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

Objective: This work proposes a semi-supervised training approach fordetecting lung and heart sounds simultaneously with only one trained model andin invariance to the auscultation point. Methods: We use open-access data fromthe 2016 Physionet/CinC Challenge, the 2022 George Moody Challenge, and fromthe lung sound database HF_V1. We first train specialist single-task modelsusing foreground ground truth (GT) labels from different auscultation databasesto identify background sound events in the respective lung and heartauscultation databases. The pseudo-labels generated in this way were combinedwith the ground truth labels in a new training iteration, such that a new modelwas subsequently trained to detect foreground and background signals. Benchmarktests ensured that the newly trained model could detect both, lung, and heartsound events in different auscultation sites without regressing on the originaltask. We also established hand-validated labels for the respective backgroundsignal in heart and lung sound auscultations to evaluate the models. Results:In this work, we report for the first time results for i) a multi-classprediction for lung sound events and ii) for simultaneous detection of heartand lung sound events and achieve competitive results using only one model. Thecombined multi-task model regressed slightly in heart sound detection andgained significantly in lung sound detection accuracy with an overall macro F1score of 39.2% over six classes, representing a 6.7% improvement over thesingle-task baseline models. Conclusion/Significance: To the best of ourknowledge, this is the first approach developed to date for measuring heart andlung sound events invariant to both, the auscultation site and capturingdevice. Hence, our model is capable of performing lung and heart sounddetection from any auscultation location.

Training one model to detect heart and lung sound events from single point auscultations