Using Vision Transformer for high robustness and generalization in predicting EGFR mutation status in lung adenocarcinoma.

BACKGROUND: Lung adenocarcinoma is a common cause of cancer-related deaths worldwide, and accurate EGFR genotyping is crucial for optimal treatment outcomes. Conventional methods for identifying the EGFR genotype have several limitations. Therefore, we proposed a deep learning model using non-invasive CT images to predict EGFR mutation status with robustness and generalizability. METHODS: A total of 525 patients were enrolled at the local hospital to serve as the internal data set for model training and validation. In addition, a cohort of 30 patients from the publicly available Cancer Imaging Archive Data Set was selected for external testing. All patients underwent plain chest CT, and their EGFR mutation status labels were categorized as either mutant or wild type. The CT images were analyzed using a self-attention-based ViT-B/16 model to predict the EGFR mutation status, and the model's performance was evaluated. To produce an attention map indicating the suspicious locations of EGFR mutations, Grad-CAM was utilized. RESULTS: The ViT deep learning model achieved impressive results, with an accuracy of 0.848, an AUC of 0.868, a sensitivity of 0.924, and a specificity of 0.718 on the validation cohort. Furthermore, in the external test cohort, the model achieved comparable performances, with an accuracy of 0.833, an AUC of 0.885, a sensitivity of 0.900, and a specificity of 0.800. CONCLUSIONS: The ViT model demonstrates a high level of accuracy in predicting the EGFR mutation status of lung adenocarcinoma patients. Moreover, with the aid of attention maps, the model can assist clinicians in making informed clinical decisions.

Associations of blood cadmium and lead concentrations with all-cause mortality in US adults with chronic obstructive pulmonary disease.

BACKGROUND: Some literature indicates an association between exposure to cadmium and lead and the presence of emphysema and chronic bronchitis, which are the two primary components of COPD. Understanding whether there is a potential association between cadmium and lead exposure and higher mortality rates in individuals with COPD could provide profound insights into the long-term effects of these two metal exposures on human health. METHODS: This study included 2024 patients with COPD in the US from the NHANES from 1999 through 2016 who were followed up to 2019. Multivariable Cox regression models were used to calculate HRs and 95 % CIs for all-cause mortality in relation to blood cadmium and lead concentrations. Plotting Kaplan-Meier curves and Restricted cubic spline curves to visualize results. Furthermore, stratified and sensitivity analyses were conducted. RESULTS: After multivariate adjustment, blood cadmium and blood lead concentrations were independently associated with an increased risk of all-cause mortality. Compared with the first tertile, the HRs of all-cause mortality associated with the blood cadmium concentration were 1.74 (95 % CI, 1.22-2.49) in the second tertile and 1.89 (95 % CI, 1.31-2.72) in the third tertile. The HRs of all-cause mortality associated with the blood lead concentration were 1.13 (95 % CI, 0.84-1.51) in the second tertile and 1.43 (95 % CI, 1.05-1.93) in the third tertile. CONCLUSION: This study found that increased blood cadmium and blood lead concentrations were associated with increased all-cause mortality in COPD patients. Reducing cadmium and lead exposure could potentially mitigate mortality risk in these individuals. More prospective studies are needed in the future to demonstrate our findings.

Associations between the muscle quality index and adult lung functions from NHANES 2011-2012.

Background: The muscle quality index (MQI), as an important component of sarcopenia, is defined as the ratio of muscle strength to muscle mass. Lung function, is a clinical indicator to assess ventilation and air exchange function. This study investigated the relationship between lung function indices and MQI in the NHANES database from 2011 to 2012. Methods: This study included 1,558 adults from the National Health and Nutrition Examination Survey from 2011 to 2012. Muscle mass and muscle strength were assessed using DXA and handgrip strength, and all participants underwent pulmonary function measurements. Multiple linear regression and multivariable logistic regression were used to assess the correlation between the MQI and lung function indices. Results: In the adjusted model, MQI was significantly correlated with FVC% and PEF%. And, after quartiles of MQI in Q3, where FEV1%, FVC%, and PEF% were all associated with MQI, in Q4, a lower relative risk of a restrictive spirometry pattern was linked to increased MQI. Compared to the lower age group, the relationship between the MQI and lung function indices was more significant in the higher age group. Conclusion: There was an association between the MQI and lung function indices. Furthermore, in the middle-aged and older adult populations, lung function indicators and restrictive ventilation impairment were significantly associated with MQI. This implies that improving lung function through muscle training may be beneficial to this group.

Oxidative balance score was negatively associated with the risk of metabolic syndrome, metabolic syndrome severity, and all-cause mortality of patients with metabolic syndrome.

Background: The oxidative balance score (OBS), an encompassing scoring mechanism for assessing oxidative stress, is formulated based on nutritional and lifestyle components. The emergence of metabolic syndrome (MetS) is intricately linked to oxidative stress. Nonetheless, the correlation between OBS and MetS displays variability within distinct cohorts. Objective: We worked on the relationships between OBS and the risk of MetS, MetS severity, and all-cause mortality of MetS patients. Methods: A total of 11,171 adult participants were collected from the U.S. National Health Examination Survey (NHANES) 2007-2018. Employing survey-weighted logistic models, we evaluated the relationship between OBS and MetS risk. Furthermore, survey-weighted linear models were utilized to investigate the connection between OBS and MetS severity. Among the participants, 3,621 individuals had their survival status recorded, allowing us to employ Cox proportional hazards regression models in order to ascertain the association between OBS and the all-cause mortality within the subset of individuals with MetS. The OBS (where a higher OBS signified an increased prevalence of anti- or pro-oxidant exposures) weighed the 20 factors, while the MetS severity score weighed the five factors. Results: After multivariable adjustment, individuals with elevated OBS were found to exhibit a decreased susceptibility to MetS [odds ratio (OR) 0.95; 95% CI 0.94-0.96]. The adjusted OR was 0.42 (95% CI 0.33-0.53) for MetS risk in the fourth OBS quartile compared with those in the first OBS quartile (P for trend < 0.001). A one-unit increase in OBS was linked to a 3% reduction in MetS severity score by 3% (mean difference, -0.03; 95% CI, -0.04 to -0.03). Moreover, increased OBS correlated with decreased hazard of all-cause mortality risk among MetS subjects (adjusted hazard ratio, 0.95; 95% CI, 0.93-0.98). These associations retained their strength even subsequent to the introduction of sensitivity analyses. There existed a statistically significant negative correlation between diet/lifestyle OBS and both MetS risk as well as MetS severity. Conclusions: An inverse correlation was observed between OBS and the susceptibility to MetS, MetS severity, and all-cause mortality of MetS patients. Health outcomes for MetS patients were positively related to antioxidant diets and lifestyles.