Search Results (42)

Deep vein thrombosis is a condition associated with substantial morbidity and a high risk of pulmonary embolism, underscoring the need for rapid and reliable diagnostic solutions. Although machine learning and deep learning techniques are increasingly being applied for clinical decision support, comprehensive analyses of their contributions to early detection, risk prediction, and monitoring remain limited. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines, we conducted a systematic search in ScienceDirect, IEEE Xplore, Scopus, and Web of Science for studies published between January 2014 and March 2025. Eligible studies applied machine learning or deep learning approaches for the early prediction, monitoring, or risk assessment of deep vein thrombosis, or described reference datasets for algorithm development. Two authors independently extracted data and evaluated methodological quality using the Quality Assessment of Diagnostic Accuracy Studies-2 framework. The included studies were categorized into four domains: Early prediction, monitoring, risk assessment, and reference datasets. In total, 66 studies met the inclusion criteria. Recent advances include deep learning-assisted ultrasound interpretation and real-time implementation of machine learning algorithms. While most studies demonstrated a low overall risk of bias, recurring limitations were identified in terms of patient selection, reporting practices, and validation strategies. Dataset harmonization and external validation were infrequently performed, and documentation of data provenance and class imbalance handling was inconsistent. Machine learning and deep learning approaches demonstrate considerable potential to accelerate accurate diagnoses and facilitate individualized risk stratification; however, their translation into routine practice requires standardized datasets, rigorous external validation, and integration into existing clinical workflows. This review consolidates a decade of research, links methodological quality to clinical applicability, and provides a task-oriented roadmap for advancing machine learning-enabled diagnostics and monitoring in the context of deep vein thrombosis. Full article

Structured illumination microscopy (SIM) with π/2 phase-shift modulation traditionally relies on frequency-domain computation, which greatly limits processing efficiency. In addition, the illumination regime inherent in structured illumination techniques often results in poor visual quality of reconstructed images. To address these dual challenges, this study introduces DM-SIM-LLIE (Differential Low-Light Image Enhancement SIM), a novel framework that integrates two synergistic innovations. First, the study pioneers a spatial-domain computational paradigm for π/2 phase-shift SIM reconstruction. Through system differentiation, mathematical derivation, and algorithm simplification, an optimized spatial-domain model is established. Second, an adaptive local overexposure correction strategy is developed, combined with a zero-shot learning deep learning algorithm, RUAS, to enhance the image quality of structured light reconstructed images. Experimental validation using specimens such as fluorescent microspheres and bovine pulmonary artery endothelial cells demonstrates the advantages of this approach: compared with traditional frequency-domain methods, the reconstruction speed is accelerated by five times while maintaining equivalent lateral resolution and excellent axial resolution. The image quality of the low-light enhancement algorithm after local overexposure correction is superior to existing methods. These advances significantly increase the application potential of SIM technology in time-sensitive biomedical imaging scenarios that require high spatiotemporal resolution. Full article

Fibrotic diseases of the skin and lung, such as systemic sclerosis, hypertrophic scars, keloids, and pulmonary fibrosis, share core molecular mechanisms despite their distinct anatomical settings. Central to their pathogenesis are persistent fibroblast activation, immune dysregulation, ECM remodeling, and failure of resolution pathways, all modulated by an ever-changing environment and epigenetic regulation. Increasing evidence reveals that chronic injury from air pollution, ultraviolet radiation, climate stressors, and occupational hazards accelerates fibroinflammatory remodeling across these barrier organs. Moreover, shared signaling networks, including TGF-β, IL-4/IL-13, Wnt/β-catenin, and epigenetic regulators like miR-21 and miR-29, suggest convergent fibrotic programs may be subject to cross-organ therapeutic targeting. This review integrates recent insights into the exposome’s role in driving fibrosis, highlights novel RNA- and epigenetic-based interventions, and evaluates the repurposing of antifibrotic agents approved for pulmonary disease within dermatologic contexts. We emphasize the emerging concept of fibrosis-aware precision medicine and propose a unifying framework to guide integrated therapeutic strategies. In the face of global climate change and rising environmental insults, a cross-organ perspective on fibrosis offers a timely and translationally relevant approach to addressing this growing burden on human health. Full article

