Search

Background Rapid on‐site cytologic evaluation (ROSE) helps to improve the diagnostic accuracy in endobronchial ultrasound (EBUS) procedures. However, cytologists are seldom available to perform ROSE in many institutions. Recent studies have investigated the application of deep learning in cytologic image analysis. As such, the present study analyzed lung cytologic images obtained by EBUS procedures, and employed deep‐learning methods to distinguish between benign and malignant cells and to semantically segment malignant cells. Methods Ninety‐seven patients who underwent 104 EBUS procedures were enrolled. Four hundred and ninety‐nine lung cytologic images obtained via ROSE, including 425 malignant and 74 benign, and most malignant were lung adenocarcinoma (64.3%). All the images were used to train a residual network model with 101 layers (ResNet101), with suitable hyperparameters selected to classify benign and malignant lung cytologic images. An HRNet model was also employed to mark the area of malignant cells. Automatic patch‐cropping was adopted to facilitate dataset preparation. Results Malignant cells were successfully classified by ResNet101 with 98.8% classification accuracy, 98.8% sensitivity, and 98.8% specificity in patch‐based classification; 95.5% classification accuracy in image‐based classification; and 92.9% classification accuracy in patient‐based classification. Malignant cell area was successfully marked by HRNet with a mean intersection over union of 89.2%. The automatic cropping method enabled the system to complete diagnosis within 1 s. Conclusions This is the first study to combine lung cytologic image deep‐learning classification with semantic segmentation. The model was optimized for high accuracy and the automatic cropping facilitates the clinical application of our model. The success in both lung cytologic images classification and semantic segmentation on our dataset shows a promising result for clinical application in the future., This study leveraged the high computational speed characteristics of deep learning to distinguish and segmentally mark malignant cells in lung cytologic images obtained by EBUS procedures. Classification with ResNet101 and segmentation with HRNet were completed within 1 s and with high accuracy.

Background: Comprehensive rehabilitation programs are recommended for patients with prolonged mechanical ventilation (PMV) to facilitate functional recovery and ventilator weaning, but whether the functional status after rehabilitation influences outcome has not been clearly evaluated. This study aimed to investigate the association between post-rehabilitation functional status and weaning and survival outcome in PMV patients.Methods: We retrospectively enrolled PMV patients admitted to the respiratory care center (RCC), a post-ICU weaning facility with protocolized rehabilitation program, from January 2016 through December 2017. Functional status was measured by the de Morton Mobility Index (DEMMI), with a cut-off value set at 20 points. The primary outcomes were the weaning status at RCC discharge and hospital survival. The secondary outcomes were overall survival and survival at 3 months after RCC discharge. We followed patients until 3 months after RCC discharge or death. Logistic and Cox regressions were performed to identify significant parameters associated with weaning success and survival.Results: In total, 320 patients were enrolled. The weaning success rate was 71.6%. The survival rate at RCC discharge, hospital discharge, and 3 months after RCC discharge was 89.1, 77.5, and 66.6%, respectively. Post-rehabilitation DEMMI ≥ 20 (odds ratio [OR], 3.514; 95% confidence interval [CI], 1.436–8.598; P = 0.006) was the most significantly associated with weaning success. The weaning success and higher post-rehabilitation DEMMI were the two most significant independent factors associated with both hospital survival (weaning success, OR, 12.272; 95% CI, 5.281–28.517; P < 0.001; post-rehabilitation DEMMI ≥ 20, OR, 6.298; 95% CI, 1.302–30.477; P = 0.022) and survival at 3 months after RCC discharge (weaning success, OR, 38.788; 95% CI, 11.505–130.762; P < 0.001; post-rehabilitation DEMMI ≥ 20, OR, 4.830; 95% CI, 1.072–21.756; P = 0.040). Post-rehabilitation DEMMI ≥ 20 remained significantly association with overall survival at 3 months after RCC discharge (hazard ratio, 0.237; 95% CI, 0.072–0.785; P = 0.018).Conclusions: Post-rehabilitation functional status of PMV patients was independently associated with weaning success, as well as hospital and 3-month overall survival after RCC discharge. Post-rehabilitation, but not pre-rehabilitation, functional status was a significant parameter associated with weaning success and survival in patients requiring PMV.

