首页 > 最新文献

Journal of thoracic disease最新文献

英文 中文
COVID-19 infection and pulmonary sarcoidosis: a systematic review and meta-analysis of morbidity, severity and mortality.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-24-1620
Sue In Choi, Won Jai Jung, Yujin Jeong, Sanghoon Park, Byung-Keun Kim, Sang Yeub Lee, Hyonggin An, Eun Joo Lee

Background: The pandemic coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) influenced millions of lives, not only healthy subjects but also patients with various comorbidities. Of those, interstitial lung disease (ILD) is known to be specifically vulnerable to SARS-CoV-2, sometimes leading to a lethal outcome. Sarcoidosis, one of the ILDs, has been suggested to be more susceptible to COVID-19, but the results of previous studies are in disagreement.

Methods: We performed a meta-analysis, attempting to explain the correlation between COVID-19 and sarcoidosis. Electronic databases were searched and selected for analysis under pre-established criteria. Risk ratio (RR) for incidence and odds ratio (OR) for severity, i.e., intensive care unit (ICU) admission and death, were calculated with (95%) confidence interval (CI) using R Statistical Software (version 4.3.1).

Results: The RR of COVID-19 incidence on sarcoidosis patients was 5.86 (95% CI: 8.02-11.91). Admission of sarcoidosis patients to the ICU who were infected with SARS-CoV-2 was 2.48 (95% CI: 2.04-3.01). Death of sarcoidosis by COVID-19 was also significantly higher compared with healthy controls (OR =1.95, 95% CI: 1.58-2.41). Both morbidity and mortality due to COVID-19 was significantly higher in the sarcoidosis patients.

Conclusions: Sarcoidosis patients are undeniably prone to SARS-CoV-2 infection, with increased severity, morbidity and greater mortality of COVID-19. Vaccination against SARS-CoV-2 for sarcoidosis therefore is beneficial, and may be a compulsory measure. Further studies regarding other factors are needed for a better understanding of the correlation between sarcoidosis and COVID-19.

{"title":"COVID-19 infection and pulmonary sarcoidosis: a systematic review and meta-analysis of morbidity, severity and mortality.","authors":"Sue In Choi, Won Jai Jung, Yujin Jeong, Sanghoon Park, Byung-Keun Kim, Sang Yeub Lee, Hyonggin An, Eun Joo Lee","doi":"10.21037/jtd-24-1620","DOIUrl":"https://doi.org/10.21037/jtd-24-1620","url":null,"abstract":"<p><strong>Background: </strong>The pandemic coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) influenced millions of lives, not only healthy subjects but also patients with various comorbidities. Of those, interstitial lung disease (ILD) is known to be specifically vulnerable to SARS-CoV-2, sometimes leading to a lethal outcome. Sarcoidosis, one of the ILDs, has been suggested to be more susceptible to COVID-19, but the results of previous studies are in disagreement.</p><p><strong>Methods: </strong>We performed a meta-analysis, attempting to explain the correlation between COVID-19 and sarcoidosis. Electronic databases were searched and selected for analysis under pre-established criteria. Risk ratio (RR) for incidence and odds ratio (OR) for severity, i.e., intensive care unit (ICU) admission and death, were calculated with (95%) confidence interval (CI) using R Statistical Software (version 4.3.1).</p><p><strong>Results: </strong>The RR of COVID-19 incidence on sarcoidosis patients was 5.86 (95% CI: 8.02-11.91). Admission of sarcoidosis patients to the ICU who were infected with SARS-CoV-2 was 2.48 (95% CI: 2.04-3.01). Death of sarcoidosis by COVID-19 was also significantly higher compared with healthy controls (OR =1.95, 95% CI: 1.58-2.41). Both morbidity and mortality due to COVID-19 was significantly higher in the sarcoidosis patients.</p><p><strong>Conclusions: </strong>Sarcoidosis patients are undeniably prone to SARS-CoV-2 infection, with increased severity, morbidity and greater mortality of COVID-19. Vaccination against SARS-CoV-2 for sarcoidosis therefore is beneficial, and may be a compulsory measure. Further studies regarding other factors are needed for a better understanding of the correlation between sarcoidosis and COVID-19.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"744-752"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898392/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Accuracy of lung structure constructed by three-dimensional image analysis with non-enhanced computed tomography.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-01-23 DOI: 10.21037/jtd-24-1406
Osamu Noritake, Shoji Okado, Yuka Kadomatsu, Harushi Ueno, Taketo Kato, Shota Nakamura, Tetsuya Mizuno, Toyofumi Fengshi Chen-Yoshikawa

Background: There are few papers on three-dimensional (3D) images of the lungs using non-enhanced computed tomography (CT). This study aimed to investigate the accuracy of 3D images of the lungs using non-enhanced CT.

Methods: The study included 10 consecutive cases for each lung lobe, totalling 50 cases between March and December 2022. The patients had both non-enhanced and contrast-enhanced CT taken within 2 months before surgery. A 3D image analysis system (SYNAPSE VINCENT) was used to obtain 3D images of the pulmonary artery (PA), pulmonary vein (PV), and bronchus (Br). The system automatically generated 3D images based on both non-enhanced and contrast-enhanced CTs, which were then compared with each other and also with actual surgical findings.

