JAMA network open
-
The longer-term risk of rehospitalizations and death of adult sepsis survivors is associated with index sepsis illness characteristics. ⋯ The prognostic score reported in this study uses 8 internationally feasible predictors measured during the index sepsis admission and provides clinically useful information on sepsis survivors' risk of unplanned rehospitalization or death in the first year after hospital discharge.
-
Deep learning, a family of machine learning models that use artificial neural networks, has achieved great success at predicting outcomes in nonmedical domains. ⋯ In this study, deep learning RNN models outperformed conventional LR models, suggesting that RNN models could be used to identify patients with HCV-related cirrhosis with a high risk of developing HCC for risk-based HCC outreach and surveillance strategies.
-
Life expectancy has decreased in the US, driven largely by increases in drug poisoning, suicide, and alcohol-induced deaths. Assessing whether patterns of these causes differ is required to inform public health interventions. ⋯ This cross-sectional study found that demographic characteristics and geographic patterns varied by cause of death, suggesting that increasing death rates from these causes were not concentrated in 1 group or region. Specialized interventions tailored for the underlying drivers of each cause of death are urgently needed.
-
Living in areas with more vegetation (referred to as residential greenness) may be associated with cardiovascular disease (CVD), but little data are available from low- and middle-income countries. In addition, it remains unclear whether the presence of cardiometabolic disorders modifies or mediates the association between residential greenness and CVD. ⋯ In this cross-sectional study, higher residential greenness levels were associated with lower CVD prevalence, and this association may be partially mediated by the presence of cardiometabolic disorders. Further studies, preferably longitudinal, are warranted to confirm these findings.
-
Some patients are avoiding essential care for fear of contracting coronavirus disease 2019 (COVID-19) in hospitals. There are few data, however, on the risk of acquiring COVID-19 in US hospitals. ⋯ In this cohort study of patients in a large academic medical center with rigorous infection control measures, nosocomial COVID-19 was rare during the height of the pandemic in the region. These findings may inform practices in other institutions and provide reassurance to patients concerned about contracting COVID-19 in hospitals.