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

Standard objective functions used during the training of neural-network-basedpredictive models do not consider clinical criteria, leading to models that arenot necessarily clinically acceptable. In this study, we look at this problemfrom the perspective of the forecasting of future glucose values for diabeticpeople. In this study, we propose the coherent mean squared glycemic error(gcMSE) loss function. It penalizes the model during its training not only ofthe prediction errors, but also on the predicted variation errors which isimportant in glucose prediction. Moreover, it makes possible to adjust theweighting of the different areas in the error space to better focus ondangerous regions. In order to use the loss function in practice, we propose analgorithm that progressively improves the clinical acceptability of the model,so that we can achieve the best tradeoff possible between accuracy and givenclinical criteria. We evaluate the approaches using two diabetes datasets, onehaving type-1 patients and the other type-2 patients. The results show thatusing the gcMSE loss function, instead of a standard MSE loss function,improves the clinical acceptability of the models. In particular, theimprovements are significant in the hypoglycemia region. We also show that thisincreased clinical acceptability comes at the cost of a decrease in the averageaccuracy of the model. Finally, we show that this tradeoff between accuracy andclinical acceptability can be successfully addressed with the proposedalgorithm. For given clinical criteria, the algorithm can find the optimalsolution that maximizes the accuracy while at the same meeting the criteria.

Integration of Clinical Criteria into the Training of Deep Models: Application to Glucose Prediction for Diabetic People