Results: The coincidence rate of PA, PV, and Br between 3D images based on non-enhanced CT and enhanced CT was 70% for the right lung and 65% for the left lung. The coincidence rate of PA, PV, and Br between 3D images based on non-enhanced CT and actual surgical findings was 100% for the right middle, right lower, and left lower lobes, but 50% for the right upper lobe and 60% for the left upper lobe.

Conclusions: The 3D images of the lungs based on non-enhanced CT showed that the right middle lobe and both lower lobes were correctly depicted. The right and left upper lobes were poorly visualized using non-enhanced CT, while the right upper lobe was poorly visualized using contrast-enhanced CT.

{"title":"Accuracy of lung structure constructed by three-dimensional image analysis with non-enhanced computed tomography.","authors":"Osamu Noritake, Shoji Okado, Yuka Kadomatsu, Harushi Ueno, Taketo Kato, Shota Nakamura, Tetsuya Mizuno, Toyofumi Fengshi Chen-Yoshikawa","doi":"10.21037/jtd-24-1406","DOIUrl":"https://doi.org/10.21037/jtd-24-1406","url":null,"abstract":"<p><strong>Background: </strong>There are few papers on three-dimensional (3D) images of the lungs using non-enhanced computed tomography (CT). This study aimed to investigate the accuracy of 3D images of the lungs using non-enhanced CT.</p><p><strong>Methods: </strong>The study included 10 consecutive cases for each lung lobe, totalling 50 cases between March and December 2022. The patients had both non-enhanced and contrast-enhanced CT taken within 2 months before surgery. A 3D image analysis system (SYNAPSE VINCENT) was used to obtain 3D images of the pulmonary artery (PA), pulmonary vein (PV), and bronchus (Br). The system automatically generated 3D images based on both non-enhanced and contrast-enhanced CTs, which were then compared with each other and also with actual surgical findings.</p><p><strong>Results: </strong>The coincidence rate of PA, PV, and Br between 3D images based on non-enhanced CT and enhanced CT was 70% for the right lung and 65% for the left lung. The coincidence rate of PA, PV, and Br between 3D images based on non-enhanced CT and actual surgical findings was 100% for the right middle, right lower, and left lower lobes, but 50% for the right upper lobe and 60% for the left upper lobe.</p><p><strong>Conclusions: </strong>The 3D images of the lungs based on non-enhanced CT showed that the right middle lobe and both lower lobes were correctly depicted. The right and left upper lobes were poorly visualized using non-enhanced CT, while the right upper lobe was poorly visualized using contrast-enhanced CT.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"816-823"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898399/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Club cell secretory protein 16 promotes cell proliferation and inhibits inflammation and pyroptosis in response to particulate matter 2.5-induced epithelial damage in asthmatic mice.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-24-1371
Jinle Lin, Xiaowen Chen, Yuehua Chen, Xiaobing Zeng, Fang Wang, Shaohua Luo, Lei Jiang, Wenxue Hu, Xiaolong Liu, Jing Zhang, Jian Wu

Background: Club cell secretory protein 16 (CC16) has protective roles in airway diseases, including anti-inflammatory, immunomodulatory, and antioxidant functions. This study investigates CC16's potential to repair lung injury from particulate matter 2.5 (PM2.5) exposure in asthmatic mice.

Methods: In an ovalbumin (OVA)-induced asthma model, 6-week-old male C57BL/6J mice were exposed to PM2.5 for 24 hours and then treated with CC16. We conducted arterial blood gas analysis, lung function tests, histopathology, and immunohistochemical (IHC) staining. The BEAS-2B cell line was exposed to PM2.5 for 24 hours and then treated with CC16. Tissues were analyzed by hematoxylin and eosin (HE) staining, electron, and IHC microscopy. The expression of indicators related to inflammation and pyroptosis was also detected and explored by performing RNA sequencing (RNA-seq).

Results: Upon OVA-sensitized asthmatic mice's exposure to PM2.5, CC16 therapy reversed lung tissue pathology, corrected acidosis in respiratory gases, and normalized airway constriction. Decreased CC16 also bolstered cellular growth, inhibited PM2.5-mediated pyroptosis, and downregulated the expression of inflammatory cytokines and pyroptosis markers at both protein and RNA levels. Transcriptome profiling showed that CC16 modulated the expression of genes linked to inflammatory adhesion, suppressing them, and upregulated those related to proliferation, particularly E-twenty-six-1 (ETS1).

Conclusions: CC16 efficiently remedies airway epithelial cells (AECs) harm caused by PM2.5 in asthmatic mice, fostering cellular multiplication and suppressing pyroptosis and inflammation. Our findings imply CC16's potential as a promising therapeutic option for addressing future health threats stemming from PM2.5 exposure.