ObjectivesLarge-scale, population-based real-world studies on the treatment outcomes of first-line tyrosine kinase inhibitors (TKIs) and subsequent systemic chemotherapy agents for lung adenocarcinoma (with activating epidermal growth factor receptor [EGFR] mutations) remain limited.Materials and MethodsFrom March 2014 to December 2016, patients with advanced lung adenocarcinoma, identified from the Taiwan Cancer Registry were included in this study if they received any of the three TKIs as first-line treatment. The primary outcome was overall survival (OS). The secondary outcome was time-to-treatment discontinuation (TTD).ResultsA total of 4,889 patients (median age: 67 years and two-thirds with distant metastasis) were recruited (1,778 gefitinib, 1,599 erlotinib, and 1,512 afatinib users). A 1:1 propensity score (PS)-matched cohorts of 1,228 afatinib/erlotinib and 1054 afatinib/gefitinib was created. After PS matching, it was found that afatinib was not associated with better OS (afatinib vs. erlotinib, HR: 0.96, 95% CI: 0.86–1.07; afatinib vs. gefitinib, HR: 0.91, 95% CI: 0.81–1.02). In the subgroup analysis, afatinib demonstrated a survival benefit in patients with active smoking (afatinib vs. erlotinib, HR: 0.69, 95% CI: 0.51–0.93; afatinib vs. gefitinib, HR: 0.67, 95% CI: 0.48–0.94) and ECOG > 1 (afatinib vs. erlotinib, HR: 0.79, 95% CI: 0.63–0.99; afatinib vs. gefitinib, HR: 0.78, 95% CI: 0.62–0.98). A total of 41.1% (n = 1992) of first-line TKI users received subsequent chemotherapy. Among the three TKI groups, pemetrexed usage was associated with better OS compared with other chemotherapy agents, with the exception of gemcitabine in the afatinib and gefitinib groups. Pemetrexed and gemcitabine had the longest TTD of 3–4 months.ConclusionsAmong patients with EGFR mutant lung adenocarcinoma, afatinib use may not provide longer OS compared with first-generation TKIs. Afatinib may be preferably considered among patients with active smoking and should not be withheld among those with worse performance status. With 40% of patients receiving subsequent chemotherapy, pemetrexed may be the preferred agent, while gemcitabine can be a reasonable alternative.

Background/Purpose: Rapid on-site cytologic evaluation (ROSE) has been shown to improve the diagnostic accuracy of endobronchial ultrasound-guided transbronchial biopsy (EBUS-TBB). However, ROSE by a cytopathologist or cytotechnologist is not always available during the procedure. The purposes of this study were to verify that a pulmonologist, after receiving training in cytology, could accurately assess an EBUS-TBB specimen on-site, and to evaluate the contribution of ROSE to EBUS-TBB. Methods: A retrospective chart review of patients who underwent EBUS-TBB for diagnosis of peripheral pulmonary lesions (PPLs) from January 2014 to June 2017 was performed. PPLs without a malignant diagnosis were excluded. The ROSE result determined by a pulmonologist was compared to the formal imprint cytologic report and pathologic report. The diagnostic accuracy of EBUS-TBB was also compared between those with and without ROSE. Results: Two hundred ninety-three patients who underwent 336 EBUS-TBB procedures for PPL diagnosis and were found to have proven malignancy were enrolled. Eighty-six procedures were performed with ROSE. With the formal imprint cytologic diagnosis as the standard, ROSE had 96.9% sensitivity, 68.2% specificity, 89.9% positive predictive value (PPV), 88.2% negative predictive value (NPV), and 89.5% diagnostic accuracy. With the formal pathologic result as the standard, ROSE had 88.2% sensitivity, 80% specificity, 97.1% PPV, 47.1% NPV, and 87.2% diagnostic accuracy, respectively. The diagnostic accuracy was significantly higher when ROSE was performed during EBUS-TBB (88.4% vs 68.0%, P

