English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a robust in-time predictor for in-hospital COVID-19 patient'sprobability of requiring mechanical ventilation. A challenge in the riskprediction for COVID-19 patients lies in the great variability and irregularsampling of patient's vitals and labs observed in the clinical setting.Existing methods have strong limitations in handling time-dependent features'complex dynamics, either oversimplifying temporal data with summary statisticsthat lose information or over-engineering features that lead to less robustoutcomes. We propose a novel in-time risk trajectory predictive model to handlethe irregular sampling rate in the data, which follows the dynamics of risk ofperforming mechanical ventilation for individual patients. The modelincorporates the Multi-task Gaussian Process using observed values to learn theposterior joint multi-variant conditional probability and infer the missingvalues on a unified time grid. The temporal imputed data is fed into amulti-objective self-attention network for the prediction task. A novelpositional encoding layer is proposed and added to the network for producingin-time predictions. The positional layer outputs a risk score at eachuser-defined time point during the entire hospital stay of an inpatient. Weframe the prediction task into a multi-objective learning framework, and therisk scores at all time points are optimized altogether, which adds robustnessand consistency to the risk score trajectory prediction. Our experimentalevaluation on a large database with nationwide in-hospital patients withCOVID-19 also demonstrates that it improved the state-of-the-art performance interms of AUC (Area Under the receiver operating characteristic Curve) and AUPRC(Area Under the Precision-Recall Curve) performance metrics, especially atearly times after hospital admission.

Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network