Supervised Learning Method and Neural Network Algorithm for the Analysis of Diabetic Mellius and its Comparitive Analysis

Abstract

Diabetes is the key critical issue needs to be concerned for various problems in our body. Increase in glucose and fructose content in our body results in diabetes mellitus. When a body generates higher insulin level than the required, it results in increased urination and excessive thirstiness which in turn results in kidney failure and other cardio-related issues. Many research agencies invested their funds on defining the predictive methodology and finding the root cause of those results in mellitus. Mellitus results in the highest mortality rate compared to any other disease reported by the health organizations across the globe. In this, the predictive methodologies, various classification techniques are discussed, and the results are analyzed. The classification methodology could be on medications, food habits, personal behaviors, age factors and so on. The datasets are processed and analyzed with the neural network algorithms, and the results are compared with one another. The datasets are taken from the National Family Health Survey results published during the period of 2016–2017. The result implies that men between ages 15–49 among 1 billion people have reported with diabetes mellitus. Diagnose and forecast on this disease are done by recognizing the pattern formation and grouping the similar structures. Various algorithmic techniques like M-layer perceptron, nearest neighbor, vector machines, data regressions, binary regression and their accuracy of forecast, speed and sensitivity are calculated, analyzed and compared to define the accurate prediction methodology over a short span of time. The forecast methodologies are focussed to provide solutions to avoid the intensive care system provided proper medications with a long duration when it is been predicted to be a risk factor. A statistical method of analyzing is performed for the comparative analysis. The learning and training methodologies are discussed in this system. Accuracy, specificity, sensitivity are the key parameters to define the best forecast methodology. Classification on association, regression techniques and neural algorithmic techniques is analyzed and compared to refine the best predictive forecast methodology by processing 30 samples across the states of India with focus on determining the type of mellitus along with the accuracy on definition. The forecast data utilized to define the type of mellitus and the prediction on critical measures over a period of time.