Year: 2025
Type: article
Abstract: Hemoglobin A1c (HbA1c) is an excellent biomarker that reflects average three-month blood glucose and is of greatest benefit in evaluating control of blood glucose. The system described combines sensor-wearable, continuous glucose monitor, electronic medical records, and patient manual reports. The AI-driven HbA1c Monitoring and Management System is a new diabetes management paradigm attained through the advanced use of Artificial Intelligence (AI) and Machine Learning (ML). The most critical algorithmic components are Liner Regression, Random Forest, Gradient Boosting Machines (GBM), and Long Short-Term Memory (LSTM) Networks. They collaborate to forecast HbA1c trends, detect abnormalities, and produce customized recommendations on lifestyle change, dietary change, and medication. They are programmed to identify nonlinear trends and to eliminate temporal dependences in data. This paper provides step-by-step instructions on how to harmonize medicine, diet, and lifestyle to reveal time-dependent associations and nonlinear trends in diabetes data. Through the integration of real-time testing, predictive modelling, and individualized feedback, this study aims to improve the treatment of diabetes, bridge gaps, and reduce healthcare expenditure. The system is highly promising but is faced with a number of challenges including the ability to deal with elevated implementation costs, surpassing data confidentiality, the ability to sustain patient compliance, and surmounting regulatory challenges. The article criticizes the system's design, predictive capability, and functional uses and points to the promise of shifting diabetes care from a reactive to a proactive approach
Source: Journal of Neonatal Surgery
Institution: Bharathiar University
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4409741540