Plos One
-
Acute kidney injury (AKI) is a common complication after surgery that is associated with increased morbidity and mortality. The majority of existing perioperative AKI risk prediction models are limited in their generalizability and do not fully utilize intraoperative physiological time-series data. Thus, there is a need for intelligent, accurate, and robust systems to leverage new information as it becomes available to predict the risk of developing postoperative AKI. ⋯ Postoperative AKI prediction was improved with high sensitivity and specificity through a machine learning approach that dynamically incorporated intraoperative data.
-
A large body of research shows that social isolation and loneliness have detrimental health consequences. Identifying individuals at risk of social isolation or loneliness is, therefore, important. The objective of this study was to examine personal (e.g., sex, income) and geographic (rural/urban and sociodemographic) factors and their association with social isolation and loneliness in a national sample of Canadians aged 45 to 85 years. ⋯ The findings indicate that socially isolated individuals are, to some extent, clustered into areas with a high proportion of low-income older adults, suggesting that support and resources could be targeted at these areas. For loneliness, the focus may be less on where people live, but rather on personal characteristics that place individuals at risk.
-
Bloodstream infections in critically ill require a speeded-up microbiological diagnosis to improve clinical outcomes. In this pre-post intervention study, we evaluated how a molecular identification test directly performed on positive blood cultures of critically ill improves patient's therapeutic management. ⋯ FA-BCID testing drastically reduced time to optimal antimicrobial treatment in critically ill with bloodstream infections.
-
Mental health recovery narratives are stories of recovery from mental health problems. Narratives may impact in helpful and harmful ways on those who receive them. The objective of this paper is to develop a change model identifying the range of possible impacts and how they occur. ⋯ Interventions that incorporate the use of recovery narratives, such as peer support, anti-stigma campaigns and bibliotherapy, can use the change model to maximise benefit and minimise harms from narratives. Interventions should incorporate a diverse range of narratives available through different mediums to enable a range of recipients to connect with and benefit from this material. Service providers using recovery narratives should preserve authenticity so as to maximise impact, for example by avoiding excessive editing.
-
Robust Artificial-neural-networks for k-space Interpolation (RAKI) is a recently proposed deep-learning-based reconstruction algorithm for parallel imaging. Its main premise is to perform k-space interpolation using convolutional neural networks (CNNs) trained on subject-specific autocalibration signal (ACS) data. Since training is performed individually for each subject, the reconstruction time is longer than approaches that pre-train on databases. In this study, we sought to reduce the computational time of RAKI. ⋯ The proposed implementations of RAKI bring the computational time towards clinically acceptable ranges. The new CNN architecture yields faster training, albeit at a slight performance loss, which may be acceptable for faster visualization in some settings.