{"title":"Club cell secretory protein 16 promotes cell proliferation and inhibits inflammation and pyroptosis in response to particulate matter 2.5-induced epithelial damage in asthmatic mice.","authors":"Jinle Lin, Xiaowen Chen, Yuehua Chen, Xiaobing Zeng, Fang Wang, Shaohua Luo, Lei Jiang, Wenxue Hu, Xiaolong Liu, Jing Zhang, Jian Wu","doi":"10.21037/jtd-24-1371","DOIUrl":"https://doi.org/10.21037/jtd-24-1371","url":null,"abstract":"<p><strong>Background: </strong>Club cell secretory protein 16 (CC16) has protective roles in airway diseases, including anti-inflammatory, immunomodulatory, and antioxidant functions. This study investigates CC16's potential to repair lung injury from particulate matter 2.5 (PM<sub>2.5</sub>) exposure in asthmatic mice.</p><p><strong>Methods: </strong>In an ovalbumin (OVA)-induced asthma model, 6-week-old male C57BL/6J mice were exposed to PM<sub>2.5</sub> for 24 hours and then treated with CC16. We conducted arterial blood gas analysis, lung function tests, histopathology, and immunohistochemical (IHC) staining. The BEAS-2B cell line was exposed to PM<sub>2.5</sub> for 24 hours and then treated with CC16. Tissues were analyzed by hematoxylin and eosin (HE) staining, electron, and IHC microscopy. The expression of indicators related to inflammation and pyroptosis was also detected and explored by performing RNA sequencing (RNA-seq).</p><p><strong>Results: </strong>Upon OVA-sensitized asthmatic mice's exposure to PM<sub>2.5</sub>, CC16 therapy reversed lung tissue pathology, corrected acidosis in respiratory gases, and normalized airway constriction. Decreased CC16 also bolstered cellular growth, inhibited PM<sub>2.5</sub>-mediated pyroptosis, and downregulated the expression of inflammatory cytokines and pyroptosis markers at both protein and RNA levels. Transcriptome profiling showed that CC16 modulated the expression of genes linked to inflammatory adhesion, suppressing them, and upregulated those related to proliferation, particularly E-twenty-six-1 (<i>ETS1</i>).</p><p><strong>Conclusions: </strong>CC16 efficiently remedies airway epithelial cells (AECs) harm caused by PM<sub>2.5</sub> in asthmatic mice, fostering cellular multiplication and suppressing pyroptosis and inflammation. Our findings imply CC16's potential as a promising therapeutic option for addressing future health threats stemming from PM<sub>2.5</sub> exposure.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"753-773"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898337/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Machine learning for predicting the prognosis of patients with thymoma and thymic carcinoma.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-20 DOI: 10.21037/jtd-24-1263
Haijie Xu, Xirui Lin, Junhan Wu, Jianrong Chen, Jiaying Wu, Zheng Lin, Xiaoming Cai, Jiong Lin, Peishen Li, Chaoquan He, Zefeng Xie, Hansheng Wu

Background: Thymoma and thymic carcinoma are the most common tumors of the anterior mediastinum. However, there are little research on applying machine learning (ML) approaches to the prognostic prediction of thymoma and thymic carcinoma. The study aims to develop predictive models utilizing ML techniques to accurately forecast the 5-year survival of patients with thymoma and thymic carcinoma.

Methods: Patients with malignant thymic neoplasms were identified in the Surveillance, Epidemiology, and End Results (SEER) 17 database, and their demographic and clinicopathological characteristics were collected. ML classifiers, including elastic net regularized logistic regression, random forest (RF), non-linear support vector machine (SVM), extreme gradient boosting (XGBoost) machine, and categorical boosting (CatBoost) were trained. The hyper-parameter of the algorithms was optimized by a grid search with five repeats of 10-fold cross-validation. Ensemble models were built based on the three algorithms with the highest area under the receiver operator characteristic (ROC) curve (AUC) in the validation set. The best model among the single models and ensemble model was selected as the final model. Calibration curve and decision curve were adopted to evaluate the calibration performance and clinical utility. For comparison, we constructed a baseline model consisting of age and Masaoka stages using logistic regression.

Results: After data cleaning, 1,363 patients and 841 patients were included in the overall survival (OS) dataset and disease-specific survival (DSS) dataset, respectively. CatBoost [AUC: 0.755; 95% confidence interval (CI): 0.698-0.811] had the best performance in the OS prediction for the original dataset. The ensemble model achieved the highest prognostic efficiency for the original dataset, with an AUC of 0.833 (95% CI: 0.765-0.901). Calibration showed favorable goodness of fit and was further verified with the Hosmer-Lemeshow test (CatBoost: χ2=12.63, P=0.13; ensemble model: χ2=7.61, P=0.47). The decision curve showed that the final model provided a high net benefit. The model could significantly distinguish the prognosis of patients (all P values <0.001). Finally, World Health Organization (WHO) histological classification, Masaoka stage, and age were the variables that significantly contributed to the models' prediction of OS and DSS.

Conclusions: We trained ML-based predictive models that could accurately predict the 5-year OS and DSS of patients with thymoma and thymic carcinoma.

