A Classification System for Diabetic Patients with Machine Learning Techniques

Abstract

Diabetes mellitus (DM) is a group of metallic disorder characterized by steep levels of blood glucose prolonged over a time. It results the defection in insulin production or improper action of the cells to the insulin produced. It is one of the significant public health care challenge worldwide. Diabetes exists in a body when pancreas does not construct enough hormone insulin or the human body is not being able to use the insulin properly. The diagnosis of diabetes (diagnosis, etiopathophysiology, therapy etc.) need to generate and process the vast amount of data. Data mining techniques have proven its usefulness and effectiveness in order to evaluate the unknown relationships or patterns if exists with such vast data. In the present work, five techniques based on machine learning namely, AdaBoost, LogicBoost, RobustBoost, Naïve Bayes and Bagging have been proposed for the analysis and prediction of DM patients. The proposed techniques are employed on the data set of Pima Indians Diabetes patients. The results computed are found to be very accurate with classification accuracy of 81.77% and 79.69% by bagging and AdaBoost techniques, respectively. Hence, the proposed techniques employed here are highly adorable, effective and efficient in order to predict the DM.

Research on Smart Healthcare Services: Based on the Design of APP Health Service Platform

“…The main value of these products is information processing. The wearer can control them and conduct intimate interaction with the device at the same time [ 19 ]. Wearable intelligent devices are mainly required for terminals, which do not require manual operation and can maintain the continuity and accuracy of information acquisition in daily life and work.…”

“…(3) Communication Module Requirements . About creating awareness of health information terminal must meet the basic design requirements, and easy to carry, the wearable perception between terminal and control terminal information transfer to each other in no wiring communication mode, the wearable perception system of mutual distance scope and management control system port to form the reality of the transmission range not far from 2 meters, so it is necessary to all business accounting cost, power consumption, and practical vision to choose a way to meet the short distance wireless communication [ 19 ].…”

“…ere is also the maximum capacity of storage on ports (output and input) etc. For the heart rate sensor terminal is not set to advantageous computing speed, ordinary SCM can be controlled by the sensor and meet the basic conditions required for communication [17][18][19].…”

Diagnosis and Classification of Type II Diabetes based on Multilayer Neural Network

“…if it is negative or positive. This might be evaluated with the mathematical formula in Equation ( 4) [18]. Accuracy = … (4) Where TN represents True Negative and FP represents False Positive.…”

“…Sensitivity is the ability of adequately choosing the positive patients subjected to the disease; i.e. the probability to have the disease (positive test) [18]. Sensitivity was utilized for determining any type of diseases in the classification approach; thus, the test sensitivity is equal to the proportion of the number of TP patients to the total number of sick individuals in population.…”