Background/Purpose: Endobronchial ultrasound (EBUS) elastography is a new technique that provides information on tissue compressibility during endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA). The purposes of this study were to evaluate the utility of EBUS elastography in differentiating malignant and benign mediastinal lymph nodes (LNs) and to explore the factors that influence its accuracy. Methods: A retrospective chart review of patients who underwent EBUS-TBNA from October 2016 to July 2017 was performed. EBUS with conventional B-mode features and elastographic patterns were compared with the final pathology results or clinical follow-up. We used the following EBUS elastographic patterns for classification: type 1, predominantly non-blue (green, yellow and red); type 2, part blue, part non-blue; type 3, predominantly blue. The potential impacts of the characteristics of LNs, the underlying lung diseases and obtaining fibrotic components from EBUS-TBNA specimens were evaluated relative to the accuracy of EBUS elastography. Results: A total of 206 LNs from 94 patients were retrospectively evaluated. In classifying type 1 as ‘benign’ and type 3 as ‘malignant,’ the sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy rate were 90.6, 82.6, 71.6, 94.7 and 85.2%, respectively. The EBUS elastographic patterns had higher diagnostic yields and negative predictive values than conventional B-mode features. Logistic regression analysis revealed that central necrosis was a factor that influenced the accuracy of elastography in malignant LNs. The fibrotic component within benign LNs could cause an incorrect elastographic pattern. Conclusion: EBUS elastography is a valuable tool in discriminating benign and malignant mediastinal LNs. Keywords: Elastography, Endobronchial ultrasound-guided transbronchial needle, Mediastinal lymph node

Background Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is now the standard for mediastinal lymph node staging of lung cancer. Training and maintenance of technical skills is very important in order to apply new techniques in clinical use. Methods A retrospective chart review was performed of patients who underwent EBUS-TBNA from November 2009 to December 2015. We assessed the learning curve, accuracy (%), and whether this procedure shortened the duration of lung cancer staging. Results The EBUS-TBNA learning curve continued to improve beyond 120 procedures. Diagnostic accuracy was similar between benign and malignant populations. There was no difference in the learning curve between the groups. Non-small cell lung cancer patients who underwent EBUS-TBNA as the first investigative procedure underwent fewer subsequent investigative procedures (1.47 vs. 2.05; P

Simple Summary Human-exhaled volatile organic compounds (VOCs) can be altered by lung cancer and become identifiable biomarkers. We used selected ion flow tube mass spectrometry (SIFT-MS) to quantitatively analyze 116 kinds of VOCs, which were exhaled by 148 lung cancer patients and 168 healthy individuals and collected from the environment to obtain a group of comprehensive data. A predictive model yielding 0.92 accuracy, 0.96 sensitivity, 0.88 specificity, and 0.98 area under the curve (AUC) was established using an advanced machine learning eXtreme Gradient Boosting (XGBoost) algorithm that considered the influences of exhaled and environmental VOCs. Abstract (1) Background: Lung cancer is silent in its early stages and fatal in its advanced stages. The current examinations for lung cancer are usually based on imaging. Conventional chest X-rays lack accuracy, and chest computed tomography (CT) is associated with radiation exposure and cost, limiting screening effectiveness. Breathomics, a noninvasive strategy, has recently been studied extensively. Volatile organic compounds (VOCs) derived from human breath can reflect metabolic changes caused by diseases and possibly serve as biomarkers of lung cancer. (2) Methods: The selected ion flow tube mass spectrometry (SIFT-MS) technique was used to quantitatively analyze 116 VOCs in breath samples from 148 patients with histologically confirmed lung cancers and 168 healthy volunteers. We used eXtreme Gradient Boosting (XGBoost), a machine learning method, to build a model for predicting lung cancer occurrence based on quantitative VOC measurements. (3) Results: The proposed prediction model achieved better performance than other previous approaches, with an accuracy, sensitivity, specificity, and area under the curve (AUC) of 0.89, 0.82, 0.94, and 0.95, respectively. When we further adjusted the confounding effect of environmental VOCs on the relationship between participants’ exhaled VOCs and lung cancer occurrence, our model was improved to reach 0.92 accuracy, 0.96 sensitivity, 0.88 specificity, and 0.98 AUC. (4) Conclusion: A quantitative VOCs databank integrated with the application of an XGBoost classifier provides a persuasive platform for lung cancer prediction.

