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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This study presents an application of machine learning (ML) methods fordetecting the presence of stenoses and aneurysms in the human arterial system.Four major forms of arterial disease -- carotid artery stenosis (CAS),subclavian artery stenosis (SAC), peripheral arterial disease (PAD), andabdominal aortic aneurysms (AAA) -- are considered. The ML methods are trainedand tested on a physiologically realistic virtual patient database (VPD)containing 28,868 healthy subjects, which is adapted from the authors previouswork and augmented to include the four disease forms. Six ML methods -- NaiveBayes, Logistic Regression, Support Vector Machine, Multi-layer Perceptron,Random Forests, and Gradient Boosting -- are compared with respect toclassification accuracies and it is found that the tree-based methods of RandomForest and Gradient Boosting outperform other approaches. The performance of MLmethods is quantified through the F1 score and computation of sensitivities andspecificities. When using all the six measurements, it is found that maximum F1scores larger than 0.9 are achieved for CAS and PAD, larger than 0.85 for SAS,and larger than 0.98 for both low- and high-severity AAAs. Correspondingsensitivities and specificities are larger than 90% for CAS and PAD, largerthan 85% for SAS, and larger than 98% for both low- and high-severity AAAs.When reducing the number of measurements, it is found that the performance isdegraded by less than 5% when three measurements are used, and less than 10%when only two measurements are used for classification. For AAA, it is shownthat F1 scores larger than 0.85 and corresponding sensitivities andspecificities larger than 85% are achievable when using only a singlemeasurement. The results are encouraging to pursue AAA monitoring and screeningthrough wearable devices which can reliably measure pressure or flow-rates

Machine learning for detection of stenoses and aneurysms: application in a physiologically realistic virtual patient database