An Predictive Deep Learning Model is used to Identify Human Tissue-Specific Regulatory Variations For Diabetes

A predictive deep learning model is designed to predict a target variable based on a set of input variables to diagnose the tissue base regulatory variants in the human islets. In this article, the identification on human tissue-specific regulatory variations for Diabetes using the Pima dataset converting data into images, and then the input variables may include genetic data, gene expression data, and the proposed model uses Pima Indian dataset with the attributes such as age, sex, and BMI to predict whether a person has Diabetes or not. And this dataset is incorporated a combination two layered ResNet18 + ResNet50 and SVM classifier. The results obtained are compared with KNN, Naive bayes, SVM Random Forest, Gradient descent and the accuracy achieved is 98%.