Background/Purpose This two-part study aimed to investigate compliance with the sepsis resuscitation bundle (SRB) and the barriers to its implementation for patients developing septic shock in the general medical wards. Methods In the first part, medical records of patients who were admitted to the intensive care unit from the general medical wards due to septic shock were reviewed. Compliance rates with the six SRB components were assessed. In the second part, responsible junior physicians (first-year and second-year residents) in the general wards and senior physicians (third-year residents and fellows) were randomly invited for questionnaire-based interviews. Results In the first part, during the 6-month study period, 40 patients were included. Overall compliance with the SRB within 6 h was only 2.5%, mainly due to femoral catheterization (42.5%) and the lack of measuring central venous oxygen saturation (ScvO2). Delayed completion of SRB components contributed little to the low compliance rate. In the second part, based on the questionnaire results of 71 junior physicians and 64 senior physicians, the junior physicians were less familiar with the SRB guidelines, particularly regarding the meaning of ScvO2 (p = 0.01) and management of low ScvO2 (p = 0.04). Junior physicians were also more reluctant to measure the central venous pressure (CVP; p = 0.04) and the ScvO2 (p = 0.01), and were also less confident with internal jugular vein or subclavian vein catheterization (p Conclusion Compliance with the SRB for patients developing septic shock in the general medical wards is very low. Besides providing educational programs to improve awareness and acceptance of the SRB, measures to help in central venous catheterization and completion of SRB may be considered.

Aim: The aim of this study was to identify easy and relatively effective ultrasound criteria for metastatic mediastinal lymph node prediction. Materials and methods: A retrospective chart review of patients who underwent endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) from March 2014 to September 2016 was performed. We used the following EBUS sonographic features for metastatic lymph node prediction: 1) length of the short axis, 2) shape, 3) margin, 4) echogenicity, 5) central hilar structure, and 6) coagulation necrosis sign. These sonographic findings were compared with the final pathology results or clinical follow-up. Results: A total of 227 lymph nodes were retrospectively evaluated in 133 lung cancer patients; 72% of the lymph nodes had been proven to be malignant metastasis. Logistic regression analysis revealed that the length of the short axis, shape, margin, and echogenicity were independent predictive factors for metastasis. We developed a sum score based on these four sonographic features. A larger sum score trended toward a greater possibility of malignancy. If all four predictive factors were preserved, the diagnostic accuracy, the value of the specificity and the positive predictive value of the sonographic feature would be higher than 90%. Conclusions: The sonographic features of EBUS are valuable tools in predicting metastatic lymph nodes in lung cancer patients.

