A Hybrid Dynamic Wavelet‑Based Modeling Method for Blood Glucose Concentration Prediction in Type ۱ Diabetes
سال انتشار: 1399
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 79
فایل این مقاله در 11 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JMSI-10-3_004
تاریخ نمایه سازی: 28 تیر 1402
چکیده مقاله:
Background: Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction
of blood glucose concentration (BGC) is essential to improve the therapy of type ۱ DM (T۱DM).
Methods: Having considered the risk of hyper‑ and hypo‑glycemia, we provide a new hybrid
modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN)
model, including a heuristic input selection. The proposed models include a hybrid dynamic
WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet‑based networks
are designed based on dominant wavelets selected by the genetic algorithm‑orthogonal least square
method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction,
an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on
real data from ۱۲ T۱DM patients and also simulated data from ۳۳ virtual patients with an UVa/
Padova simulator, an approved simulator by the US Food and Drug Administration. Results:
A comparison study is performed in terms of new glucose‑based assessment metrics, such as gFIT,
glucose‑weighted form of ESODn (gESODn), and glucose‑weighted R۲ (gR۲). For real patients’ data,
the values of the mentioned indices are accomplished as gFIT = ۰.۹۷ ± ۰.۰۱, gESODn = ۱.۱۸ ± ۰.۳۸,
and gR۲ = ۰.۸۸ ± ۰.۰۷. HDFWNN, HDWNN and jump NN method showed the prediction error (root
mean square error [RMSE]) of ۱۱.۲۳ ± ۲.۷۷ mg/dl, ۱۰.۷۹ ± ۳.۸۶ mg/dl and ۱۶.۴۵ ± ۴.۳۳ mg/dl,
respectively. Conclusion: Furthermore, the generalized estimating equation and post hoc tests show
that proposed models perform better compared with other proposed methods.
کلیدواژه ها:
Blood glucose prediction ، diabetes mellitus ، fuzzy rule induction ، fuzzy wavelet neural network ، wavelet neural network
نویسندگان
Mohsen Kharazihai Isfahani
Department of Electrical and Computer Engineering, Isfahan University of Technology
Maryam Zekri
Department of Electrical and Computer Engineering, Isfahan University of Technology
Hamid Reza Marateb
Department of Biomedical Engineering, Faculty of Engineering, University of Isfahan- Department of Automatic Control, Biomedical Engineering Research Center, Polytechnic University of Catalonia, Barcelona Tech, Barcelona, Spain
Elham Faghihimani
Isfahan Endocrine and Metabolism Research Center, Isfahan University of Medical Sciences, Isfahan, Iran