Using Recurrent Neural Networks for Predicting Type-2 Diabetes from Genomic and Tabular Data

Abstract

The development of genomic technology for smart diagnosis and therapies for various diseases has lately been the most demanding area for computer-aided diagnostic and treatment research. Exponential breakthroughs in artificial intelligence and machine intelligence technologies could pave the way for identifying challenges afflicting the healthcare industry. Genomics is paving the way for predicting future illnesses, including cancer, Alzheimer’s disease, and diabetes. Machine learning advancements have expedited the pace of biomedical informatics research and inspired new branches of computational biology. Furthermore, knowing gene relationships has resulted in developing more accurate models that can effectively detect patterns in vast volumes of data, making classification models important in various domains. Recurrent Neural Network models have a memory that allows them to quickly remember knowledge from previous cycles and process genetic data. The present work focuses on type 2 diabetes prediction using gene sequences derived from genomic DNA fragments through automated feature selection and feature extraction procedures for matching gene patterns with training data. The suggested model was tested using tabular data to predict type 2 diabetes based on several parameters. The performance of neural networks incorporating Recurrent Neural Network (RNN) components, Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU) was tested in this research. The model’s efficiency is assessed using the evaluation metrics such as Sensitivity, Specificity, Accuracy, F1-Score, and Mathews Correlation Coefficient (MCC). The suggested technique predicted future illnesses with fair Accuracy. Furthermore, our research showed that the suggested model could be used in real-world scenarios and that input risk variables from an end-user Android application could be kept and evaluated on a secure remote server.

XAI‐driven model for crop recommender system for use in precision agriculture

“…To ensure the security of the data shared across the unsecured channel using the socket layer (SSL), the data's privacy is enforced through two‐factor authentication. MongoDB, a NoSQL database, stores the corresponding user data 46,47 . If the technology described above were implemented, the future view paradigm would be replaced with a user‐centric system that includes all the essential components.…”

“…MongoDB, a NoSQL database, stores the corresponding user data. 46,47 If the technology described above were implemented, the future view paradigm would be replaced with a user-centric system that includes all the essential components.…”

Harmonic Mitigation of the Microgrid Using Multi Hidden Layer Recurrent Neural Network Controlled SAPF

“…RNNs are a sort of neural network that uses previous data from a time series to make predictions about the future [15]. Recurrent Neural Networks (RNNs) function based on the principle of retaining the output of a particular layer and reintroducing it as input in order to predict the output of that layer.…”

A model of integrating convolution and BiGRU dual-channel mechanism for Chinese medical text classifications

“…They used several text mining and machine learning strategies to perform sentiment analysis on distributed LSTM framework and ran it in three different corpora, and the results showed that they were superior to some machine learning methods such as LDA and SVD in accuracy and efficiency. Srinivasu et al [39] used recurrent neural networks such as LSTM and GRU to predict type 2 diabetes. At the same time, some scholars introduced the attention mechanism [40] into the application fields such as sentiment analysis and text classification, and the results indicate that attention mechanism is of great significance.…”