{"title":"Machine learning for predicting the prognosis of patients with thymoma and thymic carcinoma.","authors":"Haijie Xu, Xirui Lin, Junhan Wu, Jianrong Chen, Jiaying Wu, Zheng Lin, Xiaoming Cai, Jiong Lin, Peishen Li, Chaoquan He, Zefeng Xie, Hansheng Wu","doi":"10.21037/jtd-24-1263","DOIUrl":"https://doi.org/10.21037/jtd-24-1263","url":null,"abstract":"<p><strong>Background: </strong>Thymoma and thymic carcinoma are the most common tumors of the anterior mediastinum. However, there are little research on applying machine learning (ML) approaches to the prognostic prediction of thymoma and thymic carcinoma. The study aims to develop predictive models utilizing ML techniques to accurately forecast the 5-year survival of patients with thymoma and thymic carcinoma.</p><p><strong>Methods: </strong>Patients with malignant thymic neoplasms were identified in the Surveillance, Epidemiology, and End Results (SEER) 17 database, and their demographic and clinicopathological characteristics were collected. ML classifiers, including elastic net regularized logistic regression, random forest (RF), non-linear support vector machine (SVM), extreme gradient boosting (XGBoost) machine, and categorical boosting (CatBoost) were trained. The hyper-parameter of the algorithms was optimized by a grid search with five repeats of 10-fold cross-validation. Ensemble models were built based on the three algorithms with the highest area under the receiver operator characteristic (ROC) curve (AUC) in the validation set. The best model among the single models and ensemble model was selected as the final model. Calibration curve and decision curve were adopted to evaluate the calibration performance and clinical utility. For comparison, we constructed a baseline model consisting of age and Masaoka stages using logistic regression.</p><p><strong>Results: </strong>After data cleaning, 1,363 patients and 841 patients were included in the overall survival (OS) dataset and disease-specific survival (DSS) dataset, respectively. CatBoost [AUC: 0.755; 95% confidence interval (CI): 0.698-0.811] had the best performance in the OS prediction for the original dataset. The ensemble model achieved the highest prognostic efficiency for the original dataset, with an AUC of 0.833 (95% CI: 0.765-0.901). Calibration showed favorable goodness of fit and was further verified with the Hosmer-Lemeshow test (CatBoost: χ<sup>2</sup>=12.63, P=0.13; ensemble model: χ<sup>2</sup>=7.61, P=0.47). The decision curve showed that the final model provided a high net benefit. The model could significantly distinguish the prognosis of patients (all P values <0.001). Finally, World Health Organization (WHO) histological classification, Masaoka stage, and age were the variables that significantly contributed to the models' prediction of OS and DSS.</p><p><strong>Conclusions: </strong>We trained ML-based predictive models that could accurately predict the 5-year OS and DSS of patients with thymoma and thymic carcinoma.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"824-835"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898343/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Reintervention after percutaneous mitral balloon commissurotomy in patients with rheumatic heart disease: feasibility of surgical mitral valve repair.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-24-1485
Xin Li, Yinfan Zhu, Jiajun Liang, Wenjian Jiang, Jie Han, Yuyong Liu, Hongjia Zhang

Background: Currently, mitral valve replacement is the primary method of reintervention for patients with rheumatic heart disease (RHD) after percutaneous mitral balloon commissurotomy (PMBC). This study aims to investigate the feasibility of mitral valve repair in such patients and report its therapeutic outcomes compared to mitral valve replacement.

Methods: Data from patients with previous PMBC who underwent mitral valve surgery as disease progression between January 2011 and August 2023 were retrospectively analyzed. The patients were divided into two groups: the repair group and the replacement group. The stabilized inverse probability of treatment weighting (SIPTW) method was used to balance baseline characteristic differences between the two groups. Clinical outcomes investigated included freedom from mitral valve reoperation and overall survival. Survival curves were generated with the Kaplan-Meier (K-M) method, and differences between groups were compared using the Log-rank test.

Results: A total of 210 patients were included in this study (32 in the repair group and 178 in the replacement group), with an average age of 56.6±10.0 years. After SIPTW, the baseline characteristics between the two groups were comparable. The median follow-up time for the entire cohort was 75.6 months. K-M analysis, adjusted for SIPTW, showed no significant differences between the two groups in terms of freedom from mitral valve reoperation and overall survival (Log-rank P=0.07 and 0.36, respectively).

Conclusions: According to our results, even if patients with RHD have previously undergone PMBC, there is still a possibility of mitral valve repair in suitable patients, with good clinical outcomes.

{"title":"Reintervention after percutaneous mitral balloon commissurotomy in patients with rheumatic heart disease: feasibility of surgical mitral valve repair.","authors":"Xin Li, Yinfan Zhu, Jiajun Liang, Wenjian Jiang, Jie Han, Yuyong Liu, Hongjia Zhang","doi":"10.21037/jtd-24-1485","DOIUrl":"https://doi.org/10.21037/jtd-24-1485","url":null,"abstract":"<p><strong>Background: </strong>Currently, mitral valve replacement is the primary method of reintervention for patients with rheumatic heart disease (RHD) after percutaneous mitral balloon commissurotomy (PMBC). This study aims to investigate the feasibility of mitral valve repair in such patients and report its therapeutic outcomes compared to mitral valve replacement.</p><p><strong>Methods: </strong>Data from patients with previous PMBC who underwent mitral valve surgery as disease progression between January 2011 and August 2023 were retrospectively analyzed. The patients were divided into two groups: the repair group and the replacement group. The stabilized inverse probability of treatment weighting (SIPTW) method was used to balance baseline characteristic differences between the two groups. Clinical outcomes investigated included freedom from mitral valve reoperation and overall survival. Survival curves were generated with the Kaplan-Meier (K-M) method, and differences between groups were compared using the Log-rank test.</p><p><strong>Results: </strong>A total of 210 patients were included in this study (32 in the repair group and 178 in the replacement group), with an average age of 56.6±10.0 years. After SIPTW, the baseline characteristics between the two groups were comparable. The median follow-up time for the entire cohort was 75.6 months. K-M analysis, adjusted for SIPTW, showed no significant differences between the two groups in terms of freedom from mitral valve reoperation and overall survival (Log-rank P=0.07 and 0.36, respectively).</p><p><strong>Conclusions: </strong>According to our results, even if patients with RHD have previously undergone PMBC, there is still a possibility of mitral valve repair in suitable patients, with good clinical outcomes.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"593-602"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Risk factors affecting pulmonary complications in elderly patients with isolated rib fractures.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-24-1323
Rui Cheng, Minghui Yang, Ying Zhang, William C Cho, Dehua Ma, Dong Chen, Yanan Zhu, Jianfei Shen

Background: Blunt chest injuries are the predominant cause of rib fractures, which frequently result in pulmonary complications. We hypothesized that different trauma mechanisms and fracture patterns are associated with pulmonary complications in elderly patients (≥65 years) with isolated rib fractures.