Background: Pulmonary tuberculosis (TB) is increasingly recognized as a risk factor for chronic obstructive pulmonary disease (COPD), but its impact on COPD onset and severity remains poorly characterized, particularly in low- and middle-income countries. This multicenter study aimed to assess the impact of prior pulmonary TB on COPD onset, severity, the timing of the first severe exacerbation, and progression among Romanian patients with and without a history of pulmonary TB. Methods: This retrospective multicenter study included adults hospitalized for their first severe COPD exacerbation at two tertiary care centers in Romania between April 2020 and April 2025. Patients were grouped based on smoking status and prior TB history. Propensity score matching was used to control for confounding factors. Clinical characteristics, spirometry, and radiological TB patterns were analyzed comparatively between patients with prior TB and TB-naïve patients. Results: Among 403 COPD patients, those with prior TB had significantly earlier COPD onset (mean age 48.67 ± 6.42 vs. 65.61 ± 5.14 years in smokers, p < 0.001) and shorter intervals to their first severe COPD exacerbation compared to patients without prior TB (6.35 ± 4.71 vs. 15.14 ± 6.93 years in smokers, p < 0.001). COPD prevalence was higher among TB survivors compared to those without TB history, especially in smokers (OR = 5.73; 95% CI, 3.30–9.94, p < 0.001), versus non-smokers (OR =2.23; 95% CI, 1.37–3.64, p = 0.001). Radiological severity of TB lesions significantly influenced COPD prevalence among smokers (OR = 10.79, p < 0.001). Conclusions: Prior pulmonary TB substantially accelerates COPD onset, exacerbation timing, and disease severity, particularly in smokers. This multicenter comparative study demonstrates that prior pulmonary TB significantly accelerates COPD onset, exacerbation timing, and disease severity, especially among smokers. Recognizing TB history as a significant COPD risk factor underscores the importance of targeted COPD screening and tailored management in populations with high TB prevalence. Full article

Background: Iron deficiency (ID) is a prevalent comorbidity of heart failure (HF), affecting up to 59% of patients, regardless of the presence of anaemia. Although its negative impact on left ventricular (LV) function is well documented, its effect on right ventricular (RV) function remains unclear. This study assessed the effects of ID on RV global longitudinal strain (RV-GLS) in patients diagnosed with acute decompensated HF (ADHF). Methods: This study included data from 100 patients hospitalised with ADHF irrespective of LV ejection fraction (LVEF) value. ID was defined according to the European Society of Cardiology HF guidelines as serum ferritin <100 ng/mL or ferritin 100–299 ng/mL, with transferrin saturation <20%. Anaemia was defined according to World Health Organization criteria as haemoglobin level <12 g/dL in women and <13 g/dL in men. RV systolic function was assessed using parameters including RV ejection fraction (RVEF), tricuspid annular plane systolic excursion (TAPSE), RV fractional area change (FAC), peak systolic tissue Doppler velocity of the RV annulus (RV TDI S′), acceleration time of the RV outflow tract, and RV free wall GLS. Results: The mean (±SD) age of the study population (64% male) was 70 ± 10 years. The median LVEF was 35%, with 66% of patients classified with HF with reduced ejection fraction, 6% with HF with mid-range ejection fraction, and 28% with HF with preserved ejection fraction. Fifty-eight percent of patients had ID. There were no significant differences between patients with and without ID regarding demographics, LVEF, RV FAC, RV TDI S′, or systolic pulmonary artery pressure. However, TAPSE (15.6 versus [vs.] 17.2 mm; p = 0.05) and RV free wall GLS (−14.7% vs. −18.2%; p = 0.005) were significantly lower in patients with ID, indicating subclinical RV systolic dysfunction. Conclusions: ID was associated with subclinical impairment of RV systolic function in patients diagnosed with ADHF, as evidenced by reductions in TAPSE and RV-GLS, despite the preservation of conventional RV systolic function parameters. Further research validating these findings and exploring the underlying mechanisms is warranted. Full article

