Purpose: Patients with chronic obstructive pulmonary disease (COPD) would have a poor prognosis if they were not continuously managed according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) guidelines. We aim to develop a model to classify whether COPD patients have been continuously managed according to GOLD in the previous year. Methods: The Managed group were COPD patients from a prospective cohort from November 2017 to November 2019, who have been continuously managed according to GOLD for 1 year. The Control group were COPD patients who were not continuously managed according to GOLD. They were from a retrospective cohort from October 2016 to October 2017 in the same hospitals as the Managed group. A synthetic minority over-sampling technique (SMOTE) algorithm was used to up-sample the Managed group in a training dataset. Features for classification were selected using a support vector machine recursive feature elimination (SVM-RFE) algorithm. The classification model was developed using LibSVM, and its performance was assessed on the testing dataset. Results: The final analysis included 15 subjects in the Managed group and 191 in the Control group. SVM-RFE selects nine features including smoking history, post-bronchodilator (post-)FVC before management, and those after 1-year follow-up (BMI, moderate and severe AECOPD frequency in previous 12 months, mMRC score, post-FEV1, post-FEV1%pred, post-FVC, and post-FEV1/FVC). For our model, positive predictive value is 66.7%, F1 score is 0.978, and AUC is 0.987. Conclusion: SVM classifier combined with SVM-REF feature selection algorithm could achieve good classification between COPD patients who are or are not continuously managed. This model could be applied in clinical practice to help doctors make decisions and enhance COPD patients’ compliance with standard treatment.

Nonalcoholic fatty liver disease (NAFLD) is one of major causes of end-stage liver disease in the coming decades, but it shows few symptoms until it develops into cirrhosis. We aim to develop classification models with machine learning to screen NAFLD patients among general adults. This study included 14,439 adults who took health examination. We developed classification models to classify subjects with or without NAFLD using decision tree, random forest (RF), extreme gradient boosting (XGBoost) and support vector machine (SVM). The classifier with SVM was showed the best performance with the highest accuracy (0.801), positive predictive value (PPV) (0.795), F1 score (0.795), Kappa score (0.508) and area under the precision-recall curve (AUPRC) (0.712), and the second top of area under receiver operating characteristic curve (AUROC) (0.850). The second-best classifier was RF model, which was showed the highest AUROC (0.852) and the second top of accuracy (0.789), PPV (0.782), F1 score (0.782), Kappa score (0.478) and AUPRC (0.708). In conclusion, the classifier with SVM is the best one to screen NAFLD in general population based on the results from physical examination and blood testing, followed by the classifier with RF. Those classifiers have a potential to screen NAFLD in general population for physician and primary care doctors, which could benefit to NAFLD patients from early diagnosis.

Background: IL-17A directly induces epithelial-mesenchymal transition (EMT) in alveolar epithelial cells. It could coordinate with cigarette smoke extract (CSE) to promote proliferation of bronchial epithelial cells. In this study, we aim to explore the direct effect of IL-17A and CSE on EMT in bronchial epithelial cells. Methods: Bronchial epithelial cells were isolated from C57BL/6 mice, and cocultured with CSE or/and IL-17A. E-cadherin and Vimentin expressions in cells were detected using immunofluorescence staining. IL-17R expression was detected using immunohistochemistry staining. NF-κB expression was assessed using western blotting. When NF-κB was inhibited by BAY 11–7821, expressions of NF-κB, E-cadherin and Vimentin were measured. Results: The protein expression of E-cadherin in bronchial epithelial cells was lowest in CSE + IL-17A group, followed by CSE group. In contrast, the protein expression of Vimentin was highest in CSE + IL-17A group, followed by CSE group. Similarly, IL-17R and NF-κB expressions were highest in CSE + IL-17A group, followed by CSE group and IL-17A group. NF-κB inhibitor could inhibit the expressions of E-cadherin and Vimentin. Conclusions: Cigarette and IL-17A could synergistically induce EMT in bronchial epithelial cells through activating IL17R/NF-κB signaling. Our findings contribute to a better understanding in airway EMT and pathogenesis of respiratory diseases, which are involved IL-17A and cigarette smoking. Those will provide novel avenues in the immunotherapy of lung diseases.

Carotid atherosclerosis (CAS) is a risk factor for cardiovascular and cerebrovascular events, but duplex ultrasonography isn’t recommended in routine screening for asymptomatic populations according to medical guidelines. We aim to develop machine learning models to screen CAS in asymptomatic adults. A total of 2732 asymptomatic subjects for routine physical examination in our hospital were included in the study. We developed machine learning models to classify subjects with or without CAS using decision tree, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM) and multilayer perceptron (MLP) with 17 candidate features. The performance of models was assessed on the testing dataset. The model using MLP achieved the highest accuracy (0.748), positive predictive value (0.743), F1 score (0.742), area under receiver operating characteristic curve (AUC) (0.766) and Kappa score (0.445) among all classifiers. It’s followed by models using XGBoost and SVM. In conclusion, the model using MLP is the best one to screen CAS in asymptomatic adults based on the results from routine physical examination, followed by using XGBoost and SVM. Those models may provide an effective and applicable method for physician and primary care doctors to screen asymptomatic CAS without risk factors in general population, and improve risk predictions and preventions of cardiovascular and cerebrovascular events in asymptomatic adults.

High bronchodilator reversibility in adult asthma is associated with distinct clinical characteristics. In this study, we aim to make a comparison with T-helper 2 (Th2)-related biomarkers, lung function and asthma control between asthmatic patients with high airway reversibility (HR) and low airway reversibility (LR). Patients with asthma diagnosed by pulmonologist according to Global Initiative for Asthma guidelines were recruited from the outpatient department of our hospital from August 2014 to July 2017. Patients were divided into HR and LR subgroups based on their response to bronchodilators of lung function (HR = Δforced expiratory volume in one second (FEV1) postbronchodilator ≥ 20%). Blood eosinophil count and serum IgE level, which are biomarkers of T-helper (Th)-2 phenotypes, were detected for patients. Asthma Control Test (ACT) was used to assess asthma control after the first-month initial treatment. A total of 265 patients with asthma were followed 1 month after initial treatment. HR group shows a higher level of Th2-high biomarkers (blood eosinophil count (10^9/L): 0.49 ± 0.28 vs 0.36 ± 0.19, P < 0.01; IgE (ng/ml): 1306 ± 842 vs 413 ± 261, P < 0.01), lower baseline lung function (FEV1%pred: 51.91 ± 19.34% vs 60.42 ± 19.22%, P < 0.01; forced expiratory flow (FEF)25–75: 0.76 ± 0.37 vs 1.00 ± 0.67, P < 0.01; FEF25–75%pred: 21.15 ± 10.09% vs 29.06 ± 16.50%, P < 0.01), and better asthma control (ACT score: 22 ± 4 vs 20 ± 4, P = 0.01) than LR group. HR was associated with a decreased risk of uncontrolled asthma after the first-month initial treatment (adjusted OR: 0.12 [95% confidence intervals: 0.03–0.50]). HR is a physiologic indicator of lower lung function and severe small airway obstruction, and is more related with an increased level of Th2-biomarkers than LR. Moreover, HR may indicate controlled asthma after the first-month initial treatment. This finding may contribute to identification of asthma endotype.