Methods: We retrospectively reviewed the data of patients with rib fractures recorded in the electronic medical record system of a trauma center from 2015 to 2019. The correlation between age, comorbidities, trauma mechanisms, fracture patterns, and pulmonary complications was examined.

Results: A total of 168 elderly patients with isolated rib fractures after trauma were included in the study. Except for one patient who died, all other patients recovered and were discharged. Univariate analysis identified age, trauma mechanisms, and fracture patterns as potential risk factors for pulmonary complications. Multivariate logistic regression analysis found that falls [odds ratio (OR) 5.051, 95% confidence interval (CI): 1.380-18.485; P=0.01], rib fracture displacement (OR 4.924, 95% CI: 1.826-13.275; P=0.002), and multiple rib fractures (≥2 ribs) (OR 2.984, 95% CI: 1.182-7.531; P=0.02) were the independent risk factors for pulmonary complications. Subgroup analysis showed that hemothorax occurred in 47 (85.5%, P=0.001) patients with falls, 69 (89.6%, P<0.001) patients with displaced rib fractures, and 99 (74.4%, P<0.001) patients with multiple rib fractures.

Conclusions: The traumatic mechanisms and fracture patterns appear to be related to pulmonary complications, with patients experiencing falls, displaced rib fractures, and multiple rib fractures being more likely to develop these complications.

{"title":"Risk factors affecting pulmonary complications in elderly patients with isolated rib fractures.","authors":"Rui Cheng, Minghui Yang, Ying Zhang, William C Cho, Dehua Ma, Dong Chen, Yanan Zhu, Jianfei Shen","doi":"10.21037/jtd-24-1323","DOIUrl":"https://doi.org/10.21037/jtd-24-1323","url":null,"abstract":"<p><strong>Background: </strong>Blunt chest injuries are the predominant cause of rib fractures, which frequently result in pulmonary complications. We hypothesized that different trauma mechanisms and fracture patterns are associated with pulmonary complications in elderly patients (≥65 years) with isolated rib fractures.</p><p><strong>Methods: </strong>We retrospectively reviewed the data of patients with rib fractures recorded in the electronic medical record system of a trauma center from 2015 to 2019. The correlation between age, comorbidities, trauma mechanisms, fracture patterns, and pulmonary complications was examined.</p><p><strong>Results: </strong>A total of 168 elderly patients with isolated rib fractures after trauma were included in the study. Except for one patient who died, all other patients recovered and were discharged. Univariate analysis identified age, trauma mechanisms, and fracture patterns as potential risk factors for pulmonary complications. Multivariate logistic regression analysis found that falls [odds ratio (OR) 5.051, 95% confidence interval (CI): 1.380-18.485; P=0.01], rib fracture displacement (OR 4.924, 95% CI: 1.826-13.275; P=0.002), and multiple rib fractures (≥2 ribs) (OR 2.984, 95% CI: 1.182-7.531; P=0.02) were the independent risk factors for pulmonary complications. Subgroup analysis showed that hemothorax occurred in 47 (85.5%, P=0.001) patients with falls, 69 (89.6%, P<0.001) patients with displaced rib fractures, and 99 (74.4%, P<0.001) patients with multiple rib fractures.</p><p><strong>Conclusions: </strong>The traumatic mechanisms and fracture patterns appear to be related to pulmonary complications, with patients experiencing falls, displaced rib fractures, and multiple rib fractures being more likely to develop these complications.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"542-550"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898332/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Survival advantage of radiotherapy and nomogram for patients with pulmonary neuroendocrine neoplasms: a propensity score-matched Surveillance, Epidemiology, and End Results database study.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-2024-2233
Jingtao Tong, Kaitai Liu, Guodong Xu, Wei Shen, Robert A Ramirez, Qinning Wang, Hang Chen, Lu Zheng, Quan Xu, Hui Zhang

Background: The standard treatment for pulmonary neuroendocrine neoplasms (pNENs) is surgery in the early stage and is generally determined according to the histologic type and stage. Radiotherapy (RT) is a treatment option for locally advanced or unresectable lung cancers. The aim of this study was to determine the prognostic value of RT in patients with pNENs using data from the Surveillance, Epidemiology, and End Results database.

Methods: We used propensity score matching analysis to balance differences in variables between the RT and no-RT groups. Univariate and multivariate Cox proportional hazards regression analyses were used to evaluate the factors related to overall survival and cancer-specific survival (CSS). A novel nomogram was constructed, and the results were evaluated using the concordance index.

Results: A total of 7,470 cases were identified between 2000 and 2019, among whom 1,429 were placed in the RT group and propensity-score matched with those in the no-RT group at a 1:1 ratio. Age, sex, marital status, disease extension, surgery, and RT were identified as independent prognostic factors of outcome. There was no significant difference in overall or CSS between RT and no-RT patients in the surgery group (P=0.22 and P=0.72, respectively). However, RT was associated with survival benefit in the no-surgery group. According to the concordance index, the nomogram could accurately predict the prognosis of patients with pNENs.

