Diagnostic accuracy in dermatology requires both visual expertise and metacognitive skills such as confidence, calibration, and decision-making under uncertainty. Miscalibration may lead to diagnostic error, unnecessary testing, and unsafe management. Assess how confidence, response time, and decision behavior vary across levels of dermatologic experience and how these factors relate to diagnostic accuracy and efficiency. This cross-sectional study included 68 participants (medical students, resident physicians, and board-certified dermatologists) who completed a multiple-choice diagnostic task with 50 diverse dermatologic images. Participants selected a diagnosis option, rated their confidence, and decided regarding additional inspection. Diagnostic accuracy and confidence increased with experience. Board-certified dermatologists were most accurate when responding quickly, but not after longer deliberation, which did not hold true for residents. Medical students displayed significant overconfidence and poor alignment between confidence and decisions. Across all groups, 12% of melanomas were dismissed/overlooked. Small sample size limits subgroup comparisons. A simulated setting may not fully capture clinical complexity. Metacognitive skills differ by experience and influence diagnostic accuracy and efficiency. Training should support calibration and adaptive decision-making.

Diagnostic accuracy of superior vena cava variability by transthoracic echocardiography as a fluid responsiveness predictor in critically ill patients.

NRS2002 outperforms GNRI and PG-SGA SF in GLIM-based malnutrition identification among elderly patients with gastrointestinal malignancy: A multicenter diagnostic study with calibration and net benefit assessment.

Artificial Intelligence-assisted Diagnosis of Carotid Artery Calcifications on Panoramic Radiographs: A Meta-analysis.

Depression is common yet underdiagnosed in patients receiving renal replacement therapies (RRT). Several questionnaires have shown utility for depression screening, mainly among in-centre haemodialysis patients; however, no instruments have been evaluated for diagnostic accuracy in home dialysis or kidney transplant populations. This study aimed to assess the diagnostic performance of the Beck Depression Inventory-Second Edition (BDI-II), the Beck Depression Inventory-Fast Screen (BDI-FS), and the Depression Subscale of the Hospital Anxiety and Depression Scale (HADS-D) across RRT modalities and to identify the most efficient tool for clinical use. Adult patients across RRT modalities completed the BDI-II, BDI-FS, and HADS-D, and were evaluated with the Structured Clinical Interview as the reference standard. Among the 203 included patients (mean age 67.3years; 65% male), 18.2% met SCID-I criteria for depression. Optimal cut-offs were BDI-II ≥15 for in-centre haemodialysis and≥16 for home dialysis and transplantation; BDI-FS ≥3 for in-centre and home dialysis and≥4 for transplantation; and HADS-D≥5 for in-centre haemodialysis and≥6 for home dialysis and transplantation. Sensitivity and negative predictive values exceeded 90% for all instruments except the HADS-D, which showed lower sensitivity in transplanted (86.7%) and home dialysis patients (70%). The BDI-II, BDI-FS, and HADS-D are useful for depression screening in renal populations, though the HADS-D demonstrated reduced performance in home dialysis. Standard cut-offs were inadequate, and modality-specific thresholds improved diagnostic accuracy. The BDI-FS, combining strong accuracy with brevity and ease of use, emerged as the most efficient tool for routine screening across RRT modalities.

Utilization of Current ACC/AHA Genetic Testing Recommendations for Thoracic Aortic Disease at a Large Adult Aortic Center.

Target product profile to guide development of next generation diagnostic test for Salmonella enterica: Responding to the crisis of drug resistant typhoid.

Use of minimum and maximum pretest probabilities to conclude with confidence after obtaining a diagnostic test result.

