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

Acceleration of machine learning research in healthcare is challenged by lackof large annotated and balanced datasets. Furthermore, dealing with measurementinaccuracies and exploiting unsupervised data are considered to be central toimproving existing solutions. In particular, a primary objective in predictivemodeling is to generalize well to both unseen variations within the observedclasses, and unseen classes. In this work, we consider such a challengingproblem in machine learning driven diagnosis: detecting a gamut ofcardiovascular conditions (e.g. infarction, dysrhythmia etc.) from limitedchannel ECG measurements. Though deep neural networks have achievedunprecedented success in predictive modeling, they rely solely ondiscriminative models that can generalize poorly to unseen classes. We arguethat unsupervised learning can be utilized to construct effective latent spacesthat facilitate better generalization. This work extensively compares thegeneralization of our proposed approach against a state-of-the-art deeplearning solution. Our results show significant improvements in F1-scores.

Generalization Studies of Neural Network Models for Cardiac Disease Detection Using Limited Channel ECG