The development of a glucose prediction model in critically ill patients
| Autor: | P. H. J. van der Voort, V. Lagerburg, S.C.J. van Steen, R. Wedzinga, R. J. Bosman, M. van den Boorn |
|---|---|
| Přispěvatelé: | Critical care, Anesthesiology, Peri-operative and Emergency medicine (CAPE) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Blood Glucose
Icu patients medicine.medical_specialty Closed-loop system Health Informatics Mean difference CLOSED-LOOP CONTROL 030218 nuclear medicine & medical imaging law.invention TIGHT GLYCEMIC CONTROL 03 medical and health sciences STAR-LIEGE PROTOCOL HYPOGLYCEMIA 0302 clinical medicine Randomized controlled trial law Medicine Humans Icu stay ADMISSION HYPERGLYCEMIA Training set Tight glucose regulation business.industry Critically ill Blood Glucose Self-Monitoring MORTALITY Glucose Measurement INTENSIVE INSULIN THERAPY Glucose prediction model Computer Science Applications VARIABILITY Glucose Emergency medicine ICU CRITICAL ILLNESS business 030217 neurology & neurosurgery Software CARE-UNIT |
| Zdroj: | Computer Methods and Programs in Biomedicine, 206:106105. ELSEVIER IRELAND LTD |
| ISSN: | 0169-2607 |
| Popis: | Purpose: The aim of the current study is to develop a prediction model for glucose levels applicable for all patients admitted to the ICU with an expected ICU stay of at least 24 h. This model will be incorporated in a closed-loop glucose system to continuously and automatically control glucose values.Methods: Data from a previous single-center randomized controlled study was used. All patients received a FreeStyle Navigator II subcutaneous CGM system from Abbott during their ICU stay.The total dataset was randomly divided into a training set and a validation set. A glucose prediction model was developed based on historical glucose data. Accuracy of the prediction model was determined using the Mean Squared Difference (MSD), the Mean Absolute Difference (MAD) and a Clarke Error Grid (CEG).Results: The dataset included 94 ICU patients with a total of 134,673 glucose measurements points that were used for modelling. MSD was 0.410 +/- 0.495 for the model, the MAD was 5.19 +/- 2.63 and in the CEG 99.8% of the data points were in the clinically acceptable regions.Conclusion: In this study a glucose prediction model for ICU patients is developed. This study shows that it is possible to accurately predict a patient's glucose 30 min ahead based on historical glucose data. This is the first step in the development of a closed-loop glucose system. (C) 2021 Elsevier B.V. All rights reserved. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect