This study presents a distributed system using RAY, K-means clustering, and Weka software to analyze clinical data from Almasara Hospital Group in Tripoli, Libya. The goal is to reduce patient risk and healthcare costs by providing daily feedback to hospital staff. The system utilizes a dataset containing information on 560 patients, including details like patient ID, gender, doctor ID, test IDs, medication, and a binary target variable. By implementing K-means clustering in Weka, the system categorizes patients and identifies patterns to reduce risks and costs for healthcare analytics. The study first reviews existing patient care and feedback practices and then details the implementation of the daily feedback system, which involves advanced data analysis for managing patient feedback and medical data continuously. The use of K-means clustering helps segment patient data, pinpointing specific risk factors and areas for improvement. Weka software aids in the in-depth analysis of these segments, leading to actionable insights. Results show significant improvements in patient outcomes, reduced hospital-acquired infections, and medication errors, and enhanced patient satisfaction scores. Moreover, the study notes a substantial decrease in overall healthcare costs due to more efficient resource allocation and lower hospital readmission rates. This integration of daily feedback with advanced data analysis tools like K-means and Weka emerges as an effective strategy for improving patient safety and operational efficiency in healthcare settings, demonstrating the value of data-driven decision-making and providing a scalable model for other hospitals aiming to enhance patient care and cost management.
Read full abstract