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

The automated analysis of medical time series, such as the electrocardiogram(ECG), electroencephalogram (EEG), pulse oximetry, etc, has the potential toserve as a valuable tool for diagnostic decisions, allowing for remotemonitoring of patients and more efficient use of expensive and time-consumingmedical procedures. Deep neural networks (DNNs) have been demonstrated toprocess such signals effectively. However, previous research has primarilyfocused on classifying medical time series rather than attempting to regressthe continuous-valued physiological parameters central to diagnosis. Onesignificant challenge in this regard is the imbalanced nature of the dataset,as a low prevalence of abnormal conditions can lead to heavily skewed data thatresults in inaccurate predictions and a lack of certainty in such predictionswhen deployed. To address these challenges, we propose HypUC, a framework forimbalanced probabilistic regression in medical time series, making severalcontributions. (i) We introduce a simple kernel density-based technique totackle the imbalanced regression problem with medical time series. (ii)Moreover, we employ a probabilistic regression framework that allowsuncertainty estimation for the predicted continuous values. (iii) We alsopresent a new approach to calibrate the predicted uncertainty further. (iv)Finally, we demonstrate a technique to use calibrated uncertainty estimates toimprove the predicted continuous value and show the efficacy of the calibrateduncertainty estimates to flag unreliable predictions. HypUC is evaluated on alarge, diverse, real-world dataset of ECGs collected from millions of patients,outperforming several conventional baselines on various diagnostic tasks,suggesting a potential use-case for the reliable clinical deployment of deeplearning models.

HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiograms