End-to-end deep-learning model for the detection of coronary artery stenosis on coronary CT images.

Purpose: We examined whether end-to-end deep-learning models could detect moderate (≥50%) or severe (≥70%) stenosis in the left anterior descending artery (LAD), right coronary artery (RCA) or left circumflex artery (LCX) in iodine contrast-enhanced ECG-gated coronary CT angiography (CCTA) scans.

Methods: From a database of 6293 CCTA scans, we used pre-existing curved multiplanar reformations (CMR) images of the LAD, RCA and LCX arteries to create end-to-end deep-learning models for the detection of moderate or severe stenoses. We preprocessed the images by exploiting domain knowledge and employed a transfer learning approach using EfficientNet, ResNet, DenseNet and Inception-ResNet, with a class-weighted strategy optimised through cross-validation.

A Swedish dietary guideline index, gut microbial α-diversity and prevalence of metabolic syndrome - observations in the Swedish CArdioPulmonary bioImage Study (SCAPIS).

Background: Metabolic syndrome (MetS) is characterized by coexisting risk factors for type 2 diabetes and cardiovascular disease. Diet is of importance in their aetiology, and gut microbiota (GM) may constitute a link between diet and metabolic health. Understanding the interplay between diet and GM could contribute novel insights for future dietary guidelines, and aid in preventive actions to motivate adherence to dietary guidelines.

Cardiac biomarkers for detection of coronary artery disease in the community.

To investigate whether coronary artery disease (CAD) burden is associated with plasma levels of the myocardial biomarkers Troponin I (TropI) and NT-proBNP in a large population-based sample using a cross-sectional design. Coronary computerized tomography (CT) angiography was performed in 25,859 subjects without a history of atherosclerotic disease from SCAPIS study (age 50-65, 52% women). TropI and NT-proBNP were measured in plasma.

The effectiveness of a problem-solving intervention with workplace involvement on self-reported sick leave, psychological symptoms and work ability: a cluster randomised clinical trial.

Background: Problem-solving interventions with workplace involvement (PSI-WPI) have been shown to reduce sick leave and increase return to work in an occupational health services context. However, many employees struggle with reduced work functioning, anxiety-, and depressive symptoms up to 12 months after a sick leave episode, and it is unclear if the intervention affects outcomes other than sick leave. The aim of this study is to investigate if a PSI-WPI added to care as usual (CAU) is superior to CAU with respect to self-reported sick leave, psychological symptoms, work ability, work performance, and health after RTW when provided in primary care.