Deceleration capacity index for type 2 diabetes mellitus classification using support vector machines in elderly women

The purpose of this study was to present study was to stratify the degree of type 2 diabetes mellitus (T2DM) in elderly women based on the phase-rectification signal averaged (PRSA) approach to HRV analysis using SVM and cross-validated by the k-Fold. This study was designed as a cross-sectional study of elderly women subjects 60 to 70 yrs of age were divided into two groups, twenty subjects each: diabetes group (DG) with a diagnosis of T2DM and control group (CG). All subjects were instructed to lie in the supine position for 5 min at rest while breathing normally with a heart rate monitor Polar V800 working at a sampling rate of 1000 Hz was used to record RR intervals (RRi), it was created a vector of the differences between successive elements of the RRi series; the cardiac-deceleration rate (CDR) index was defined as the mean of the positive values. A Gaussian SVM classifier trained on classifying the DG and healthy based on CDC index was tuned and validated using multiple runs of k-fold cross-validation. After ten runs of ten-fold cross-validation, our method using 10-fold cross validation obtains the highest classification accuracy, 97.5%, reported so far. In conclusion, CDC index of RR time series at rest was proposed and validated to stratify the degree of T2DM in elderly women using SVM, might be complementary to existing autonomic function assessment. Then, machine learning approaches offer new solutions and ways forward in biomedical, bioengineering and clinical applications, mainly, in diabetes research.