Search

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models., Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R2 and mean squared error (MSE) in the three sets., Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R2 value was 0.27 and in set II, LightGBM was the best model with the highest R2 value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R2 value of 0.56 and the lowest MSE of 174.07., Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

Background: Complementary and alternative medicine (CAM) has been used frequently, and its use continues to increase in lung cancer patients, despite insufficient scientific of its efficacy. To investigate this situation, we analyzed the current awareness and use of CAM in Korean lung-cancer patients., Methods: This prospective survey-based study was performed at seven medical centers in South Korea between August and October 2019. The survey assessed general patient characteristics and the awareness and use of CAM. We analyzed differences in the clinical parameters of patients aware and not aware of CAM and of CAM non-users and users., Results: Of the 434 patients included in this study, 68.8% responded that they were aware of CAM and 30.9% said they had experienced it. In univariate analysis, the patients aware of CAM were younger with poor performance status, had advanced-stage lung cancer, received more systemic therapy, and received concurrent chemoradiation therapy (CCRT). By multiple logistic regression, younger age, poor performance status, advanced stage, and prior CCRT were identified as independent risk factors for CAM awareness. There were no significant differences in the general characteristics and cancer-associated clinical parameters of CAM non-users and users., Conclusion: Specific clinical parameters were associated with patients' awareness of CAM, although there were no significantly different characteristics between CAM users and non-users.

Background: Obstructive sleep apnea (OSA) is associated with pulmonary fibrosis. Chronic intermittent hypoxia (CIH) is considered to be a surrogate of OSA. However, its exact role in pulmonary fibrosis remains uncertain. Therefore, we investigated the mechanism underlying CIH-induced pulmonary fibrosis and the role of the anti-fibrotic agent in bleomycin (BLE) induced lung injury., Methods: Mice were divided into eight groups: the normoxia (NOR), CIH, NOR plus BLE, CIH plus BLE, NOR plus pirfenidone (PF), CIH plus PF, NOR plus BLE and PF, and CIH plus BLE and PF groups. BLE was administered intratracheally on day 14 following CIH or NOR exposure. Subsequently, the mice were exposed to CIH or NOR for an additional 4 weeks. PF was administered orally on day 5 after BLE instillation once daily for 3 weeks., Results: In the BLE-treated groups, CIH-induced more collagen deposition in lung tissues than NOR, and significantly increased hydroxyproline and transforming growth factor-β expression. The CIH and BLE-treated groups showed increased lung inflammation compared to NOR or CIH groups. Following CIH with BLE treatment, nuclear factor-κB (NF-κB) protein expression was significantly increased, whereas nuclear factor-erythroid-related factor 2 (Nrf2) and heme oxygenase-1 protein levels were decreased. After PF treatment, NF-κB and Kelch-like ECH-associated protein 1 expression were suppressed, and Nrf2 expression was increased., Conclusion: CIH accelerated lung fibrosis in BLE-induced lung injury in mice, potentially by regulating the NF-κB/Nrf2 signaling pathway. Our results implicate PF as a potential therapeutic agent for treating pulmonary fibrosis in individuals with OSA and idiopathic pulmonary fibrosis.

Cancer is the leading cause of death in the Republic of Korea and cancer death accounts for 27.8% of the total deaths, which is not only a social issue but also a concern for the public. Among the cancer death rates, lung cancer mortality account for 34 deaths per 100,000 populations, making it the number one cancer death rate. In a preliminary report on cancer death in 2012, the lung cancer mortality ratio showed the regional variation indicating that there were differences in the qualitative level and the structure among the medical care benefit agency and in the assessment of the treatment process. Therefore, the Health Insurance Review and Assessment Service (HIRA) had begun evaluation of the assessment of lung cancer treatment since 2014 to improve the quality of lung cancer care through evaluation and feeds back the results of lung cancer care process. In this report, authors described the current Indicators for the lung cancer adequacy assessment proposed by HIRA and results of the evaluation reported in 2017., Competing Interests: No potential conflict of interest relevant to this article was reported., (Copyright©2018. The Korean Academy of Tuberculosis and Respiratory Diseases.)