Conclusions: Our findings indicate that RT may provide a survival benefit for patients with pNENs, particularly for those who did not undergo surgery. The nomogram produced in this study may be a used to predict the prognosis of this patient group.

{"title":"Survival advantage of radiotherapy and nomogram for patients with pulmonary neuroendocrine neoplasms: a propensity score-matched Surveillance, Epidemiology, and End Results database study.","authors":"Jingtao Tong, Kaitai Liu, Guodong Xu, Wei Shen, Robert A Ramirez, Qinning Wang, Hang Chen, Lu Zheng, Quan Xu, Hui Zhang","doi":"10.21037/jtd-2024-2233","DOIUrl":"https://doi.org/10.21037/jtd-2024-2233","url":null,"abstract":"<p><strong>Background: </strong>The standard treatment for pulmonary neuroendocrine neoplasms (pNENs) is surgery in the early stage and is generally determined according to the histologic type and stage. Radiotherapy (RT) is a treatment option for locally advanced or unresectable lung cancers. The aim of this study was to determine the prognostic value of RT in patients with pNENs using data from the Surveillance, Epidemiology, and End Results database.</p><p><strong>Methods: </strong>We used propensity score matching analysis to balance differences in variables between the RT and no-RT groups. Univariate and multivariate Cox proportional hazards regression analyses were used to evaluate the factors related to overall survival and cancer-specific survival (CSS). A novel nomogram was constructed, and the results were evaluated using the concordance index.</p><p><strong>Results: </strong>A total of 7,470 cases were identified between 2000 and 2019, among whom 1,429 were placed in the RT group and propensity-score matched with those in the no-RT group at a 1:1 ratio. Age, sex, marital status, disease extension, surgery, and RT were identified as independent prognostic factors of outcome. There was no significant difference in overall or CSS between RT and no-RT patients in the surgery group (P=0.22 and P=0.72, respectively). However, RT was associated with survival benefit in the no-surgery group. According to the concordance index, the nomogram could accurately predict the prognosis of patients with pNENs.</p><p><strong>Conclusions: </strong>Our findings indicate that RT may provide a survival benefit for patients with pNENs, particularly for those who did not undergo surgery. The nomogram produced in this study may be a used to predict the prognosis of this patient group.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"1002-1012"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898353/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
COVID-19 caused by the Omicron variant in lung transplant recipients: a single center case series.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-24-1314
Li Zhao, Lijuan Guo, Bin Xing, Yi Zhang, Mengyin Chen, Wenhui Chen
<p><strong>Background: </strong>Although coronavirus disease 2019 (COVID-19) is no longer classified as a Public Health Emergency of International Concern by World Health Organization, its global impact persists. Data on its impact in lung transplant recipients (LTRs) from China remain limited. This study aims to share clinical experiences and provide insights into managing LTRs with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection.</p><p><strong>Methods: </strong>We conducted a study on LTRs with COVID-19 caused by the Omicron variant from November 17, 2022, to May 1, 2023. Clinical information was gathered retrospectively through electronic medical records, questionnaires, or follow-up telephone calls.</p><p><strong>Results: </strong>A total of 227 LTRs were reviewed for infection with Omicron variant. After excluding 49 cases without confirmed SARS-CoV-2 infection, this left a final cohort of 178 infected LTRs, accounting for an infection rate of 78.4% (178/227). Of the patients, 50% (89/178) required hospitalization, with an average hospital stay of 16 days [interquartile range (IQR): 9.5-25.5 days]. Of the 89 hospitalized patients, 41.6% (37/89) eventually progressed to severe or critical disease, forming the severe/critical group (S/C group), while the remaining 58.4% (52/89) had mild or moderate disease (M/M group). In comparison to the M/M group, the S/C group had higher C-reactive protein (CRP) (59.6 <i>vs.</i> 16.8 mg/L, P<0.001), Erythrocyte sedimentation rate (45.5 <i>vs.</i> 22.5 mm/h, P=0.005) and D-dimer level (1.09 <i>vs.</i> 0.65 mg/L, P=0.01), but lower CD4<sup>+</sup> T lymphocytes count (217 <i>vs.</i> 427 cells/µL, P=0.004). The S/C group had significantly higher rates of combined pulmonary bacterial infection (67.6% <i>vs.</i> 38.5%, P=0.006) and pulmonary fungal infection (73.0% <i>vs.</i> 38.5%, P=0.001) during the course of COVID-19, nearly double that of the M/M group. In a multivariate logistic analysis, elevated CRP (>41.8 mg/L), combined pulmonary fungal infection, and interstitial lung disease (ILD) as primary disease emerged as high-risk factors for developing the severe disease phenotype following Omicron variant infection in LTRs, with respective odds ORs values of 4.23 [95% confidence interval (CI): 1.68-11.23], 4.76 (95% CI: 1.59-15.64), and 5.13 (95% CI: 1.19-29.17). Receiver operating characteristic (ROC) curve analysis showed that CD4<sup>+</sup> T lymphocyte count may be a strong marker for predicting death. At a cutoff of 404 cells/µL, sensitivity was 0.509, specificity 0.999, and area under the curve (AUC) was 0.806 (95% CI: 0.678-0.934). Ultimately, 13 recipients succumbed to COVID-19 related respiratory failure or secondary multiple organ dysfunction, resulting in an overall mortality rate of 7.3% (13/178).</p><p><strong>Conclusions: </strong>LTRs are at high risk of secondary lung infections after Omicron. Key risk factors for severe disease include CRP >41.8 mg/L, ILD as primary d
{"title":"COVID-19 caused by the Omicron variant in lung transplant recipients: a single center case series.","authors":"Li Zhao, Lijuan Guo, Bin Xing, Yi Zhang, Mengyin Chen, Wenhui Chen","doi":"10.21037/jtd-24-1314","DOIUrl":"https://doi.org/10.21037/jtd-24-1314","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Although coronavirus disease 2019 (COVID-19) is no longer classified as a Public Health Emergency of International Concern by World Health Organization, its global impact persists. Data on its impact in lung transplant recipients (LTRs) from China remain limited. This study aims to share clinical experiences and provide insights into managing LTRs with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a study on LTRs with COVID-19 caused by the Omicron variant from November 17, 2022, to May 1, 2023. Clinical information was gathered retrospectively through electronic medical records, questionnaires, or follow-up telephone calls.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 227 LTRs were reviewed for infection with Omicron variant. After excluding 49 cases without confirmed SARS-CoV-2 infection, this left a final cohort of 178 infected LTRs, accounting for an infection rate of 78.4% (178/227). Of the patients, 50% (89/178) required hospitalization, with an average hospital stay of 16 days [interquartile range (IQR): 9.5-25.5 days]. Of the 89 hospitalized patients, 41.6% (37/89) eventually progressed to severe or critical disease, forming the severe/critical group (S/C group), while the remaining 58.4% (52/89) had mild or moderate disease (M/M group). In comparison to the M/M group, the S/C group had higher C-reactive protein (CRP) (59.6 &lt;i&gt;vs.&lt;/i&gt; 16.8 mg/L, P&lt;0.001), Erythrocyte sedimentation rate (45.5 &lt;i&gt;vs.&lt;/i&gt; 22.5 mm/h, P=0.005) and D-dimer level (1.09 &lt;i&gt;vs.&lt;/i&gt; 0.65 mg/L, P=0.01), but lower CD4&lt;sup&gt;+&lt;/sup&gt; T lymphocytes count (217 &lt;i&gt;vs.&lt;/i&gt; 427 cells/µL, P=0.004). The S/C group had significantly higher rates of combined pulmonary bacterial infection (67.6% &lt;i&gt;vs.&lt;/i&gt; 38.5%, P=0.006) and pulmonary fungal infection (73.0% &lt;i&gt;vs.&lt;/i&gt; 38.5%, P=0.001) during the course of COVID-19, nearly double that of the M/M group. In a multivariate logistic analysis, elevated CRP (&gt;41.8 mg/L), combined pulmonary fungal infection, and interstitial lung disease (ILD) as primary disease emerged as high-risk factors for developing the severe disease phenotype following Omicron variant infection in LTRs, with respective odds ORs values of 4.23 [95% confidence interval (CI): 1.68-11.23], 4.76 (95% CI: 1.59-15.64), and 5.13 (95% CI: 1.19-29.17). Receiver operating characteristic (ROC) curve analysis showed that CD4&lt;sup&gt;+&lt;/sup&gt; T lymphocyte count may be a strong marker for predicting death. At a cutoff of 404 cells/µL, sensitivity was 0.509, specificity 0.999, and area under the curve (AUC) was 0.806 (95% CI: 0.678-0.934). Ultimately, 13 recipients succumbed to COVID-19 related respiratory failure or secondary multiple organ dysfunction, resulting in an overall mortality rate of 7.3% (13/178).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;LTRs are at high risk of secondary lung infections after Omicron. Key risk factors for severe disease include CRP &gt;41.8 mg/L, ILD as primary d","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"576-592"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898398/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Erratum: KLRB1 expression is associated with lung adenocarcinoma prognosis and immune infiltration and regulates lung adenocarcinoma cell proliferation and metastasis through the MAPK/ERK pathway.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-27 DOI: 10.21037/jtd-2025b-01