// Shang-Gin Wu 1, 2 , Yi-Nan Liu 3 , Meng-Feng Tsai 4 , Yih-Leong Chang 5 , Chong-Jen Yu 2, 3 , Pan-Chyr Yang 2, 3 , James Chih-Hsin Yang 6 , Yueh-Feng Wen 7 , Jin-Yuan Shih 2, 3 1 Department of Internal Medicine, National Taiwan University Hospital Yun-Lin Branch, Yun-Lin, Taiwan 2 Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan 3 Department of Internal Medicine, National Taiwan University Hospital, and College of Medicine, National Taiwan University, Taipei, Taiwan 4 Department of Molecular Biotechnology, Da-Yeh University, Chang-Hua, Taiwan 5 Department of Pathology, National Taiwan University Hospital, College of Medicine, National Taiwan University, Taipei, Taiwan 6 Department of Oncology, National Taiwan University Hospital, and Graduate Institute of Oncology, Cancer Research Center, National Taiwan University, Taipei, Taiwan 7 Department of Internal Medicine, National Taiwan University Hospital Hsinchu Branch, Hsinchu, Taiwan Correspondence to: Jin-Yuan Shih, e-mail: jyshih@ntu.edu.tw Keywords: lung adenocarcinoma, afatinib, T790M, acquired resistance, EGFR TKI Received: October 08, 2015 Accepted: January 23, 2016 Published: February 04, 2016 ABSTRACT Introduction: Epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) are associated with favorable response in EGFR mutant lung cancer. Acquired resistance to reversible EGFR TKIs remains a significant barrier, and acquired EGFR T790M-mutation is the major mechanism. Second-generation irreversible EGFR TKI, afatinib, had also been approved for treating EGFR mutant lung cancer patients, but the mechanism of acquired resistance to afatinib has not been well studied. Results: Forty-two patients had tissue specimens taken after acquiring resistance to afatinib. The sensitizing EGFR mutation were all consistent between pre- and post-afatinib tissues. Twenty patients (47.6%) had acquired T790M mutation. T790M rate was not different between first-generation EGFR TKI-naive patients (50%) and first-generation EGFR TKI-treated patients (46.4%) ( p = 0.827). No clinical characteristics or EGFR mutation types were associated with the development of acquired T790M. No other second-site EGFR mutations were detected. There were no small cell or squamous cell lung cancer transformation. Other genetic mutations were not identified in PIK3CA , BRAF , HER2 , KRAS , NRAS , MEK1 , AKT2 , LKB1 and JAK2 . Methods: Afatinib-prescription record of our department of pharmacy from January 2007 and December 2014 was retrieved. We investigated patients with tissue specimens available after acquiring resistance to afatinib. Enrolled patients should have partial response or durable stable disease of treatment response to afatinib. Various mechanisms of acquired resistance to first-generation EGFR TKIs were evaluated. Histology and cytology were reviewed. EGFR , PIK3CA , BRAF , HER2 , KRAS , NRAS , MEK1 , AKT2 , LKB1 and JAK2 genetic alterations were evaluated by sequencing. Statistical analysis was performed using Chi-square test and Kaplan-Meier method. Conclusions: T790M was detected in half of the lung adenocarcinoma after acquiring resistance to afatinib. T790M is still the major acquired resistance mechanism. First-generation EGFR TKI exposure did not influence the prevalence of T790M in lung cancer acquired resistance to afatinib.

Very few studies have focused on the outcome and management of patients with a single sputum isolate of nontuberculous mycobacterium (NTM) on initial examination. Patients with a single isolate of Mycobacterium avium complex (MAC), M. chelonae-abscessus, M. kansasii, or M. fortuitum from at least three sputum samples collected within 1 month were retrospectively identified. Those with follow-up sputum samples within 1 year were included in the analysis. Among the 202 patients included, M. fortuitum (n = 71, 35.1%) and MAC (n = 70, 34.7%) were the most common NTM species isolated, followed by M. chelonae-abscessus (n = 40, 19.8%) and M. kansasii (n = 21, 10.4%). The mean clinical follow-up period was 26.2 months. Forty-four patients (21.8%) had subsequent positive cultures of the same NTM species, while eight (4.0%) had bronchiectasis and developed NTM lung disease (NTM-LD). Neither patients without bronchiectasis nor those with M. fortuitum subsequently developed NTM lung disease. Among bronchiectatic patients with NTM other than M. fortuitum, age ≤65 years (p 0.006, OR 32.13), malignancy (p 0.048, OR 14.35), and initial radiographic score >2 (p 0.027, OR 20.06) were associated with subsequent NTM-LD. In all of the NTM patients, bronchiectasis (p

Hyperleukocytosis and thrombocytosis may develop in hematological disorders, including acute myelogenous or lymphoblastic leukemia, chronic leukemias in accelerated phase, and polycythemia vera. In such clinical scenarios, patients are at risk for hypoxemia, either true or spurious.[1][1] The causes