Optimization of identifying insulinaemic pharmacokinetic parameters using artificial neural network

Background and Objective: The identification of insulinaemic pharmacokinetic parameters using the least -squares criterion approach is easily influenced by outlying data due to its sensitivity. Furthermore, the least-squares criterion has a tendency to overfit and produce incorrect results. Hence, this research pro-poses an alternative approach using the artificial neural network (ANN) with two hidden layers to opti-mize the identifying of insulinaemic pharmacokinetic parameters. The ANN is selected for its ability to avoid overfitting parameters and its faster speed in processing data.Methods: 18 voluntarily participants were recruited from the Canterbury and Otago region of New Zealand to take part in a Dynamic Insulin Sensitivity and Secretion Test (DISST) clinical trial. A total of 46 DISST data were collected. However, due to ambiguous and inconsistency, 4 data had to be removed. Analysis was done using MATLAB 2020a.Results and Discussion: Results show that, with 42 gathered dataset, the ANN generates higher gains, 0 P = 20.73 [12.21, 28.57] mU center dot L center dot mmol-1 center dot min -1 and 0 D = 60.42 [26.85, 131.38] mU center dot L center dot mmol -1 as com-pared to the linear least square method, 0 P = 19.67 [11.81, 28.02] mU center dot L center dot mmol -1 center dot min -1 and 0 D = 46.21 [7.25, 116.71] mU center dot L center dot mmol -1. The average value of the insulin sensitivity (SI) of ANN is lower with, SI = 16 x 10 -4 L center dot mU -1 center dot min -1 than the linear least square, SI = 17 x 10 -4 L center dot mU -1 center dot min -1.Conclusion: Although the ANN analysis provided a lower SI value, the results were more dependable than the linear least square model because the ANN approach yielded a better model fitting accuracy than the linear least square method with a lower residual error of less than 5%. With the implementation of this ANN architecture, it shows that ANN able to produce minimal error during optimization process particularly when dealing with outlying data. The findings may provide extra information to clinicians, allowing them to gain a better knowledge of the heterogenous aetiology of diabetes and therapeutic intervention options.(c) 2023 Elsevier B.V. All rights reserved.

Automated summary

This research proposes an alternative approach using artificial neural networks (ANN) to identify insulinemic pharmacokinetic parameters. The results show that ANN method outperforms the linear least squares method in terms of model fitting accuracy and residual error, making it more reliable.