Emergent phenomena arise from the interaction of competing forces at multiple scale levels, resulting in complex outcomes that are not readily apparent from analyzing the individual components. Regarding biological systems, when a critical threshold is reached, a phase transition occurs, producing a spontaneous system reorganization characterized by recognizable molecular, microscopic, and macroscopic changes. The current paper explores the emergent phenomena underlying the pathogenesis of pulmonary emphysema, a disease characterized by progressive airspace enlargement. The competitive relationship between mechanical strain imposed on alveolar walls and a countervailing increase in elastin crosslinking to prevent alveolar wall rupture leads to airspace enlargement as the balance between these two processes shifts toward increasing lung injury. This phase transition is also accompanied by an accelerated release of peptide-free elastin-specific desmosine crosslinks as the mean alveolar wall diameter begins to increase, suggesting their potential use as a biomarker for the molecular changes that precede the development of pulmonary emphysema. Early detection of the disease would allow more timely therapeutic intervention involving multiple agents that address the complexities of emergent phenomena at different scale levels. Full article

Atrial fibrillation (Afib) recurrence after catheter ablation (CA) remains a significant clinical challenge, driven by a complex and dynamic interplay of structural, electrical, and autonomic mechanisms. While pulmonary vein isolation (PVI) is the cornerstone of CA, recurrence rates remain substantial, highlighting the need to understand the evolving pathophysiology beyond PV reconnection. Post-ablation changes, including inflammation, edema, oxidative stress, and ischemia, create a transient proarrhythmic state that may contribute to early recurrence. Over time, atrial remodeling, fibrosis, and residual autonomic activity further sustain arrhythmogenicity. Additionally, epicardial adipose tissue promotes atrial myopathy, accelerating disease progression, particularly in patients with risk factors such as older age, female sex, obesity, hypertension, obstructive sleep apnea, and heart failure. The multifactorial nature of Afib recurrence underscores the limitations of a “one-size-fits-all” ablation strategy. Instead, a patient-specific approach integrating advanced mapping techniques, multimodal imaging, and computational modeling is essential. Artificial intelligence (AI) and digital twin models hold promise for predicting recurrence by simulating individualized disease progression and optimizing ablation strategies. However, challenges remain regarding the standardization and validation of these novel approaches. A deeper understanding of the dynamic interconnections between the mechanisms driving recurrence is crucial for improving long-term CA outcomes. This review explores the evolving nature of Afib recurrence, emphasizing the need for a precision medicine approach that accounts for the continuous interaction of pathophysiological processes in order to refine patient selection, ablation strategies, and post-procedural management. Full article

Background/Objectives: The prevalence of Achromobacter xylosoxidans is increasing in people with Cystic Fibrosis (pwCF), yet its clinical pathogenicity remains controversial. The objective of this study was to chart the longitudinal prevalence and examine clinical associations before and after infection. Methods: This observational, retrospective study was conducted at a single CF center over a 14-year period. Data were collated from patient charts and clinic databases. Patients with Achromobacter sputum cultures were compared to those without the bacterium and analyzed according to whether they had single, intermittent, or chronic infections. Results: During the study period, an annual average of 124 pwCF were followed up at our clinic, with a median age of 13.6 years (IQR = 7.6–27.7). The Achromobacter detection rate increased from 0 to 6.1%. Twenty-three percent (29/124) of patients had at least one positive culture. The median age at acquisition was 17 years (IQR = 14.5–33). At the time of acquisition, the median FEV₁ was 81% (IQR = 46–94), compared to 90% (IQR = 72–99) for patients without Achromobacter, p < 0.001. Patients with Achromobacter tended to demonstrate more chronic Pseudomonas (55% vs. 27%, p = 0.06) and pancreatic insufficiency (66% vs. 47%, p = 0.07). At two years post-acquisition, the median FEV₁ for patients with intermittent and chronically infected decreased by 11.5% (IQR = −3.75–7.5), compared to 1.5% (IQR = −2.5–12.5) for those with a single positive culture, p = 0.03. Similarly, pulmonary exacerbations per year became more frequent post-acquisition in intermittent and chronically infected patients: Median (range) 2.5 (0–8) pre-, versus 3.0 (0–9) post-acquisition, p = 0.036. Conclusions: Chronic and intermittent infection with Achromobacter were associated with accelerated lung function decline and increased exacerbation frequency. Larger prospective studies are needed to confirm these findings and examine the effect of eradication on the clinical course. Full article

