Performance Evaluation of Machine Learning Models for Diabetes Prediction

Abstract

Diabetes is one of the prevalent diseases all over the world. As per the International Diabetes Federation (IDF) report of the year 2017, diabetes is prevalent in about 8.8% of the Indian adult population and is one of the top ten causes of death in India. In untreated and unidentified diabetes could cause fluctuations in the sugar levels and extreme cases, damage organs such as kidneys, eyes, and arteries in the heart. By using Machine learning algorithms to predict the disease from the relevant datasets at an early stage could likely save human lives. The purpose of this investigation is to assess the classifiers that can predict the probability of disease in patients with the greatest precision and accuracy. Experimental work has been carried out using classification algorithms such as K Nearest Neighbor (KNN), Decision Tree(DT), Naive Bayes (NB), Support Vector Machine (SVM), Logistic Regression (LR) and Random Forest(RF) on Pima Indians Diabetes dataset using nine attributes which is available online on UCI Repository. The performance of classifier is evaluated based on precision, recall, accuracy and is estimated over correct and incorrect instances. The results proved that Logistic Regression (LR) performs better with the accuracy of 77.6 % in comparison to other algorithms

Type 2 Diabetes with Artificial Intelligence Machine Learning: Methods and Evaluation

“…The table is then pruned by removing redundant rules and the rules having a confidence value less than 1. The confidence for a risk factor rule is calculated as stated in Eq (20)…”

A Review on Machine Learning Techniques for Advanced Health Care Systems

“…performance with an accuracy of 81.4 % and a k-NN gave the poorest performance of 69.01 %. All the metrics here are calculated by considering the average of all individuals researches already made [31][32][33][34][35][36][37][38][39][40][41].…”

A Hybrid System to Improve the Performance of Diabetes Disease Prediction using Genetic Algorithm

“…It estimates the likelihood to create a model with predictive capabilities. This classifier can be viewed as both descriptive and predictive type where probabilities are descriptive and this is used to predict the target class [11] and [13].…”

“…It contains 9 numerical valued attributes named pregnancy, plasma, pres, skin, insulin, mass, pedi, age, and class, the first 8 are independent and the last one is dependent. There is a total of 768 instances with 500 instances are tested negative and 268 instances are tested positive [4], [10] and [11]. Table I represents the training performance of the Naïve Bayes + GA model and the graphical view of this model is shown in Fig.…”

“…A lot of rehearses have been done on this diabetes disease to predict this disease in early-stage to overcome its complications such as strokes, blindness, kidney failure, damage and failure of several organs. The Pima Indians Diabetes Database of the National Institute of Diabetes and Digestive and Kidney Diseases has used as diabetes dataset [2], [10] and [11].…”