E-DigitTool: A New-Fangled Framework for Disease Prediction and Diagnosis in Remote Healthcare Applications

The seamless communication between people and objects made possible by the Internet of Things (IoT) greatly improves our quality of life. It is especially important in the remote healthcare industry, where cutting-edge machine learning and artificial intelligence approaches are having a big impact....

Full description

Saved in:
Bibliographic Details
Published in:Iranian journal of science and technology. Transactions of electrical engineering 2024-12, Vol.48 (4), p.1463-1481
Main Authors: Lakshmi Priya, R., Kumaraswamy, Varkuti, Sunil, N. Kins Burk, Ramani, S., Latha, Sahukar
Format: Article
Language:English
Subjects:
Artificial intelligence
Cardiovascular disease
Classification
Data analysis
Electrical Engineering
Engineering
Error analysis
Feature selection
Health care
Health care industry
Internet of Things
Kalman filters
Machine learning
Medical diagnosis
Medical innovations
Neural networks
Optimization
Optimization techniques
Quality of life
Research Paper
Telemedicine
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The seamless communication between people and objects made possible by the Internet of Things (IoT) greatly improves our quality of life. It is especially important in the remote healthcare industry, where cutting-edge machine learning and artificial intelligence approaches are having a big impact. These analytics have the power to turn a proactive healthcare campaign from one that is reactive. For remote healthcare applications, this research study suggests an innovative framework called E-DigitTool to precisely identify and diagnose cardiovascular disorders. The digital health records collected by IoT sensors are preprocessed by the system using a Kalman filtering technique. The preprocessed medical data is analyzed using a modern optimization technique called Sine Cosine Optimized Feature Selection (SCO-FS) to identify the most significant features. Based on the chosen attributes, a state-of-the-art classification technology called Weighted Mean Vector Neural Network (WMVNN) is employed to accurately determine the type of sickness. Moreover, an Adaptive Wind Driven Optimization (AWDO) is used to compute the loss function optimum during illness classification, improving the performance and accuracy of the classifier. The main conclusions of the study show that E-DigitTool can analyze massive volumes of medical data with a performance accuracy of up to 99.5% for all datasets, resulting in an error rate of 0.5% and average precision, recall, and F1-score of 99%.
ISSN:2228-6179
2364-1827
DOI:10.1007/s40998-024-00743-9