(1) Background: There are little data about the differences in clinical and echocardiographic characteristics between elderly (aged ≥ 65 years) and younger patients with acute pulmonary embolism (PE). (2) Methods: Consecutive patients diagnosed with PE in a tertiary hospital were identified. Clinical characteristics, biomarkers and transthoracic echocardiography indices including right ventricular free wall longitudinal strain (RV-FWLS) were recorded. (3) Results: Of 200 patients enrolled, 19 patients had high-risk PE and were excluded from the study. Compared to younger patients, elderly patients with PE had less frequently pain and typical symptoms and more often were hospitalized due to another reason before the PE diagnosis. The elderly had higher values of D-dimer, high-sensitivity troponin I and brain natriuretic peptide (BNP). Echocardiographic differences were noted and the elderly had lower values of pulmonary vascular acceleration time, RV E/A ratio and lower tricuspid annular plane systolic excursion/pulmonary artery systolic pressure ratio. The RV-FWLS index did not show a statistically significant difference in distribution between age groups ≥ 65 and <65 years old. The RV diameter was similar across all age groups. (4) Conclusions: The elderly have differences compared with younger patients with PE regarding the mode of presentation, the values of biomarkers like D-dimer, BNP and troponins and some echocardiographic indices of RV affection. Full article

Background/Objectives: Pulmonary arterial hypertension (PAH) and chronic thromboembolic pulmonary hypertension (CTEPH) are complex diseases that require precise diagnosis and management. The ESC risk score has been used in both conditions. We assessed the relationship between the EmPHasis-10 questionnaire (patient subjective evaluation) and objective assessment using endorsed tools (simplified four-strata risk assessment and right ventricular imaging by transthoracic echocardiography). Methods: The present study retrospectively extracted data from 40 adult patients (27 PAH and 13 CTEPH cases) diagnosed in a single center in Romania. The EmPHasis-10 questionnaire and the four-strata risk assessment (FSRA) tool were applied to each patient. Mean pulmonary artery pressure (mPAP), tricuspid annular plane systolic excursion (TAPSE), TAPSE/systolic pulmonary artery pressure (TAPSE/sPAP) ratio, and right ventricular outflow tract acceleration time (RVOT-AT) were assessed. Results: A significant correlation was observed between the EmPHasis-10 scores and the FSRA tool, the WHO functional class, and the 6 min walking distance. Emphasis-10 score did not correlate with any of the echocardiographic parameters. The FSRA tool showed a moderate positive correlation with mPAP (r = 0.42, p = 0.01) and a negative correlation with TAPSE (r = −0.46, p = 0.003); additionally, across the entire cohort, it was moderately negatively correlated with both RVOT-AT (r = −0.42, p = 0.01) and TAPSE/sPAP ratio (r = −0.43, p = 0.005). Conclusions: Our study evidenced the alignment between EmPHasis-10 scores and prognostic risk score, with poorer health-related quality of life corresponding to higher FSRA. The EmPHasis-10 questionnaire proves to be a valuable, easy-to-use instrument, offering meaningful insights into patients’ health-related quality of life, underscoring its utility in enhancing comprehensive patient assessment and management. Full article

