NIRCa: An artificial neural network-based insulin resistance calculator
- 19 June 2017
- journal article
- research article
- Published by Wiley in Pediatric Diabetes
- Vol. 19 (2) , 231-235
Abstract
Direct measurement of insulin sensitivity in children with type 1 diabetes is cumbersome and time consuming. The aim of our study was to develop novel, accurate machine learning-based methods of insulin resistance estimation in children with type 1 diabetes. A hyperinsulinemic hyperglycemic clamp study was performed to evaluate the glucose disposal rate (GDR) in a study group consisting of 315 patients aged 7.6 to 19.7 years. The group was randomly divided into a training and independent testing set for model performance assessment. GDR was estimated on the basis of simple clinical variables using 2 non-linear methods: artificial neural networks (ANN) and multivariate adaptive regression splines (MARSplines). The results were compared against the most frequently used predictive model, based on waist circumference, triglyceride (TG), and HbA1c levels. The reference model showed moderate performance ( R 2 = 0.26) with a median absolute percentage error of 49.1%, and with the worst fit observed in young (7-12 years) children ( R 2 = 0.17). Predictions of the MARSplines model were significantly more accurate than those of the reference model (median error 3.6%, R 2 = 0.44 P < .0001). The predictions of the ANN, however, showed significantly lower error than those of the reference model (P < .0001) and MARSplines (P < .0001) and better fit regardless of patient age. ANN-estimated GDRs were within a ±20% error range in 75% of cases with a median error of 0.6% and an R 2 = 0.66. The predictive tool is available at http://link.konsta.com.pl/gdr. The developed GDR estimation model reliant on ANN allows for an optimized prediction of GDR for research and clinical purposes.Keywords
Funding Information
- National Science Center (NN 407 1878 36, 2014/15/B/NZ5/00144)
This publication has 15 references indexed in Scilit:
- Insulin sensitivity and arterial stiffness in youth with type 1 diabetes: the SEARCH CVD studyJournal of Diabetes and its Complications, 2015
- Magnetic resonance imaging measures of decreased aortic strain and distensibility are proportionate to insulin resistance in adolescents with type 1 diabetes mellitusPediatric Diabetes, 2014
- Prevalence of overweight, obesity and metabolic syndrome components in children, adolescents and young adults with type 1 diabetes mellitusDiabetes/Metabolism Research and Reviews, 2014
- Clinical evolution of beta cell function in youth with diabetes: the SEARCH for Diabetes in Youth studyDiabetologia, 2012
- Measuring insulin sensitivity in youth: How do the different indices compare with the gold-standard method?Diabetes & Metabolism, 2011
- Development, validation and use of an insulin sensitivity score in youths with diabetes: the SEARCH for Diabetes in Youth studyDiabetologia, 2010
- Association of insulin sensitivity to lipids across the lifespan in people with Type 1 diabetesDiabetic Medicine, 2010
- Insulin sensitivity in Type 1 diabetic children and adolescentsDiabetic Medicine, 2008
- Homeostasis Model Assessment Is More Reliable Than the Fasting Glucose/Insulin Ratio and Quantitative Insulin Sensitivity Check Index for Assessing Insulin Resistance Among Obese Children and AdolescentsPediatrics, 2005
- An introduction to multivariate adaptive regression splinesStatistical Methods in Medical Research, 1995