Implementation of Artificial Neural Network to Predict Diabetes with High-Quality Health System.

Area of Science:

• Biomedical Engineering
• Computer Science
• Health Informatics

Background:

• Diabetes management significantly impacts patient quality of life.
• Technological advancements, particularly the Internet of Things (IoT), offer potential for cost reduction in healthcare.
• E-health applications require intelligent, network-connected systems with high energy efficiency.

Purpose of the Study:

• To develop and evaluate a neural network-based ensemble voting classifier for accurate diabetes prediction.
• To leverage Internet of Things (IoT) devices for continuous online patient monitoring.
• To assess the performance of the proposed system in terms of accuracy, precision, recall, and f-measure.

Main Methods:

• Utilized Internet of Things (IoT) devices for real-time patient data collection.
• Implemented a data transfer pipeline from IoT devices to smartphones and then to a cloud-based classification system.
• Modeled a neural network-based ensemble voting classifier for diabetes prediction.
• Conducted simulations using Python on collected patient data.

Main Results:

• The proposed neural network-based ensemble voting classifier demonstrated high accuracy in diabetes prediction.
• The system achieved superior precision, recall, and f-measure compared to existing state-of-the-art ensemble models.
• Online monitoring via IoT devices facilitated efficient data processing and classification.

Conclusions:

• The developed intelligent system effectively predicts diabetes through online monitoring, enhancing patient care.
• The integration of IoT and advanced classification models improves healthcare efficiency and accuracy.
• This approach holds promise for improving the quality of life for diabetes patients through proactive health management.