A host-protein test's diagnostic accuracy for discriminating bacterial from viral infections [MeMed BV (MMBV)] was established at emergency departments and urgent care settings. We determined its performance in children postadmission and in subcohorts stratified according to timing of the blood draw. We analyzed postadmission MMBV data from children (3 months to 17 years) with suspected acute infections recruited across 5 previous studies. MMBV results were interpreted as bacterial/viral/equivocal according to the manufacturer's instructions. Reference standard infection etiology was as assigned in the original studies, where adjudicators were provided comprehensive patient data but blinded to MMBV. We calculated diagnostic performance by comparing MMBV to the reference standard. The study population comprised 1059 children, encompassing 659 patients sampled on admission day (day = 0), 69 patients sampled on day ≥1 of hospital stay and 331 with blood drawn postadmission without recorded timing. Median age was 1.9 years (interquartile range 1.0, 4.0), with 51.5% males. The most prevalent discharge diagnoses were systemic viral infections (29.7%), upper respiratory tract infection (17.6%) and lower respiratory tract infection (14.4%). MMBV attained comparable area under the receiver operating characteristic curves ( P > 0.9) of 0.92 (95% confidence interval: 0.90-0.94) for the study population, 0.92 (0.89-0.94) for those sampled on day = 0, 0.92 (0.82-1.0) for those sampled on day ≥1 of hospital stay and 0.92 (0.88-0.96) for those with sampling time unknown. These data support MMBV's performance in hospitalized children. Real-world studies are warranted to establish MMBV's utility postadmission.

Metagenomic next-generation sequencing in pediatric infectious disease diagnosis: A comprehensive systematic literature review and meta-analysis.

Application value of prostate-specific antigen density combined with multiparametric MRI in early diagnosis of prostate cancer.

Evaluation of the Performance of the IOTA ADNEX Model in Discriminating Adnexal Masses Preoperatively: An Ambispective Study.

Pericardial disease spans a wide spectrum from small effusions to life-threatening tamponade or constriction. Transthoracic echocardiography (TTE) is the main diagnostic tool, but its interpretation is limited by operator dependence and incomplete functional assessment. Existing deep learning (DL) models focus mainly on effusion detection, lacking broader evaluation. We developed a DL-based framework that performs sequential assessment of pericardial disease: (i) morphological features, including effusion amount (normal/small/moderate/large) and pericardial thickening/adhesion (yes/no), from five B-mode views, and (ii) haemodynamic significance (yes/no), incorporating Doppler and inferior vena cava measurements. The developmental dataset comprises 2253 TTEs from multiple Korean institutions (225 for internal testing), and the independent external test set consists of 274 TTEs. In the internal test set, diagnostic accuracy was 81.8-97.3% for effusion, 91.6% for thickening/adhesion, and 86.2% for haemodynamic significance. External test set accuracy was 80.3-94.2%, 94.5%, and 85.5%, respectively. Area under the receiver operating curves for the three tasks were 0.92-0.99, 0.90, and 0.79 internally, and 0.95-0.98, 0.85, and 0.76 externally. Sensitivity for thickening/adhesion and haemodynamic significance improved from 66.7% to 77.3%, and 68.8% to 80.8%, respectively, when poor image quality were excluded. Similar performance gains were observed in subgroups with complete target views and a higher number of available video clips. This study presents the first DL-based TTE model for broader pericardial disease evaluation, integrating morphological with supportive functional assessments. The proposed framework demonstrated strong generalizability and aligned with the real-world diagnostic workflow. However, caution is warranted when interpreting results under suboptimal imaging conditions.

Identification of mitochondrial dysfunction-related biomarkers and immune infiltration in liver ischemia-reperfusion injury via integrated bioinformatics and machine learning.

Application of artificial intelligence in colonoscopy imaging for polyp analysis-A systematic review.

Salivary gland tumors are rare but diverse, with a higher prevalence of benign tumors in the parotid gland and a greater incidence of malignancy in other glands. Fine needle aspiration (FNA), enhanced by the Milan Reporting System, is widely used to evaluate these tumors. This study aimed to assess the diagnostic accuracy of the Milan Reporting System in a Saudi Arabian setting. This retrospective study included 117 patients from the western region of Saudi Arabia who underwent salivary gland FNA cytology with histological confirmation. Data were analyzed to evaluate demographic variables, Milan system category distribution, and diagnostic accuracy using SPSS Version 25. The study cohort had a slight male predominance, with most patients being middle-aged or older. Tumors were most commonly found in the parotid glands. Pleomorphic adenoma and squamous cell carcinoma were the most frequent benign and malignant tumors, respectively, in this study. The Milan Reporting System demonstrated excellent diagnostic performance, with high sensitivity (87.9%), specificity (99.5%), Positive Predictive Value (98.1%), and Negative Predictive Value (96.4%). The system correctly classified all benign tumors, indicating high diagnostic concordance and showed high sensitivity for malignant tumors. Statistical analysis revealed a significant correlation between the Milan Reporting System and histological diagnosis (p = 0.000). Our study evaluated the Milan Reporting System for salivary gland cytopathology in the western region of Saudi Arabia, revealing it to be a highly reliable screening tool for salivary gland tumors. The system demonstrated exceptional performance, particularly for common entities, such as pleomorphic adenoma and squamous cell carcinoma. This promotes early and accurate detection. However, when malignancy is suspected but the Milan Reporting System results are negative, it is crucial to perform additional confirmatory tests (such as repeating the FNA or performing a core biopsy) to avoid missing a diagnosis of cancer.

