CLOUD-NATIVE PREDICTIVE HEALTH ANALYTICS USING EXPLAINABLE JAVA-BASED ML MODELS

Abstract

This research explores cloud-native predictive health analytics using explainable Java-based ML models through secondary qualitative data analysis. The study identifies three themes: scalability and adaptability, explainability and transparency, and ethical integration. Findings reveal that Java-based ML frameworks enhance interpretability and security within distributed cloud environments. Key recoveries include improved clinician trust, operational scalability, and compliance with ethical standards. The research contributes to understanding how explainable ML models integrated into cloud-native infrastructures can drive transparent, secure, and efficient predictive health analytics for sustainable digital healthcare transformation.