FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089240207> ?p ?o ?g. }

• W3089240207 abstract "Standard objective functions used during the training of neural-network-based predictive models do not consider clinical criteria, leading to models that are not necessarily clinically acceptable. In this study, we look at this problem from the perspective of the forecasting of future glucose values for diabetic people. In this study, we propose the coherent mean squared glycemic error (gcMSE) loss function. It penalizes the model during its training not only of the prediction errors, but also on the predicted variation errors which is important in glucose prediction. Moreover, it makes possible to adjust the weighting of the different areas in the error space to better focus on dangerous regions. In order to use the loss function in practice, we propose an algorithm that progressively improves the clinical acceptability of the model, so that we can achieve the best tradeoff possible between accuracy and given clinical criteria. We evaluate the approaches using two diabetes datasets, one having type-1 patients and the other type-2 patients. The results show that using the gcMSE loss function, instead of a standard MSE loss function, improves the clinical acceptability of the models. In particular, the improvements are significant in the hypoglycemia region. We also show that this increased clinical acceptability comes at the cost of a decrease in the average accuracy of the model. Finally, we show that this tradeoff between accuracy and clinical acceptability can be successfully addressed with the proposed algorithm. For given clinical criteria, the algorithm can find the optimal solution that maximizes the accuracy while at the same meeting the criteria." @default.
• W3089240207 created "2020-10-01" @default.
• W3089240207 creator A5038934826 @default.
• W3089240207 creator A5039660232 @default.
• W3089240207 creator A5043602666 @default.
• W3089240207 date "2020-09-21" @default.
• W3089240207 modified "2023-09-27" @default.
• W3089240207 title "Integration of Clinical Criteria into the Training of Deep Models: Application to Glucose Prediction for Diabetic People" @default.
• W3089240207 cites W1980337932 @default.
• W3089240207 cites W1997188340 @default.
• W3089240207 cites W2003274998 @default.
• W3089240207 cites W2016210396 @default.
• W3089240207 cites W2019652008 @default.
• W3089240207 cites W2031534975 @default.
• W3089240207 cites W2035857772 @default.
• W3089240207 cites W2101539208 @default.
• W3089240207 cites W2116146322 @default.
• W3089240207 cites W2126105956 @default.
• W3089240207 cites W2146588145 @default.
• W3089240207 cites W2523526638 @default.
• W3089240207 cites W2754879033 @default.
• W3089240207 cites W2810149880 @default.
• W3089240207 cites W2889087356 @default.
• W3089240207 cites W2889249519 @default.
• W3089240207 cites W2947919073 @default.
• W3089240207 cites W2963351448 @default.
• W3089240207 cites W2980234472 @default.
• W3089240207 cites W2993720025 @default.
• W3089240207 cites W3038098604 @default.
• W3089240207 cites W3110006982 @default.
• W3089240207 hasPublicationYear "2020" @default.
• W3089240207 type Work @default.
• W3089240207 sameAs 3089240207 @default.
• W3089240207 citedByCount "0" @default.
• W3089240207 crossrefType "posted-content" @default.
• W3089240207 hasAuthorship W3089240207A5038934826 @default.
• W3089240207 hasAuthorship W3089240207A5039660232 @default.
• W3089240207 hasAuthorship W3089240207A5043602666 @default.
• W3089240207 hasConcept C105795698 @default.
• W3089240207 hasConcept C11413529 @default.
• W3089240207 hasConcept C119857082 @default.
• W3089240207 hasConcept C126255220 @default.
• W3089240207 hasConcept C126838900 @default.
• W3089240207 hasConcept C134018914 @default.
• W3089240207 hasConcept C139945424 @default.
• W3089240207 hasConcept C14036430 @default.
• W3089240207 hasConcept C154945302 @default.
• W3089240207 hasConcept C167085575 @default.
• W3089240207 hasConcept C183115368 @default.
• W3089240207 hasConcept C1862650 @default.
• W3089240207 hasConcept C2779974597 @default.
• W3089240207 hasConcept C2780473172 @default.
• W3089240207 hasConcept C2780668416 @default.
• W3089240207 hasConcept C33923547 @default.
• W3089240207 hasConcept C41008148 @default.
• W3089240207 hasConcept C50644808 @default.
• W3089240207 hasConcept C555293320 @default.
• W3089240207 hasConcept C71924100 @default.
• W3089240207 hasConcept C78458016 @default.
• W3089240207 hasConcept C86803240 @default.
• W3089240207 hasConceptScore W3089240207C105795698 @default.
• W3089240207 hasConceptScore W3089240207C11413529 @default.
• W3089240207 hasConceptScore W3089240207C119857082 @default.
• W3089240207 hasConceptScore W3089240207C126255220 @default.
• W3089240207 hasConceptScore W3089240207C126838900 @default.
• W3089240207 hasConceptScore W3089240207C134018914 @default.
• W3089240207 hasConceptScore W3089240207C139945424 @default.
• W3089240207 hasConceptScore W3089240207C14036430 @default.
• W3089240207 hasConceptScore W3089240207C154945302 @default.
• W3089240207 hasConceptScore W3089240207C167085575 @default.
• W3089240207 hasConceptScore W3089240207C183115368 @default.
• W3089240207 hasConceptScore W3089240207C1862650 @default.
• W3089240207 hasConceptScore W3089240207C2779974597 @default.
• W3089240207 hasConceptScore W3089240207C2780473172 @default.
• W3089240207 hasConceptScore W3089240207C2780668416 @default.
• W3089240207 hasConceptScore W3089240207C33923547 @default.
• W3089240207 hasConceptScore W3089240207C41008148 @default.
• W3089240207 hasConceptScore W3089240207C50644808 @default.
• W3089240207 hasConceptScore W3089240207C555293320 @default.
• W3089240207 hasConceptScore W3089240207C71924100 @default.
• W3089240207 hasConceptScore W3089240207C78458016 @default.
• W3089240207 hasConceptScore W3089240207C86803240 @default.
• W3089240207 hasLocation W30892402071 @default.
• W3089240207 hasOpenAccess W3089240207 @default.
• W3089240207 hasPrimaryLocation W30892402071 @default.
• W3089240207 hasRelatedWork W2015363484 @default.
• W3089240207 hasRelatedWork W2187666952 @default.
• W3089240207 hasRelatedWork W2211879833 @default.
• W3089240207 hasRelatedWork W2223699453 @default.
• W3089240207 hasRelatedWork W2618438111 @default.
• W3089240207 hasRelatedWork W2924706473 @default.
• W3089240207 hasRelatedWork W2945100890 @default.
• W3089240207 hasRelatedWork W2949910870 @default.
• W3089240207 hasRelatedWork W2969655192 @default.
• W3089240207 hasRelatedWork W2973596050 @default.
• W3089240207 hasRelatedWork W2976456386 @default.
• W3089240207 hasRelatedWork W2995826354 @default.
• W3089240207 hasRelatedWork W3036530548 @default.
• W3089240207 hasRelatedWork W3118447610 @default.
• W3089240207 hasRelatedWork W3133360745 @default.

• next