Sex-specific incidence of hepatitis B virus flares among Bcr-Abl tyrosine kinase inhibitor users in Taiwan.

BACKGROUND: The use of Bcr-Abl TKI was found to be associated with hepatitis B (HBV) flares, with a more profound risk observed in females. This study was conducted to characterize the clinical features of patients with HBV flare among Bcr-Abl TKI users, to estimate sex-specific incidence rates of HBV flare, and to evaluate potential cumulative effect of Bcr-Abl TKI. METHODS: Bcr-Abl TKI users with chronic HBV infection were identified from Taiwan's National Health Insurance database. The HBV flare cases were identified within the cohort. Incidence rates of HBV flare between men and women were assessed. Nested case-control analysis was used to evaluate the cumulative effect of Bcr-Abl TKI use on HBV flare. RESULTS: Among 415 patients with chronic HBV infection treated with Bcr-Abl TKI from 2005 through 2018, 45 flare cases (28 males and 17 females) were identified. Days between Bcr-Abl TKI initiation and HBV flare was 319 days in women compared to 610 days in men. 66.7% of the flares occurred during TKI therapy. Twelve of the 45 patients died, half of them died around 6 months after hepatitis B flare. Incidence rates of HBV flare were 2.34 and 3.33 per 100 person-years in males and females, respectively. Higher incidence was observed among patients with chronic myeloid leukemia. Cumulative effect of Bcr-Abl TKI on HBV flare was not observed. CONCLUSION: Approximately 10% of HBV carriers who used Bcr-Abl TKI experienced HBV flare in Taiwan. The risk was higher in women and among patients with chronic myeloid leukemia.

Deep learning-based classification for lung opacities in chest x-ray radiographs through batch control and sensitivity regulation.

In this study, we implemented a system to classify lung opacities from frontal chest x-ray radiographs. We also proposed a training method to address the class imbalance problem presented in the dataset. We participated in the Radiological Society of America (RSNA) 2018 Pneumonia Detection Challenge and used the datasets provided by the RSNA for further research. Using convolutional neural networks, we implemented a training procedure termed batch control to manipulate the data distribution of positive and negative cases in each training batch. The batch control method regulated and stabilized the performance of the deep-learning models, allowing the adaptive sensitivity of the network models to meet the specific application. The convolutional neural network is practical for classifying lung opacities on chest x-ray radiographs. The batch control method is advantageous for sensitivity regulation and optimization for class-unbalanced datasets.