- 作者列表："Nabi FG","Sundaraj K","Lam CK","Palaniappan R
:Objective: This study aimed to statistically analyze the behavior of time-frequency features in digital recordings of wheeze sounds obtained from patients with various levels of asthma severity (mild, moderate, and severe), and this analysis was based on the auscultation location and/or breath phase. Method: Segmented and validated wheeze sounds were collected from the trachea and lower lung base (LLB) of 55 asthmatic patients during tidal breathing maneuvers and grouped into nine different datasets. The quartile frequencies F25, F50, F75, F90 and F99, mean frequency (MF) and average power (AP) were computed as features, and a univariate statistical analysis was then performed to analyze the behavior of the time-frequency features. Results: All features generally showed statistical significance in most of the datasets for all severity levels [χ2 = 6.021-71.65, p < 0.05, η2 = 0.01-0.52]. Of the seven investigated features, only AP showed statistical significance in all the datasets. F25, F75, F90 and F99 exhibited statistical significance in at least six datasets [χ2 = 4.852-65.63, p < 0.05, η2 = 0.01-0.52], and F25, F50 and MF showed statistical significance with a large η2 in all trachea-related datasets [χ2 = 13.54-55.32, p < 0.05, η2 = 0.13-0.33]. Conclusion: The results obtained for the time-frequency features revealed that (1) the asthma severity levels of patients can be identified through a set of selected features with tidal breathing, (2) tracheal wheeze sounds are more sensitive and specific predictors of severity levels and (3) inspiratory and expiratory wheeze sounds are almost equally informative.
目的: 本研究旨在统计分析不同哮喘严重程度 (轻度、中度和重度) 患者获得的哮鸣音数字记录中的时频特征行为,该分析基于听诊位置和/或呼吸阶段。方法: 在潮气呼吸动作中，收集 55 例哮喘患者的气管和下肺底 (LLB) 的分段和验证哮鸣音，并分为 9 个不同的数据集。计算四分位数频率 F25 、 F50 、 F75 、 F90 和 F99 、平均频率 (MF) 和平均功率 (AP) 作为特征,然后进行单变量统计分析，分析时频特征的行为。结果: 所有特征在所有严重程度水平的大多数数据集中普遍表现出统计学意义 [χ 2 = 6.021-71.65，p <0.05，η 2 = 0.01-0.52]。在调查的 7 个特征中，只有 AP 在所有数据集中都显示出统计学显著性。F25 、 F75 、 F90 和 F99 在至少六个数据集中表现出统计学意义 [χ 2 = 4.852-65.63，p <0.05，η 2 = 0.01-0.52],f25 、 F50 和 MF 在所有气管相关数据集中均显示出较大的 η 2，差异有统计学意义 [χ 2 = 13.54-55.32，p <0.05,Η 2 = 0.13-0.33]。结论: 时间-频率特征的结果显示 (1) 患者的哮喘严重程度可以通过一组选择的潮气呼吸特征来确定，(2) 气管哮鸣音是更敏感和更具体的预测严重程度水平和 (3)吸气和呼气哮鸣音几乎同样具有信息性。
METHODS:Background Dye localization is a useful method for the resection of unidentifiable small pulmonary lesions. This study compares the transbronchial route with augmented fluoroscopic bronchoscopy (AFB) and conventional transthoracic CT-guided methods for preoperative dye localization in thoracoscopic surgery. Methods Between April 2015 and March 2019, a total of 231 patients with small pulmonary lesions who received preoperative dye localization via AFB or percutaneous CT-guided technique were enrolled in the study. A propensity-matched analysis, incorporating preoperative variables, was used to compare localization and surgical outcomes between the two groups. Results After matching, a total of 90 patients in the AFB group ( N = 30) and CT-guided group ( N = 60) were selected for analysis. No significant difference was noted in the demographic data between both the groups. Dye localization was successfully performed in 29 patients (96.7%) and 57 patients (95%) with AFB and CT-guided method, respectively. The localization duration (24.1 ± 8.3 vs. 21.4 ± 12.5 min, p = 0.297) and equivalent dose of radiation exposure (3.1 ± 1.5 vs. 2.5 ± 2.0 mSv, p = 0.130) were comparable in both the groups. No major procedure-related complications occurred in either group; however, a higher rate of pneumothorax (0 vs. 16.7%, p = 0.029) and focal intrapulmonary hemorrhage (3.3 vs. 26.7%, p = 0.008) was noted in the CT-guided group. Conclusion AFB dye marking is an effective alternative for the preoperative localization of small pulmonary lesions, with a lower risk of procedure-related complications than the conventional CT-guided method.
