During the COVID-19 pandemic, novel nanoparticle-based mRNA vaccines were developed. A small number of individuals developed allergic reactions to these vaccines although the mechanisms remain undefined.

Background It is increasingly recognized that interstitial lung abnormalities (ILAs) detected at CT have potential clinical implications, but automated identification of ILAs has not yet been fully established. Purpose To develop and test automated ILA probability prediction models using machine learning techniques on CT images. Materials and Methods This secondary analysis of a retrospective study included CT scans from patients in the Boston Lung Cancer Study collected between February 2004 and June 2017. Visual assessment of ILAs by two radiologists and a pulmonologist served as the ground truth. Automated ILA probability prediction models were developed that used a stepwise approach involving section inference and case inference models. The section inference model produced an ILA probability for each CT section, and the case inference model integrated these probabilities to generate the case-level ILA probability. For indeterminate sections and cases, both two- and three-label methods were evaluated. For the case inference model, we tested three machine learning classifiers (support vector machine [SVM], random forest [RF], and convolutional neural network [CNN]). Receiver operating characteristic analysis was performed to calculate the area under the receiver operating characteristic curve (AUC). Results A total of 1382 CT scans (mean patient age, 67 years ± 11 [SD]; 759 women) were included. Of the 1382 CT scans, 104 (8%) were assessed as having ILA, 492 (36%) as indeterminate for ILA, and 786 (57%) as without ILA according to ground-truth labeling. The cohort was divided into a training set ( = 96; ILA, = 48), a validation set ( = 24; ILA, = 12), and a test set ( = 1262; ILA, = 44). Among the models evaluated (two- and three-label section inference models; two- and three-label SVM, RF, and CNN case inference models), the model using the three-label method in the section inference model and the two-label method and RF in the case inference model achieved the highest AUC, at 0.87. Conclusion The model demonstrated substantial performance in estimating ILA probability, indicating its potential utility in clinical settings. © RSNA, 2024 See also the editorial by Zagurovskaya in this issue.

The number of new cancer cases in Commonwealth countries rose by 35% between 2008 and 2018, but progress in cancer control has been slow in many low-income and lower-middle-income member states. We aimed to examine cancer outcomes and priority areas in the Commonwealth to provide insight and guidance on prioritisation of efforts to improve cancer survival and make the best use of scarce resources.

Antiretroviral therapy (ART) is recommended for all people with HIV. Understanding ART use among Medicare beneficiaries with HIV is therefore critically important for improving quality and equity of care among the growing population of older adults with HIV. However, a comprehensive national evaluation of filled ART prescriptions among Medicare beneficiaries is lacking.

Hypertension is highly prevalent in India, but the proportion of patients achieving blood pressure control remains low. Efforts have been made to expand health insurance coverage nationwide with the aim of improving overall healthcare access. It is critical to understand the role of health insurance coverage in improving hypertension care.

The World Health Organization (WHO) recently launched the Global Initiative for Childhood Cancer (GICC), with the goal of attaining at least 60% cancer survival for children worldwide by the year 2030. This study aims to describe the global patterns of childhood cancer survival in 2019 to help guide progress in attaining the GICC target goal. In this ecological, cross-sectional study, we used 5-year net childhood cancer survival (2015-2019) data from a prior micro-modeling study from 197 countries and territories. Descriptive statistics were used to analyze the patterns of overall childhood cancer survival and survival for each of the six cancer tracer diagnoses as proposed by the GICC. We used hot spot analysis to identify geographic clusters of high and low cancer survival. Most high-income countries reached at least 60% (92%, n = 59/64), net childhood cancer survival at baseline. No lower-middle-income or low-income country reached at least 60% overall cancer survival at baseline. The South-East Asia region had the highest proportion of countries that did not achieve at least 60% survival at baseline (100%, n = 10/10), followed by the African region (98%, n = 49/50). For each cancer tracer diagnosis, we found the highest number of countries that have achieved at least 60% survival was for Burkitt lymphoma (44%, n = 87/197) followed by acute lymphocytic leukemia (41%, n = 80/197).Hot spot analysis showed the highest overall survival was concentrated in North America and Europe, while the lowest survival was concentrated in Sub-Saharan Africa and South-East Asia.A majority of LMICs had not reached the WHO target goal of at least 60% survival from childhood cancer at baseline in 2019, with variable success for the six childhood cancer tracer diagnoses of the GICC. These findings provide baseline assessment of individual country performance to help achieve the GICC goal of 60% overall cancer survival globally by 2030.