Robust Healthcare Systems Utilising HPE GreenLake for Disaster Recovery and Machine Learning Integration

• Published in: Communications and Signal Processing, International Conference on pp. 1861 - 1866
• Main Authors: Sekar, Satheeshkumar, Poonia, Pregya, Jayaraman, Venkatesh, R, Suriya, M, Muthulekshmi, A, Athish
• Format: Conference Proceeding
• Language: English
• Published: IEEE 05.06.2025
• Subjects: data security; Decision making; disaster recovery; Disasters; Healthcare systems; Hewlett Packard Enterprise GreenLake; Machine learning; Machine learning algorithms; Medical diagnostic imaging; Medical services; Real-time systems; System recovery; Training; Transformers
• ISSN: 2836-1873
• DOI: 10.1109/ICCSP64183.2025.11089201

Contemporary healthcare settings need optimal availability, safe data management, and sophisticated analytics to successfully address crises and provide continuous care provision. This study tackles the difficulty of constructing robust and intelligent healthcare systems by using Hewlett Packard Enterprise (HPE) GreenLake's hybrid cloud framework. The primary aim is to amalgamate catastrophe recovery techniques with scalable machine learning capabilities to guarantee operational continuity and enhance decision-making. HPE GreenLake offers a versatile infrastructure-as-a-service solution that facilitates real-time data processing, automatic backups, and rapid system recovery. Modern machine learning methods, like XGBoost, LightGBM, and Transformer-based models, are included in this framework to manage extensive clinical data, improve risk prediction, and facilitate personalized therapy recommendations. These models provide superior accuracy, expedited training durations, and flexibility to evolving healthcare datasets. Results indicate increased system availability, decreased recuperation times, and augmented clinical insights. The integration of HPE GreenLake's infrastructure with sophisticated machine learning methodologies creates a dependable and scalable healthcare solution, enhancing digital resilience and intelligent services in disaster-prone and data-intensive medical settings.