Artificial Intelligence Based Insulin Sensitivity Prediction for Personalized Glycaemic Control in Intensive Care (2020)
Stress-induced hyperglycaemia is a frequent complication in the intensive therapy that can be safely and efficiently treated by using the recently developed model-based tight glycaemic control (TGC) protocols. The most widely applied TGC protocol is the STAR (Stochastic-TARgeted) protocol which uses the insulin sensitivity (SI) for the assessment of the patients state. The patient-specific metabolic variability is managed by the so-called stochastic model allowing the prediction of the 90% confidence interval of the future SI value of the patients. In this paper deep neural network (DNN) based methods (classification DNN and Mixture Density Network) are suggested to implement the patient state prediction. The deep neural networks are trained by using three years of STAR treatment data. The methods are validated by comparing the prediction statistics with the reference data set. The prediction accuracy was also compared with the stochastic model currently used in the clinical practice. The presented results proved the applicability of the neural network based methods for the patient state prediction in the model based clinical treatment. Results suggest that the methods’ prediction accuracy was the same or better than the currently used stochastic model. These results are the initial successful step in the validation process of the proposed methods which will be followed by in-silico simulation trials.
CitationBenyó B, Paláncz B, Szlávecz Á, Szabó B, Anane Y, Kovács K, Chase JG (2020). Artificial Intelligence Based Insulin Sensitivity Prediction for Personalized Glycaemic Control in Intensive Care. IFAC-PapersOnLine. 53(2). 16335-16340.
This citation is automatically generated and may be unreliable. Use as a guide only.
Keywordsmachine learning; artificial intelligence; mixture density network; deep neural network; insulin sensitivity; tight glycaemic control; intensive care; STAR protocol
ANZSRC Fields of Research32 - Biomedical and clinical sciences::3202 - Clinical sciences::320212 - Intensive care
32 - Biomedical and clinical sciences::3202 - Clinical sciences::320208 - Endocrinology
40 - Engineering::4003 - Biomedical engineering::400306 - Computational physiology
40 - Engineering::4009 - Electronics, sensors and digital hardware::400909 - Photonic and electro-optical devices, sensors and systems (excl. communications)
46 - Information and computing sciences::4611 - Machine learning::461104 - Neural networks
46 - Information and computing sciences::4611 - Machine learning::461103 - Deep learning
RightsAll rights reserved unless otherwise stated
Showing items related by title, author, creator and subject.
Artificial Intelligence Based Insulin Sensitivity Prediction for Personalized Glycaemic Control in Intensive Care Szabo B; Palancz B; Szlavecz A; Kovacs K; Benyo B; Chase, Geoff (2020)Stress-induced hyperglycaemia is a frequent complication in intensive therapy that can be safely and efficiently treated using the recently developed model-based tight glycemic control (TGC) protocols. The most widely ...
Campbell JD; Holder-Pearson L; Benton C; Chase, Geoff; Pretty, Christopher; Knopp, Jennifer (Elsevier BV, 2020)Abstract: Currently, there are no continuous, non-invasive blood glucose monitors. With over 366 million people worldwide expected to be diagnosed as diabetic by 2030, an alternative to the current invasive methods is ...
Pirotte M; Morimont P; Lambermont B; Shaw, Geoff; Desaive T; Uyttendaele, Vincent; Knopp, Jennifer; Chase, Geoff (BMC, 2020)Introduction: Stress-induced hyperglycemia is a common complication associated with higher morbidity and mortality in ICU patients. The Stochastic TARgeted (STAR) glycemic control (GC) framework provides consistent, ...