Abstract
The rapid advancement of Artificial Intelligence (AI) and intelligent digital systems has created significant opportunities to enhance clinical decision-making and data management within healthcare infrastructures. Electronic Health Record (EHR) platforms, while widely adopted, often struggle with issues related to data overload, inefficient triage, and limited real-time prioritization challenges that are particularly pronounced in resource-constrained healthcare environments such as Bangladesh. This study presents the design and development of an AI-enabled EHR prototype that integrates a priority-based patient management algorithm, real-time data processing, and modular analytics workflows. The system architecture incorporates structured preprocessing, severity-classification logic, and rule-based decision layers implemented using KNIME for data analytics and C# for application development. Quantitative evaluations were conducted to assess improvements in queue management, task scheduling efficiency, and physician usability, demonstrating measurable enhancements compared with conventional manual triage approaches. The findings illustrate the potential of AI-assisted EHR systems to strengthen operational efficiency and clinical responsiveness, providing a scalable pathway for digital healthcare transformation in developing countries.
Keywords
Artificial Intelligence (AI), Biomedical Engineering (BME), Deep Learning (DL), Data Fusion, Data Management System, Electronical Health Records (EHR), Machine Learning (ML)