Background: COPD is a respiratory disease caused by a combination of genetic and environmental factors. Polymorphism, as a genetic factor, can affect the susceptibility of the disease of COPD. In this study, we assessed the relationship between the polymorphisms of three genes and COPD risk in a Chinese Han population. Patients and Methods: A total of 376 patients diagnosed with COPD and 284 control subjects were enrolled in this study. Multivariate logistic regression analysis was used to analyze the association between three polymorphisms (SMAD4 rs10502913, IL-4 rs2070874, HSPA1L rs2227956) and COPD susceptibility. Results: The SMAD4 rs10502913 GG and AG genotype significantly increased COPD risk (adjusted OR = 2.235, 95% CI 1.198– 4.104; adjusted OR = 2.218, 95% CI 1.204– 4.151, respectively) compared with the AA genotype. In the stratification analyses, the GG genotype significantly increased the risk of COPD in subjects aged 60 and over (adjusted OR = 2.519, 95% CI 1.266– 5.015) and with a smoking history of less than 30 years (p=0.009; adjusted OR = 3.751; 95% CI 1.398– 10.062). This increased risk was more pronounced in the group of GOLD I and GOLD II (adjusted OR = 3.628, 95% CI 1.022– 12.885; adjusted OR = 2.394, 95% CI 1.004– 5.710, respectively). In addition, AG genotype was associated with an increased COPD risk in subjects aged 60 and over (adjusted OR = 2.599, 95% CI 1.304– 5.176) and in smokers (p=0.021; adjusted OR = 2.269; 95% CI 1.132– 4.548). This increased risk was more obvious in the group of GOLD III COPD (p=0.047; adjusted OR = 2.532; 95% CI 1.012– 6.336). Conclusion: Our present study indicated that the genotype GG and AG of SMAD4 rs10502913 are associated with an increased risk of COPD in a Chinese Han population. Further validation studies with large-scale populations are needed to confirm our findings.
Purpose:: : The purpose of the passage is to introduce and describe NATMIL (Neighborhood Attention Transformer Multiple Instance Learning), an innovative deep learning approach aimed at improving the classification of tumor cells and subtypes in whole slide images (WSIs) of tissue section biopsies for diagnosing cancer. Method:: The method involves leveraging dependencies among WSI tiles using the Neighborhood Attention Transformer, which incorporates contextual constraints as prior knowledge into multiple instance learning models. The approach utilizes weakly supervised methods, classifying WSIs using image parts or tiles along with attention ratings, to address the limitations of traditional methods. Result:: NATMIL has demonstrated superior performance compared to other weakly supervised algorithms when subtyping non-small cell lung cancer (NSLC) and lymph node (LN) tumors. The accuracy values achieved on the Camelyon dataset reached 89.6\% and 88.1\% for TCGA-LUSC. The introduction of NATMIL presents an effective and scalable sliding window attention technique for vision, known as Neighborhood Attention, which improves performance and reduces the burden on pathologists while making more data available. Conclusion:: NATMIL's success in improving tumor-level classifications by considering the interdependence of nearby tiles in histopathological pictures highlights its potential to enhance cancer diagnosis. By incorporating contextual constraints and leveraging dependencies among WSI tiles, NATMIL demonstrates promising results in improving accuracy and reducing false positives and negatives, thus advancing the field of cancer diagnosis through deep learning-based approaches.