived thresholds should be interpreted as data-driven derivation cut-offs; resampling-based internal validation and external validation are required before broader clinical use. Full article

Background: Subarachnoid hemorrhage (SAH) has high mortality and disability rates. The timely and precise assessment of SAH severity is of critical importance in predicting life-threatening complications. Several CT-based radiological grading systems have been proposed, but a comprehensive meta-analysis of their inter-rater reliability (IRR) has not been conducted. Methods: This study followed the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Two authors performed a systematic search of original articles in the PubMed database. Methodological quality of the studies was assessed using the Quality Appraisal of Reliability Studies (QAREL). Meta-analyses of Cohen’s kappa and intra-class correlation coefficient (ICC) were performed using R packages “metafor” and “meta”. Results: A systematic literature analysis was performed for twenty articles that met the inclusion criteria. The methodological quality was moderate in 14 of 20 studies; five studies were of low quality. Only eight articles were suitable for meta-analysis. Cohen’s kappa of the binarized Fisher scale was 0.85 (95% CI 0.70–0.93), though it was based on only two studies and 109 patients. The Hijdra scale had an ICC of 0.75 (95% CI 0.29–0.93). The original and modified Graeb scales proposed for the assessment of concomitant intra-ventricular hemorrhage demonstrated ICC of 0.83 (95% CI 0.59–0.94) and 0.93 (95% CI 0.84–0.97), respectively. For other scales, meta-analysis was not possible due to incomplete reporting or single evaluations. Conclusions: The current evidence on IRR of radiological grading scales for SAH is limited, emphasizing the need for further high-quality research to validate their reliability and clinical applicability. Full article

Background and Objectives: The prioritization of intensive care unit (ICU) admission following surgery for cancer is controversial. There is an urgent need to develop an appropriate clinical predictive model to aid in making ICU admission decisions after surgery. Materials and Methods: Four model strategies were used to build post−operative ICU admission predictive models: SVM, Catboost, ANN, and KNN. Internal verification was used for model evaluation at a ratio of 7:3. The area under the curve (AUC) value, calibration plots, and decision curve analysis were employed to assess the performance and clinical usefulness of the model. Results: The ICU group of patients with cancer who underwent surgery showed better prognosis for disease−free survival (DFS, p = 0.0008) and overall survival (OS, p < 0.0001). Cox multivariate analyses validated that lower baseline RBC, LDH, and CRP; higher baseline ALB, LCR, and lower post−operative LDH; higher post−operative HCT and ApoA−I; and higher fluctuating MCH independently predicted better DFS and OS (all p < 0.05). The AUC of the Catboost model was superior to that of the other models in the training cohort and internal validation cohort. Calibration plot and decision curve analysis indicated that the Catboost model possessed the best performance, with higher clinical utility, compared with other models. Conclusions: ICU admission after surgery was associated with superior survival in patients with cancer. The cost−effective Catboost model has promising clinical application but requires further clinical evaluation. Unravelling the cellular and molecular foundation of ICU admission might enable the development of more practical life−support strategies. Full article

In the biodegradable metal class, Mg-based alloys are considered the most promising candidates for temporary implant manufacture. However, their high corrosion rate in physiological media is considered a main drawback for clinical translation. Conversion coatings address the limitations of Mg-based alloys and provide a strategy to control corrosion and improve surface biocompatibility. In this review paper, a detailed analysis of various conversion coating techniques, including ceramic conversion coatings based on metals, polymeric conversion coatings, bioactive conversion coatings, and hybrid conversion coatings, is performed. Attention is devoted to the corrosion process and parameters, as well as to the biological response in relation to bioactivity or biocompatibility. The main angiogenic and osteogenic signaling pathways are described based on the analyzed conversion coatings, and the evolution of the cellular response is estimated. Although significant progress has been made in the field, there are still challenges associated with synchronizing Mg alloy degradation with new bone formation and with precisely guiding cell signaling responses to achieve a desired biological response. An overall conclusion of the paper consists of the fact that conversion coatings are an important topic, as they can enhance the surface of Mg-based alloys, making them prone to clinical translation. Full article