[This corrects the article DOI: 10.21037/jtd-24-8.].

{"title":"Erratum: <i>KLRB1</i> expression is associated with lung adenocarcinoma prognosis and immune infiltration and regulates lung adenocarcinoma cell proliferation and metastasis through the MAPK/ERK pathway.","authors":"","doi":"10.21037/jtd-2025b-01","DOIUrl":"https://doi.org/10.21037/jtd-2025b-01","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.21037/jtd-24-8.].</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"1122-1125"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898371/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Prediction of ipsilateral and contralateral pneumothorax using a simple chest X-ray.
IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM Pub Date : 2025-02-28 Epub Date: 2025-02-24 DOI: 10.21037/jtd-24-1729
Kwanyong Hyun, Jae Jun Kim, Kyong Shil Im, Yoon Ho Kim, Jeong Hwan Ryu

Background: Accurate prediction is essential for the effective management of spontaneous pneumothorax (SP). To improve prediction, this study primarily focuses on using simple chest X-rays to predict ipsilateral recurrence and contralateral occurrence of SP.

Methods: All consecutive subjects diagnosed with SP from July 2017 to June 2023 were retrospectively reviewed. Ipsilateral recurrence and contralateral occurrence of SP within two years of completing treatment were analyzed. Using simple chest X-rays and clinical parameters such as age, sex, smoking, chronic obstructive pulmonary disease (COPD) and surgery, machine learning algorithms were applied to predict SP development. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to highlight the X-ray regions associated with SP development.