Background: We aimed to analyze the factors predicting the diagnostic performance of flexible bronchoscopy without guidance in peripheral lung lesions that are endoscopically invisible., Methods: This was a retrospective study conducted in St. Paul's Hospital, The Catholic University of Korea, between January 2007 and March 2013. We included all patients who received bronchoscopy during this period. The analyzed variables were age, sex, the etiology of the lesion, lesion size, distance from the pleura, and presence of the bronchus sign. We used multiple logistic regression analysis to identify the significant independent factors associated with diagnostic yield., Results: We included 151 patients in this study. The overall diagnostic yield was 58.3%. The sensitivity was 43.2% for malignant disease and 78.1% for benign disease. The benign lung lesions (p<0.001), lesion size (p=0.015), presence of the exposed type of bronchus sign (p<0.001), and presence of cavitary lung lesions (p=0.005) were factors influencing the yield of flexible bronchoscopy by univariate analysis. In a multivariate logistic regression analysis, the exposed type of bronchus sign and benign lung lesions were independent predicting factors (odds ratio [OR]: 27.95; 95% confidence interval [CI], 7.56-103.32; p<0.001 and OR, 4.91; 95% CI, 1.76-13.72; p=0.002)., Conclusion: The presence of the exposed type of bronchus sign and benign lung lesions are determining factors of the diagnostic yield in flexible bronchoscopy in evaluating peripheral lesions that are not endoscopically visible., Competing Interests: Conflicts of Interest: No potential conflict of interest relevant to this article was reported.

An 18-year-old woman was evaluated for a chronic productive cough and dyspnea. She was subsequently diagnosed with mediastinal non-Hodgkin lymphoma (NHL). A covered self-expandable metallic stent (SEMS) was implanted to relieve narrowing in for both main bronchi. The NHL went into complete remission after six chemotherapy cycles, but atelectasis developed in the left lower lobe 18 months after SEMS insertion. The left main bronchus was completely occluded by granulation tissue. However, the right main bronchus and intermedius bronchus were patent. Granulation tissue was observed adjacent to the SEMS. The granulation tissue and the SEMS were excised, and a silicone stent was successfully implanted using a rigid bronchoscope. SEMS is advantageous owing to its easy implantation, but there are considerable potential complications such as severe reactive granulation, stent rupture, and ventilation failure in serious cases. Therefore, SEMS should be avoided whenever possible in patients with benign airway disease. This case highlights that SEMS implantation should be avoided even in malignant airway obstruction cases if the underlying malignancy is curable.

Background: Conventional biomarkers cannot always establish the cause of pleural effusions; thus, alternative tests permitting rapid and accurate diagnosis are required. The primary aim of this study is to assess the ability of pentraxin-3 (PTX3) in order to diagnose the cause of pleural effusion and compare its efficacy to that of other previously identified biomarkers., Methods: We studied 118 patients with pleural effusion, classified as transudates and exudates including malignant, tuberculous, and parapneumonic effusions (MPE, TPE, and PPE). The levels of PTX3, C-reactive protein (CRP), procalcitonin (PCT) and lactate in the pleural fluid were assessed., Results: The levels of pleural fluid PTX3 were significantly higher in patients with PPE than in those with MPE or TPE. PTX3 yielded the most favorable discriminating ability to predict PPE from MPE or TPE by providing the following: area under the curve, 0.74 (95% confidence interval, 0.63-0.84), sensitivity, 62.07%; and specificity, 81.08% with a cut-off point of 25.00 ng/mL., Conclusion: Our data suggests that PTX3 may allow improved differentiation of PPE from MPE or TPE compared to the previously identified biomarkers CRP and PCT.