Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression

Pencarian berdasarkan :

SEMUA Pengarang Subjek ISBN/ISSN Pencarian Spesifik

Pencarian terakhir:

e-journal

Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression

Eleni I. Georga - Nama Orang; Vasilios C. Protopappa - Nama Orang; Diego Ardig`o - Nama Orang; Michela Marina - Nama Orang; Ivana Zavaroni - Nama Orang; Demosthenes Polyzos - Nama Orang; Dimitrios I. Fotiadis - Nama Orang;

Abstract—Data-driven techniques have recently drawn significant interest in the predictive modeling of subcutaneous (s.c.) glucose concentration in type 1 diabetes. In this study, the s.c. glucose prediction is treated as a multivariate regression problem, whichisaddressedusingsupportvectorregression(SVR).Theproposed method is based on variables concerning: 1) the s.c. glucose proﬁle; 2) the plasma insulin concentration; 3) the appearance of meal-derivedglucoseinthesystemiccirculation;and4)theenergy expenditure during physical activities. Six cases corresponding to differentcombinationsoftheaforementionedvariablesareusedto investigatetheinﬂuenceoftheinputonthedailyglucoseprediction. Theproposed method is evaluated using a dataset of 27 patientsin free-living conditions. Tenfold cross validation is applied to each datasetindividuallytobothoptimizeandtesttheSVRmodel.Inthe case,wherealltheinputvariablesareconsidered,theaverageprediction errors are 5.21, 6.03, 7.14, and 7.62 mg/dl for 15-, 30-, 60-, and 120-min prediction horizons, respectively. The results clearly indicate that the availability of multivariable data and their effective combination can signiﬁcantly increase the accuracy of both short-term and long-term predictions.

Index Terms—Subcutaneous (s.c.) glucose concentration, support vector machines, type 1 diabetes.

Ketersediaan

Tidak ada salinan data

Informasi Detail

Judul Seri: -
No. Panggil: -
Penerbit: : IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS., 2013
Deskripsi Fisik: IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, VOL. 17, NO. 1, JANUARY 2013 p. 71-81
Bahasa: English
ISBN/ISSN: 1089-7771
Klasifikasi: NONE
Tipe Isi: -
Tipe Media: -
Tipe Pembawa: -
Edisi: -
Subjek: DIABETES-PENELITIAN
Info Detail Spesifik: -
Pernyataan Tanggungjawab: Eleni I. Georga ... [et al.]

Versi lain/terkait

Tidak tersedia versi lain

Lampiran Berkas

Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression

Komentar

Anda harus masuk sebelum memberikan komentar