Results: The study included 1,086 cases of SP, with 546 right-side and 540 left-side developments. Surgeries were performed in 243 right and 204 left cases. Ipsilateral recurrence occurred in 93 cases total, while contralateral occurrence occurred in 60 right and 34 left cases. For predicting ipsilateral recurrence in the young group, gradient boosting (GB) [area under curve (AUC) of 0.686, accuracy of 0.769, F1 score of 0.733, precision of 0.706, and recall of 0.769] for the right side and logistic regression (AUC of 0.628, accuracy of 0.781, F1 score of 0.753, precision of 0.737, and recall of 0.781) for the left side were the top-performing models. In the older group, K-nearest neighbors (KNN) (AUC of 0.615, accuracy of 0.801, F1 score of 0.760, precision of 0.735, and recall of 0.801) for the right side and logistic regression (AUC of 0.623, accuracy of 0.824, F1 score of 0.804, precision of 0.794, and recall of 0.824) for the left side were the best models. For predicting contralateral occurrence in the young group, random forest (RF) (AUC of 0.597, accuracy of 0.774, F1 score of 0.741, precision of 0.709, and recall of 0.774) for the right side and KNN (AUC of 0.650, accuracy of 0.893, F1 score of 0.849, precision of 0.809, and recall of 0.893) for the left side were the most effective models. In the older group, logistic regression (AUC of 0.630, accuracy of 0.935, F1 score of 0.914, precision of 0.894, and recall of 0.935) for the right side and neural network (NN) (AUC of 0.765, accuracy of 0.961, F1 score of 0.948, precision of 0.936, and recall of 0.961) for the left side were the top performers. Grad-CAM analysis revealed that apical lung portions were strongly associated with both ipsilateral recurrence and contralateral occurrence of SP.

Conclusions: The results of this study suggest that machine learning algorithms using simple X-rays and basic clinical data can predict SP development with fair performance. The apical regions of the lung were strongly associated with SP development, consistent with clinical knowledge.

{"title":"Prediction of ipsilateral and contralateral pneumothorax using a simple chest X-ray.","authors":"Kwanyong Hyun, Jae Jun Kim, Kyong Shil Im, Yoon Ho Kim, Jeong Hwan Ryu","doi":"10.21037/jtd-24-1729","DOIUrl":"https://doi.org/10.21037/jtd-24-1729","url":null,"abstract":"<p><strong>Background: </strong>Accurate prediction is essential for the effective management of spontaneous pneumothorax (SP). To improve prediction, this study primarily focuses on using simple chest X-rays to predict ipsilateral recurrence and contralateral occurrence of SP.</p><p><strong>Methods: </strong>All consecutive subjects diagnosed with SP from July 2017 to June 2023 were retrospectively reviewed. Ipsilateral recurrence and contralateral occurrence of SP within two years of completing treatment were analyzed. Using simple chest X-rays and clinical parameters such as age, sex, smoking, chronic obstructive pulmonary disease (COPD) and surgery, machine learning algorithms were applied to predict SP development. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to highlight the X-ray regions associated with SP development.</p><p><strong>Results: </strong>The study included 1,086 cases of SP, with 546 right-side and 540 left-side developments. Surgeries were performed in 243 right and 204 left cases. Ipsilateral recurrence occurred in 93 cases total, while contralateral occurrence occurred in 60 right and 34 left cases. For predicting ipsilateral recurrence in the young group, gradient boosting (GB) [area under curve (AUC) of 0.686, accuracy of 0.769, F1 score of 0.733, precision of 0.706, and recall of 0.769] for the right side and logistic regression (AUC of 0.628, accuracy of 0.781, F1 score of 0.753, precision of 0.737, and recall of 0.781) for the left side were the top-performing models. In the older group, K-nearest neighbors (KNN) (AUC of 0.615, accuracy of 0.801, F1 score of 0.760, precision of 0.735, and recall of 0.801) for the right side and logistic regression (AUC of 0.623, accuracy of 0.824, F1 score of 0.804, precision of 0.794, and recall of 0.824) for the left side were the best models. For predicting contralateral occurrence in the young group, random forest (RF) (AUC of 0.597, accuracy of 0.774, F1 score of 0.741, precision of 0.709, and recall of 0.774) for the right side and KNN (AUC of 0.650, accuracy of 0.893, F1 score of 0.849, precision of 0.809, and recall of 0.893) for the left side were the most effective models. In the older group, logistic regression (AUC of 0.630, accuracy of 0.935, F1 score of 0.914, precision of 0.894, and recall of 0.935) for the right side and neural network (NN) (AUC of 0.765, accuracy of 0.961, F1 score of 0.948, precision of 0.936, and recall of 0.961) for the left side were the top performers. Grad-CAM analysis revealed that apical lung portions were strongly associated with both ipsilateral recurrence and contralateral occurrence of SP.</p><p><strong>Conclusions: </strong>The results of this study suggest that machine learning algorithms using simple X-rays and basic clinical data can predict SP development with fair performance. The apical regions of the lung were strongly associated with SP development, consistent with clinical knowledge.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 2","pages":"898-907"},"PeriodicalIF":2.1,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11898339/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Journal of thoracic disease
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1