Non-invasive Approach to Predict the Cholesterol Level in Blood Using Bioimpedance and Neural Network Techniques

This paper presents a new non-invasive approach to predict the status of high total cholesterol (TC) level in blood using bioimpedance and the arti ̄cial neural network (ANN) techniques. The input parameters for the ANN model are acquired from a non-invasive bioelectrical impedance analysis (BIA) measurement technique. The measurement data were obtained from 260 volunteered participants. A total of 190 subject's data were used for the ANN training purpose and the remaining 70 subject's data were used for model testing. Six parameters from the BIA parameters were found to be signi ̄cant predictors for TC level in blood using logistic regression analysis. The six input predictors for the ANN modeling are age, body mass index (BMI), body capacitance, basal metabolic rate, extracellular mass and lean body mass. Four ANN techniques such as the gradient descent with momentum, the resilient, the scaled conjugate gradient and the Levenberg Marquardt were used and compared for predicting the high TC level in the blood. The ̄nding showed that the resilient method was the best model with prediction accuracy, sensitivity, speci ̄city and area under the curve value obtained from the test data were 82.9%, 85.4%, 79.3% and 0.83%, respectively.