Background: Chronic kidney disease (CKD) is associated with increased cardiovascular morbidity and mortality, even at early stages. Postmenopausal women represent a particularly vulnerable population due to estrogen deficiency, which promotes adverse cardiovascular remodeling. However, data specifically characterizing the cardiac phenotype of hypertensive postmenopausal women with mild-to-moderate CKD remain limited. Methods: We conducted a prospective observational cohort study including 413 hypertensive postmenopausal women consecutively referred to a tertiary center between 2019 and 2022. Participants were stratified into a CKD group with stage 3 CKD (estimated glomerular filtration rate of 30–59 mL/min/1.73 m²; n = 213) and a control group without CKD (n = 200). All subjects underwent comprehensive clinical evaluation, laboratory testing, and standardized transthoracic echocardiography. The prevalence of left ventricular hypertrophy (LVH), left ventricular diastolic dysfunction (LVDD), and chronic coronary syndromes (CCS) was assessed. Multivariable logistic regression analyses were performed to evaluate independent associations between CKD and cardiovascular abnormalities. Results: Compared with controls, women with CKD showed a significantly higher prevalence of LVH (46.7% vs. 21.5%), LVDD (55.8% vs. 36.0%), and CCS (15.5% vs. 7.5%) (all p < 0.01). The coexistence of LVH and LVDD identified a high-risk cardiac phenotype that was markedly more frequent in the CKD group (41.3% vs. 12.5%). After adjustment for age, body mass index, blood pressure, duration of hypertension, smoking status, and antihypertensive therapy, stage 3 CKD remained independently associated with LVH, LVDD, and CCS. Conclusions: In hypertensive postmenopausal women, mild-to-moderate CKD is associated with a substantial burden of cardiac structural and functional abnormalities exceeding that attributable to hypertension alone, supporting early cardiovascular screening and an integrated cardiorenal approach. Full article

Background/Objectives: Regadenoson is increasingly used as a vasodilator stress agent for perfusion cardiac magnetic resonance (CMR) imaging due to its favorable pharmacologic profile. However, its long-term prognostic value in patients with myocardial ischemia remains insufficiently established. Methods: We retrospectively analyzed all regadenoson stress-CMR studies performed at our institution between May 2017 and July 2020, including patients with follow-up longer than three months. Inducible ischemia and late gadolinium enhancement (LGE) were assessed using standardized criteria. The primary composite endpoint included cardiovascular death, non-fatal myocardial infarction, late coronary revascularization (≥3 months after CMR), or hospitalization for unstable angina. Event-free survival was analyzed with Kaplan–Meier curves, and prognostic factors were evaluated using a Fine–Gray competing-risks model. Results: Of 705 examinations, 698 were eligible, and 517 patients (78.5%) completed follow-up over a median of 1.93 years (IQR 1.37–2.79). Inducible ischemia was identified in 142 patients (27.5%). During follow-up, 38 composite events occurred. Event incidence was significantly higher in patients with ischemia (109.6 events/1000 person-years; 95% CI 75.7–158.7) than in those without (13.3 events/1000 person-years; 95% CI 7.2–24.7; RR 8.25; 95% CI 4.01–16.98; p < 0.001). In multivariable analysis, inducible ischemia independently predicted adverse outcomes (HR 4.50; 95% CI 1.86–10.9; p = 0.001), whereas LGE was not independently associated (HR 1.28; 95% CI 0.46–3.57; p = 0.63). Conclusions: Regadenoson stress-CMR provides robust medium-term risk stratification in patients with suspected or known coronary artery disease. Detection of inducible ischemia strongly predicts major cardiovascular events, underscoring its prognostic and clinical relevance. Full article

Background: Obstructive sleep apnea (OSA) is a significant cardiovascular risk factor, frequently co-existing with systemic hypertension. While the association between OSA and blood pressure elevation is well documented, its specific prevalence and impact among patients with resistant hypertension remain a critical area of clinical investigation. Objective: The primary aim of this study was to evaluate the prevalence and severity of obstructive sleep apnea (OSA) specifically within a cohort of patients with resistant hypertension (RHT). Additionally, we sought to identify the clinical and anthropometric factors that distinguish RHT patients with OSA from non-resistant hypertensive and normotensive controls, thereby clarifying the increased hypoxic burden and polysomnographic differences unique to this high-risk population. Methods: A total of 300 patients presenting with OSA symptoms were included. Participants were classified into three groups: Group 0 (n = 100), normotensive individuals; Group 1 (n = 100), non-resistant hypertension; and Group 2 (n = 100), confirmed resistant hypertension. Standard overnight polysomnography (PSG) was performed on all participants. Demographic data, comorbidities, anthropometric measurements, and PSG parameters were recorded and compared across groups. Results: Of the subjects, 50.3% were female (sex), and the mean age was $49.5 \pm 12.3$ years. Patients with RHT (Group 2) were significantly older and had a higher prevalence of diabetes mellitus. OSA prevalence was 94% in Group 2 (37% severe), 89% in Group 1 (22% severe), and 74% in Group 0 (only 2% severe). In PSG analysis, AHI and ODI values were significantly higher in hypertensive groups (Groups 1 and 2) compared to normotensive individuals (Group 0), while minimum and mean oxygen saturations were significantly lower. Conclusions: OSA is both more prevalent and more severe in patients with resistant hypertension. Furthermore, hypertensive OSA patients are characterized by an increased hypoxic load compared to normotensives. Systematic investigation and detailed polysomnographic evaluation of OSA are of paramount importance in hypertensive individuals, particularly those with resistant hypertension. Full article

