Discrete Mean Amplitude of Glycemic Excursion (MAGE) Measurement on Diabetics with Spline Interpolation Method

Abstract

Diabetes Mellitus (DM) is a disease that is characterized by glycemic disorders, including sustained chronic hyperglycemia and acute glucose fluctuations. Because DM is closely related to the body metabolism, the observation of the blood vessels becomes very important to perform. The observation is done by using the Mean Amplitude of Glycemic Excursion (MAGE). Definitively, MAGE is an important variable to solve clinical DM problems that contributes in generating oxidative stress related to the macro and microvascular complications. MAGE is technically used with continuous blood glucose data which is obtained by Continuous Glucose Monitoring (CGM). Because of the CGM is expensive for personal use, it cannot be used in the daily observation. The contribution of this study is the utilization of discrete data (3 days observation) to be used in MAGE measurement. This research employs Spline Interpolation technique to convert discrete blood glucose data to continuous signal. The validation of interpolated signal is conducted by comparing the pattern of discrete data and continuous signal for both original and clustered data. The experiment showed that both scenarios depicted identical pattern. The smallest RMSE was achieved by Linear Spline with 57.66 while the highest RMSE value was obtained by Quadratic Spline with 177.00.

Prediksi Diabetes Berdasarkan Pengukuran Mean Amplitude Glycemic Excursion (MAGE) Menggunakan Naïve Bayes

“…Penelitian Daniela, Christopher, dan Roger membuktikan Nave Bayes klasifikasi yang lebih baik dari neural network dan decision tree dengan akurasi 97,89% [9]. Penelitian lain yang serupa juga pernah dilakukan dengan data yang sama pada penelitian ini, yakni dengan hasil nilai RMSE 57.66 [10] dan hasil akurasi 92.85% [11].…”