Development of a hospital management system leveraging support vector machine technique

Healthcare institutions are extensively faced with challenges including ineffective patient record administration, dependence on hand made operational assessment, delay decision-making, and challenge evaluate to automated devices that assist clinical decision-making. Conventional hospital administration systems are complicated designed to address administrative operations and often lack complex forecast attributes that allow healthcare professionals to detect potential health dangers and provide timely interventions for strong-risk patients. The study proposed to development a web-based Hospital Management System (HMS) application leveraging Support Vector Machine (SVM) technique to facilitate the efficiency, accuracy and dependability in healthcare management processes. This developed model attained accuracy of 84.42%, precision value of 81.25%, recall rate of 86.11%, and F1 score of 83.61%. All these shows that embedding Machine Learning (ML) techniques into HMS can improve patient risk forecasting and promoting timely, data-driven clinical decision-making. The study infers that the presented system offers an effective model for automated healthcare administration and gives a foundation for the implementation of future artificial intelligence (AI) based healthcare solutions.