Background: Pneumonia of unknown etiology (PUE), defined as pneumonia cases without an identified pathogen at the time of clinical presentation, represents a critical clinical warning signal for emerging infectious disease (EID) outbreaks with pandemic potential. Yet, conventional pathogen-centric surveillance systems suffer from an inherent blind spot: they cannot detect early clustering signals before the causative agent is identified, creating a window of vulnerability during novel pathogen emergence. To address this gap, this study aims to develop a deep learning model that leverages unstructured chest imaging text—a routinely available clinical data stream—to enable real-time, automated screening of PUE cases and early warning of EID clusters, independent of prior pathogen knowledge, within an integrated multi-pathogen surveillance framework. Methods: We retrospectively collected data from 8860 patients with respiratory illnesses at a tertiary hospital in Beijing, China, including 980 PUE cases (11.1%) and 7880 known-etiology pneumonia cases. A deep learning model (RoBERTa with attention enhancement) was developed using unstructured chest imaging reports. The Matthews correlation coefficient (MCC) curve was employed to determine the optimal decision threshold. Model performance was assessed for PUE case identification and clustering signal detection on a test set. Results: The model achieved an area under the receiver operating characteristic curve of 0.986 (95% CI: 0.981–0.991). At the optimal threshold of 0.08, selected by maximizing the Matthews correlation coefficient (MCC)—a balanced metric that accounts for all four confusion matrix outcomes—sensitivity was 89.8%, and specificity was 97.0% for identifying PUE cases. In a simulated surveillance exercise, the model showed a high correlation between the predicted and actual case counts (Pearson’s r = 0.901), suggesting its potential to detect abnormal clustering signals prior to pathogen identification. Conclusions: The developed model demonstrates potential to detect clustering signals of PUE caused by unknown pathogens and can be integrated with hospital information systems, providing a feasible, low-cost tool for integrated surveillance of pathogens with pandemic potential. This approach enables earlier outbreak detection and supports public health decision-making during the critical window before pathogen identification. Full article

Sleep quality is closely associated with cardiovascular, metabolic, and mental health outcomes, yet the clinical gold standard, polysomnography (PSG), is costly and intrusive for long-term home monitoring. Ballistocardiography (BCG) enables unobtrusive in-bed sensing and is therefore attractive for low-burden sleep assessment in natural environments. However, most existing BCG studies are PSG-referenced and mainly focus on sleep staging, while movement and out-of-bed episodes are often treated as artifacts rather than modeled jointly. In this study, we propose an interpretable unsupervised proxy-state modeling framework for three-state in-bed monitoring from BCG signals under an unlabeled setting. BCG recordings were segmented into 30 s windows with 50% overlap, and multi-domain features were extracted from waveform morphology, spectral power, heart rate-related dynamics, and wavelet energy distribution. K-means clustering (K = 3) was used to construct cluster-derived proxy labels, TreeSHAP-based feature ranking together with inner-CV-guided Top-N subset selection was used for training-only feature screening, and multiple classifiers were compared under a strict leave-one-subject-out protocol, with an ROA-optimized RBF-SVM achieving the best overall performance. Using data from 32 volunteers, the framework achieved an accuracy of 0.9932 ± 0.0047 (mean ± SD), together with consistently strong Macro-F1 and MCC scores. Overall, it outperformed the alternative methods compared in this study. Full article

Background/Objectives: Chronic diseases pose a major challenge for healthcare systems, requiring integrated, patient-centered approaches that combine clinical management, prevention, and self-care. Lifestyle Medicine (LM) and lifestyle in general offers complementary frameworks to address these needs. However, the potential integration of LM within community nursing—particularly through the role of Family and Community Nurse (FCN)—has not been comprehensively synthesized. This narrative review aimed to synthesize international evidence on the role of community nursing—particularly FCN—in integrating chronic care management and LM view. Methods: For quality assessment, a narrative review was conducted in accordance with the SANRA criteria to enable the integration of heterogeneous evidence and a comprehensive synthesis of this complex topic. Literature searches were performed in the PubMed–Medline database, and the final screening of references from included studies was used to identify relevant manuscripts. Primary studies published in English over the past ten years were screened and analyzed using the PICOS framework. Sixteen eligible studies were included in the final synthesis. Results: The included studies indicated that nurse-led community interventions in LM view were associated with improvements in self-management, treatment adherence, and selected clinical outcomes, such as blood pressure, glycated hemoglobin, and physical activity levels. Empowerment-based approaches and the use of digital or telehealth tools supported patient engagement and health literacy. At the organizational level, multidisciplinary collaboration, shared protocols, and professional leadership emerged as key factors in sustaining continuity and quality of care, while organizational fragmentation and limited training in behavioral counseling were commonly reported barriers. Conclusions: Community nursing, particularly through FCNs, plays a relevant role in integrating chronic care management and LM approaches, contributing to improved self-management, treatment adherence, and selected clinical outcomes. The evidence highlights the importance of empowerment-based interventions, digital support tools, and multidisciplinary collaboration in enhancing care continuity and patient engagement. Addressing organizational barriers and strengthening behavioral counseling training remain essential to support effective implementation in community settings. Full article