The context of rapid global environmental change underscores the pressing necessity to investigate the environmental factors and high-risk areas that contribute to the occurrence of brucellosis. In this study, a maximum entropy (MaxEnt) model was employed to analyze the factors influencing brucellosis in the Aksu Prefecture from 2014 to 2023. A distributed lag nonlinear model (DLNM) was employed to investigate the lagged effect of meteorological factors on the occurrence of brucellosis. A total of 17 environmental factors were identified as affecting the distribution of brucellosis to varying degrees. The largest contributing was the normalized difference vegetation index (NDVI), followed by gross domestic product (GDP), and then meteorological factors such as average temperature, average relative humidity, and average wind speed. The receiver operating characteristic (ROC) curve demonstrated that the MaxEnt model exhibited a high degree of predictive efficacy, with an area under the curve (AUC) value of 0.921. The impact of high temperature (25℃ with a 2-month lag, RR = 3.130, 95% CI 1.642 ~ 5.965), low relative humidity (28% with a 2.5-month lag, RR = 1.795, 95% CI 1.298 ~ 2.483), and low wind speed (1.9 m/s with a 0-month lag, RR = 2.408, 95% CI 1.360 ~ 4.264) are the most significant meteorological factors associated with the incidence of brucellosis. The trends in the impact of extreme meteorological conditions on the spread of brucellosis were found to be generally consistent. Stratified analyses indicated that males were more affected by meteorological factors than females. The prevalence of brucellosis is influenced by a range of socio-economic and meteorological factors, and a multifaceted approach is necessary to prevent and control brucellosis.
Efficient and rapid auxiliary diagnosis of different grades of lung adenocarcinoma is conducive to helping doctors accelerate individualized diagnosis and treatment processes, thus improving patient prognosis. Currently, there is often a problem of large intra-class differences and small inter-class differences between pathological images of lung adenocarcinoma tissues under different grades. If attention mechanisms such as Coordinate Attention (CA) are directly used for lung adenocarcinoma grading tasks, it is prone to excessive compression of feature information and overlooking the issue of information dependency within the same dimension. Therefore, we propose a Dimension Information Embedding Attention Network (DIEANet) for the task of lung adenocarcinoma grading. Specifically, we combine different pooling methods to automatically select local regions of key growth patterns such as lung adenocarcinoma cells, enhancing the model's focus on local information. Additionally, we employ an interactive fusion approach to concentrate feature information within the same dimension and across dimensions, thereby improving model performance. Extensive experiments have shown that under the condition of maintaining equal computational expenses, the accuracy of DIEANet with ResNet34 as the backbone reaches 88.19%, with an AUC of 96.61%, MCC of 81.71%, and Kappa of 81.16%. Compared to seven other attention mechanisms, it achieves state-of-the-art objective metrics. Additionally, it aligns more closely with the visual attention of pathology experts under subjective visual assessment.