Motion (physics)

Algorithm

Statistics

Endocrinology

Computer science

Interpolation (computer graphics)

Pattern recognition (psychology)

Mathematics

Bilinear interpolation

Spline interpolation

Glycemic

Artificial intelligence

Medicine

Machine learning

Diabetes mellitus

Bulletin of Electrical Engineering and Informatics

Chronic Hyperglycemia and Acute Glucose Fluctuations are the two main null null factors that trigger complications in Diabetes Mellitus (DM). Continuous and sustainable observation of the two triggering factors is significant to be done null null to reduce the potential of cardiovascular problems in the future. This potential can be reduced null null by minimizing the occurrence of glycemic variability (GV). At present, null null observations on GV are based on the Mean Amplitude of Glycemic Excursion null null (MAGE), which is measured based on continuous blood glucose data from null null patients using particular devices. Continuous blood glucose uptake has technical constraints, null null especially in the provision of equipment. Thus, this study aims to calculate null null the value of MAGE based on discrete blood glucose observations from 43 null null volunteer patients. The resulting MAGE value is used to predict the diabetes null null status of volunteers. The hypothesis is that the discrete data is relevant to null null be used to predict the value of MAGE. Experiments were carried out by null null calculating MAGE values ​​from original discrete data (21 observations over null null three days) and continuous data obtained using Spline Interpolation. This null null study also utilizes the Machine Learning algorithm, especially k-Nearest null null Neighbor with Dynamic Time Wrapping (DTW) as a technique to measure the null null distance between time series data. From the classification test, discrete null null data and continuous data from the interpolation results show precisely the null null same accuracy value that is equal to 82.85%. Furthermore, there are null null variations in the MAGE value for each patient where the diabetes class has null null the most significant difference, followed by the pre-diabetes class, and the null null typical class. The conclusion that can be drawn is that patients in null null pre-diabetic and diabetic classes tend to have more varied blood glucose null null values ​​than patients from normal classes.

Study on diabetes prediction based on discrete and continuous mean amplitude of glycemic excursions using machine learning methods