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

In this paper we are interested in the prediction of preterm birth based ondiagnosis codes from longitudinal EHR. We formulate the prediction problem as asupervised classification with noisy labels. Our base classifier is a RecurrentNeural Network with an attention mechanism. We assume the availability of adata subset with both noisy and clean labels. For the cohort definition, mostof the diagnosis codes on mothers' records related to pregnancy are ambiguousfor the definition of full-term and preterm classes. On the other hand,diagnosis codes on babies' records provide fine-grained information onprematurity. Due to data de-identification, the links between mothers andbabies are not available. We developed a heuristic based on admission anddischarge times to match babies to their mothers and hence enrich mothers'records with additional information on delivery status. The obtained additionaldataset from the matching heuristic has noisy labels and was used to leveragethe training of the deep learning model. We propose an Alternating LossCorrection (ALC) method to train deep models with both clean and noisy labels.First, the label corruption matrix is estimated using the data subset with bothnoisy and clean labels. Then it is used in the model as a dense output layer tocorrect for the label noise. The network is alternately trained on epochs withthe clean dataset with a simple cross-entropy loss and on next epoch with thenoisy dataset and a loss corrected with the estimated corruption matrix. Theexperiments for the prediction of preterm birth at 90 days before deliveryshowed an improvement in performance compared with baseline and stateof-the-art methods.

Alternating Loss Correction for Preterm-Birth Prediction from EHR Data with Noisy Labels