Background/Objectives: Surgical pneumoperitoneum (PP) significantly impacts volume-controlled ventilation, characterized by reduced respiratory compliance, elevated peak inspiratory pressure, and an accelerated expiratory phase due to an earlier onset of the airway pressure gradient. We hypothesized that this would shorten expiratory time, potentially increasing expiratory flow rate compared to pneumoperitoneum conditions. Calculations were performed to establish correlations between respiratory parameters and the mean increase in expiratory flow rate relative to baseline. Methods: Mechanical ventilation parameters were recorded for 67 patients both pre- and post-PP. Ventilator settings were standardized with a tidal volume of 6 mL/kg, a respiratory rate of 12 breaths per minute, a PEEP of 3 cmH₂O, an inspiratory time of 2 s, and an inspiratory-to-expiratory ratio of 1:1.5 (I:E). Results: The application of PP increased both peak inspiratory pressure and mean expiratory flow rate by 28% compared to baseline levels. The elevated intra-abdominal pressure of 20 cmH₂O resulted in a 34% reduction in dynamic chest compliance, a 50% increase in elastance, and a 20% increase in airway resistance. The mean expiratory flow rate increments relative to baseline showed a significant negative correlation with elastance (p = 0.0119) and a positive correlation with dynamic compliance (p = 0.0028) and resistance (p = 0.0240). Conclusions: A PP of 20 cmH₂O resulted in an increase in the mean expiratory flow rate in the conventional I:E ratio in the volume-ventilated mode. PP reduces lung and chest wall compliance by elevating the diaphragm, compressing the thoracic cavity, and increasing airway pressures. Consequently, the lungs and chest wall stiffen, requiring greater ventilatory effort and accelerating expiratory flow due to increased airway resistance and altered pulmonary mechanics. Prolonging the inspiratory phase through I:E ratio adjustment helps maintain peak inspiratory pressures closer to baseline levels, and this method enhances the safety and efficacy of mechanical ventilation in maintaining optimal respiratory function during laparoscopic surgery. Full article

Background/Objective: This study aims to utilize advanced artificial intelligence (AI) image recog-nition technologies to establish a robust system for identifying features in lung computed tomog-raphy (CT) scans, thereby detecting respiratory infections such as SARS-CoV-2 pneumonia. Spe-cifically, the research focuses on developing a new model called Residual-Dense-Attention Gates U-Net (RDAG U-Net) to improve accuracy and efficiency in identification. Methods: This study employed Attention U-Net, Attention Res U-Net, and the newly developed RDAG U-Net model. RDAG U-Net extends the U-Net architecture by incorporating ResBlock and DenseBlock modules in the encoder to retain training parameters and reduce computation time. The training dataset in-cludes 3,520 CT scans from an open database, augmented to 10,560 samples through data en-hancement techniques. The research also focused on optimizing convolutional architectures, image preprocessing, interpolation methods, data management, and extensive fine-tuning of training parameters and neural network modules. Result: The RDAG U-Net model achieved an outstanding accuracy of 93.29% in identifying pulmonary lesions, with a 45% reduction in computation time compared to other models. The study demonstrated that RDAG U-Net performed stably during training and exhibited good generalization capability by evaluating loss values, model-predicted lesion annotations, and validation-epoch curves. Furthermore, using ITK-Snap to convert 2D pre-dictions into 3D lung and lesion segmentation models, the results delineated lesion contours, en-hancing interpretability. Conclusion: The RDAG U-Net model showed significant improvements in accuracy and efficiency in the analysis of CT images for SARS-CoV-2 pneumonia, achieving a 93.29% recognition accuracy and reducing computation time by 45% compared to other models. These results indicate the potential of the RDAG U-Net model in clinical applications, as it can accelerate the detection of pulmonary lesions and effectively enhance diagnostic accuracy. Additionally, the 2D and 3D visualization results allow physicians to understand lesions' morphology and distribution better, strengthening decision support capabilities and providing valuable medical diagnosis and treatment planning tools. Full article

