The complexity of inpatient healthcare has increased with rising patient numbers, diverse medical
conditions, and the growing volume of hospital data. Manual management of patient records and
diagnostic information can lead to delays, errors, and suboptimal treatment outcomes. This study
presents MediSync, an AI-powered inpatient diagnosis system designed to streamline medical data
management, assist doctors in real-time diagnosis, and provide decision support for optimal treatment
planning. MediSync integrates electronic health records (EHR), laboratory results, imaging data, and
clinical notes to provide a unified platform for inpatient management. By leveraging machine learning
and deep learning algorithms, the system identifies patterns, predicts disease progression, and flags
high-risk cases for immediate attention. Experimental evaluations on simulated and real-world
hospital datasets demonstrate high accuracy in predicting inpatient diagnoses and prioritizing care.
The system aims to improve efficiency, reduce diagnostic errors, and enhance patient outcomes while
providing a scalable framework for hospital information systems.