Diagnostic sensitivity: Surgical biopsy versus minimally invasive techniques in bronchopulmonary cancer.

Leukocytoclastic vasculitis (LCV) and microvascular occlusion (MVO) are distinct histopathologic patterns underlying dermatologic diagnoses of purpura. This study explores the potential of attention-based artificial intelligence (AI) models to enhance diagnostic accuracy and provide interpretable insights in differentiating these conditions, serving as a proof of concept for the application of explainable AI in dermatopathology. We compared the performance of two attention-based AI models, clustering-constrained-attention multiple-instance learning (CLAM) and attention multiple instance learning (MIL), in analyzing whole slide images of LCV and MVO cases. The models were trained and evaluated using a cohort of 69 biopsies. Performance metrics included precision, recall, accuracy, AUROC, and F1 score. Attention-based heatmaps were generated to highlight diagnostic regions and reveal histopathologic patterns. The CLAM model outperformed the attention MIL model across all evaluation metrics. Generated heatmaps effectively highlighted key diagnostic regions, including subtle areas of occlusion in the superficial papillary dermis of MVO cases. This study demonstrates the potential of attention-based AI models to improve diagnostic accuracy and provide interpretable insights in differentiating LCV and MVO. The use of explainable AI and heatmaps offers a valuable tool for pathologists, enhancing their ability to identify and understand subtle histopathologic patterns.

Plasma cell-free DNA biomarkers as novel diagnostic and prognostic tools in breast cancer.

Introduction: Pleural Effusion (PE) results from an imbalance between pleural fluid production and absorption. It may occur due to multiple aetiologies, including heart failure, infections, malignancies, and liver disease. While Light’s criteria remain the gold standard for classification, they misclassify up to 25% of transudates. Additional biochemical markers such as pleural fluid cholesterol, Alkaline Phosphatase (ALP), and D-dimer have shown promise in enhancing diagnostic accuracy. Aim: To compare the diagnostic efficacy of pleural fluid total cholesterol, pleural ALP, and D-dimer levels with Light’s criteria in differentiating exudative from transudative PEs. Materials and Methods: The present hospital-based crosssectional study was conducted jointly in the Departments of Respiratory Medicine and Biochemistry at Adesh Medical College and Hospital, Shahabad (M), Kurukshetra, Haryana, India, from November 2022 to October 2023. A total of 100 adult patients presenting with PE were recruited. Each patient underwent detailed clinical history, physical examination, chest radiography or Computed Tomography (CT) when indicated, and routine laboratory investigations. Pleural fluid samples were analysed for protein, Lactate Dehydrogenase (LDH), cholesterol, ALP, and D-dimer, while corresponding serum levels were also measured. Effusions were classified as transudative or exudative using Light’s criteria. Data were statistically analysed using independent t-test, Chi-square or Fisher’s exact test, binary logistic regression, and Receiver Operating Characteristic (ROC) curve analysis. A p-value <0.05 was considered statistically significant. Results: In the present study, 71% of participants were male, and the mean age was comparable between the exudative and transudative groups. Pleural fluid cholesterol, pleural ALP, pleural/serum ALP ratio, pleural D-dimer, and pleural/serum D-dimer ratio were significantly higher in exudates than in transudates (p <0.001). ROC analysis demonstrated that all parameters had an Area Under the Curve (AUC) of 1.0, with 100% sensitivity and specificity at the identified cut-off values. Logistic regression analysis identified serum ALP as a protective factor and the pleural/serum LDH ratio as an independent predictor of exudative effusion. Conclusion: Pleural fluid cholesterol, ALP, and D-dimer, along with their respective ratios, are highly reliable in differentiating exudative from transudative PEs and may serve as valuable adjuncts to Light’s criteria. These findings warrant validation in larger multicentric studies.