Previous experimental findings have led to considerable interest in the beneficial effects on pulmonary hypertension (PH) produced by sildenafil and in the pleiotropic effects of rosuvastatin and their positive role in the process of pulmonary angiogenesis. However, magnesium sulfate, the most abundant intracellular cation, is essential in vascular endothelial functionality due to its anti-inflammatory and vasodilatory effects. Therefore, the present study aims to assess these treatment regimens and how they could potentially provide some additional benefits in PH therapy. Fourteen days after chronic-hypoxia PH was induced, rosuvastatin, sildenafil and magnesium sulfate were administered for an additional fourteen days to male Wistar rats. The Fulton Index, right ventricle (RV) anterior wall thickness, RV internal diameter and pulmonary arterial (PA) acceleration time/ejection time were evaluated, and another four biochemical parameters were calculated: brain natriuretic peptide, vascular endothelial growth factor, nitric oxide metabolites and endothelin 1. The present study demonstrates that sildenafil and rosuvastatin have modest effects in reducing RV hypertrophy and RV systolic pressure. The drug combination of sildenafil + rosuvastatin + magnesium sulfate recorded statistically very highly significant results on all parameters; through their positive synergistic effects on vascular endothelial function, oxidative stress and pathological RV remodeling, they attenuated PH in the chronic hypoxia pulmonary hypertension (CHPH) rat model. Full article

Our research evaluates advanced artificial (AI) methodologies to enhance diagnostic accuracy in pulmonary radiography. Utilizing DenseNet121 and ResNet50, we analyzed 108,948 chest X-ray images from 32,717 patients and DenseNet121 achieved an area under the curve (AUC) of 94% in identifying the conditions of pneumothorax and oedema. The model’s performance surpassed that of expert radiologists, though further improvements are necessary for diagnosing complex conditions such as emphysema, effusion, and hernia. Clinical validation integrating Latent Dirichlet Allocation (LDA) and Named Entity Recognition (NER) demonstrated the potential of natural language processing (NLP) in clinical workflows. The NER system achieved a precision of 92% and a recall of 88%. Sentiment analysis using DistilBERT provided a nuanced understanding of clinical notes, which is essential for refining diagnostic decisions. XGBoost and SHapley Additive exPlanations (SHAP) enhanced feature extraction and model interpretability. Local Interpretable Model-agnostic Explanations (LIME) and occlusion sensitivity analysis further enriched transparency, enabling healthcare providers to trust AI predictions. These AI techniques reduced processing times by 60% and annotation errors by 75%, setting a new benchmark for efficiency in thoracic diagnostics. The research explored the transformative potential of AI in medical imaging, advancing traditional diagnostics and accelerating medical evaluations in clinical settings. Full article

Background and Objectives: Pulmonary hypertension (PH) is a clinical condition with high mortality rates, particularly in patients over 65. Current guidelines recommend assessing the likelihood of pulmonary hypertension (LPH) using advanced echocardiography before proceeding to right heart catheterization. This study proposed using the common femoral vein (CFV), an accessible vein that reflects right atrial pressure, as an alternative method to assess the high likelihood of pulmonary hypertension (H-LPH). Materials and Methods: This prospective observational study included 175 emergency patients from three hospitals. Ultrasound assessed the pulsed wave Doppler (PW-Doppler) morphology of the CFV. This diagnostic yield for H-LPH was evaluated alongside traditional ultrasound parameters (right-to-left ventricular basal diameter ratio greater than 1 (RV > LV), septal flattening, right ventricular outflow acceleration time (RVOT) of less than 105 ms and/or mesosystolic notching, pulmonary artery diameter greater than the aortic root (AR) diameter or over 25 mm, early pulmonary regurgitation maximum velocity > 2.2 m/s; TAPSE/PASP less than 0.55, inferior vena cava (IVC) diameter over 21 mm with decreased inspiratory collapse, and right atrial (RA) area over 18 cm²). Results: The CFV’s PW-Doppler cardiac pattern correlated strongly with H-LPH, showing a sensitivity (Sn) of 72% and a specificity (Sp) of 96%. RA dilation and TAPSE/PASP < 0.55 also played significant diagnostic roles. Conclusions: The CFV’s PW-Doppler cardiac pattern is an effective indicator of H-LPH, allowing reliable exclusion of this condition when absent. This approach could simplify initial LPH evaluation in emergency settings or where echocardiographic resources are limited. Full article