METHODS:Background The use of artificial intelligence, including machine learning, is increasing in medicine. Use of machine learning is rising in the prediction of patient outcomes. Machine learning may also be able to enhance and augment anesthesia clinical procedures such as airway management. In this study, we sought to develop a machine learning algorithm that could classify vocal cords and tracheal airway anatomy real-time during video laryngoscopy or bronchoscopy as well as compare the performance of three novel convolutional networks for detecting vocal cords and tracheal rings. Methods Following institutional approval, a clinical dataset of 775 video laryngoscopy and bronchoscopy videos was used. The dataset was divided into two categories for use for training and testing. We used three convolutional neural networks (CNNs): ResNet, Inception and MobileNet. Backpropagation and a mean squared error loss function were used to assess accuracy as well as minimize bias and variance. Following training, we assessed transferability using the generalization error of the CNN, sensitivity and specificity, average confidence error, outliers, overall confidence percentage, and frames per second for live video feeds. After the training was complete, 22 models using 0 to 25,000 steps were generated and compared. Results The overall confidence of classification for the vocal cords and tracheal rings for ResNet, Inception and MobileNet CNNs were as follows: 0.84, 0.78, and 0.64 for vocal cords, respectively, and 0.69, 0.72, 0.54 for tracheal rings, respectively. Transfer learning following additional training resulted in improved accuracy of ResNet and Inception for identifying the vocal cords (with a confidence of 0.96 and 0.93 respectively). The two best performing CNNs, ResNet and Inception, achieved a specificity of 0.985 and 0.971, respectively, and a sensitivity of 0.865 and 0.892, respectively. Inception was able to process the live video feeds at 10 FPS while ResNet processed at 5 FPS. Both were able to pass a feasibility test of identifying vocal cords and tracheal rings in a video feed. Conclusions We report the development and evaluation of a CNN that can identify and classify airway anatomy in real time. This neural network demonstrates high performance. The availability of artificial intelligence may improve airway management and bronchoscopy by helping to identify key anatomy real time. Thus, potentially improving performance and outcomes during these procedures. Further, this technology may theoretically be extended to the settings of airway pathology or airway management in the hands of experienced providers. The researchers in this study are exploring the performance of this neural network in clinical trials.
METHODS:BACKGROUND:The optimal mode of delivering topical anesthesia during flexible bronchoscopy remains unknown. This article compares the efficacy and safety of nebulized lignocaine, lignocaine oropharyngeal spray, or their combination. METHODS:Consecutive subjects were randomized 1:1:1 to receive nebulized lignocaine (2.5 mL of 4% solution, group A), oropharyngeal spray (10 actuations of 10% lignocaine, group B), or nebulization (2.5 mL, 4% lignocaine) and two actuations of 10% lignocaine spray (group C). The primary outcome was the subject-rated severity of cough according to a visual analog scale. The secondary outcomes included bronchoscopist-rated severity of cough and overall procedural satisfaction on a visual analog scale, total lignocaine dose, subject's willingness to undergo a repeat procedure, adverse reactions to lignocaine, and others. RESULTS:A total of 1,050 subjects (median age, 51 years; 64.8% men) were included. The median (interquartile range) score for subject-rated cough severity was significantly lower in group B compared to group C or group A (4 [1-10] vs 11 [4-24] vs 13 [5-30], respectively; P < .001). The bronchoscopist-rated severity of cough was also the least (P < .001), and the overall satisfaction was highest in group B (P < .001). The cumulative lignocaine dose administered was the least in group B (P < .001). A significantly higher proportion of subjects (P < .001) were willing to undergo a repeat bronchoscopy in group B (73.7%) than in groups A (49.1%) and C (59.4%). No lignocaine-related adverse events were observed. CONCLUSIONS:Ten actuations of 10% lignocaine oropharyngeal spray were superior to nebulized lignocaine or their combination for topical anesthesia during diagnostic flexible bronchoscopy. TRIAL REGISTRY:ClinicalTrials.gov; No.: NCT03109392; URL: www.clinicaltrials.gov.