Search

Background: Radial probe endobronchial ultrasound (radial EBUS) is widely used to diagnose pulmonary lesions; however, the diagnostic value of radial EBUS-guided transbronchial biopsy (TBB) varies, and its complications (especially the risk of bleeding) are not properly understood. Objectives: In this study, we evaluated the diagnostic performance and rate of complication of this procedure, and investigated the risk factors associated with the procedure-related bleeding events. Design: A retrospective cohort study. Methods: This was a retrospective study that included consecutive patients who underwent radial EBUS-guided TBB. Radial EBUS was performed under moderate sedation in inpatients or outpatients. The severity of bleeding was graded using the standardized definitions of bleeding. Results: Of 133 patients (median age, 69 years; men 57.1%) included, 41 were outpatients (30.8%). The diagnostic accuracy, sensitivity, and specificity for malignancy were 76.1% (89/117), 71.1% (69/97), and 100% (20/20), respectively. The diagnostic accuracy ranged from 66.9% to 79.0%, depending on the classification of undiagnosed cases as either false negatives or true negatives. Twenty-seven patients (20.3%) developed complications (pneumothorax, 3; pneumonia, 5; complicated pleural effusion, 2; bleeding event grade 2 or higher, 21). Of the 41 outpatients, two developed complications (pneumothorax without intervention, 1; grade 2 bleeding event, 1). Of the 21 patients (15.8%) with procedure-related bleeding events, 18 had grade 2, and three had grade 3 bleeding complications. In multivariate analysis, a large size of ⩾30 mm (adjusted odds ratio (OR), 5.09; p = 0.03) and central lesion (adjusted OR, 3.67; p = 0.03) were significantly associated with the risk of grade 2 or higher bleeding events. Conclusion: Our results suggest that radial EBUS-guided TBB is an accurate and safe method for diagnosing pulmonary lesions. Clinically significant procedure-related bleeding was rare. The central location and larger size (⩾30 mm) of pulmonary lesions were risk factors for grade 2 or higher bleeding events. [ABSTRACT FROM AUTHOR]

Backgruound: To identify a screening tool for obstructive sleep apnea (OSA) and evaluate the effects of endoscopic transsphenoidal surgery on improving OSA in patients with acromegaly., Methods: We prospectively enrolled adults with acromegaly scheduled for endoscopic transsphenoidal surgery. All measurements were conducted when participants were admitted for a baseline work-up for acromegaly before surgery and surveillance approximately 3 to 6 months after surgery. Respiratory event index (REI) was used as a surrogate for apnea-hypopnea index (Trial Registration: NCT03526016)., Results: Of the 35 patients with acromegaly (median age, 47 years; 40% men; median body mass index, 24.4 kg/m2), 24 (68.6%) had OSA (REI ≥5/hour), 15 (42.9%) had moderate-to-severe OSA (REI ≥15/hour). At baseline, serum insulin-like growth factor 1 (IGF-1) levels were positively correlated with the REI (ρ=0.53, P=0.001). The sensitivity and negative predictive value of a Snoring, Tiredness, Observed apnea, high blood Pressure-Body mass index, age, Neck circumference, and Gender (STOP-Bang) score ≥ 3 were 93.3% and 87.5%, respectively, detecting moderate-to-severe OSA. Biochemical acromegaly remission was achieved in 32 (91.4%) patients. The median difference in the REI was -9.5/hour (95% confidence interval, -13.3 to -5.3). Half of the 24 patients diagnosed with OSA preoperatively had REI <5/hour postoperatively. In a linear mixed-effects model, changes in the REI across surgery were related to changes in IGF-1 levels., Conclusion: The STOP-Bang questionnaire is a reliable tool for OSA among patients with acromegaly. Improvement in OSA severity after surgery is related to decreased IGF-1 levels.

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well-annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied clinical environments and providing personalized volumetric reports to patients undergoing BM treatment., Competing Interests: Conflicts of Interest No conflicts of interest to disclose.

Rationale: Differential diagnosis of pleural effusion is challenging in clinical practice. Objectives: We aimed to develop a machine learning model to classify the five common causes of pleural effusions. Methods: This retrospective study collected 49 features from clinical information, blood, and pleural fluid of adult patients who underwent diagnostic thoracentesis between October 2013 and December 2018. Pleural effusions were classified into the following five categories: transudative, malignant, parapneumonic, tuberculous, and other. The performance of five different classifiers, including multinomial logistic regression, support vector machine, random forest, extreme gradient boosting, and light gradient boosting machine (LGB), was evaluated in terms of accuracy and area under the receiver operating characteristic curve through fivefold cross-validation. Hybrid feature selection was applied to determine the most relevant features for classifying pleural effusion. Results: We analyzed 2,253 patients (training set, n  = 1,459; validation set, n  = 365; extra-validation set, n  = 429) and found that the LGB model achieved the best performance in both validation and extra-validation sets. After feature selection, the accuracy of the LGB model with the selected 18 features was equivalent to that with all 49 features (mean ± standard deviation): 0.818 ± 0.012 and 0.777 ± 0.007 in the validation and extra-validation sets, respectively. The model's mean area under the receiver operating characteristic curve was as high as 0.930 ± 0.042 and 0.916 ± 0.044 in the validation and extra-validation sets, respectively. In our model, pleural lactate dehydrogenase, protein, and adenosine deaminase levels were the most important factors for classifying pleural effusions. Conclusions: Our LGB model showed satisfactory performance for differential diagnosis of the common causes of pleural effusions. This model could provide clinicians with valuable information regarding the major differential diagnoses of pleural diseases.

Objectives: The purpose of this study was to assess the effectiveness of human papillomavirus (HPV) vaccination administered to adolescent girls through Korea's National Immunization Program., Methods: This retrospective cohort study included patients who were 12-13 years old, whether vaccinated or unvaccinated, between July 2016 and December 2017. The incidence of genital warts (GWs) was monitored through 2021. Time-stratified hazard ratios (HRs) were estimated, adjusting for birth year, socioeconomic status, and the level of urbanization of the region, and were presented with 95% confidence intervals (CIs). Data were sourced from the Immunization Registry Integration System, linked with the National Health Information Database., Results: The study included 332,062 adolescent girls, with an average follow-up period of approximately 4.6 years. Except for the first year, the HRs for the vaccinated group were lower than those for the unvaccinated group. The HRs for specific cut-off years were as follows: year 2, 0.62 (95% CI, 0.31 to 1.13); year 3, 0.58 (95% CI, 0.35 to 0.96); and year 4 and beyond, 0.39 (95% CI, 0.28 to 0.52)., Conclusions: Our findings indicate that HPV vaccination was associated with a reduction in the risk of GWs among adolescent girls. Notably, this reduction became significant as the incidence of GWs increased with age.