This study introduces a multi-cloud framework for biomedical image storage and retrieval, utilizing blockchain for secure access control. It ensures data integrity, prevents unauthorized access, and enables healthcare providers to share patient records efficiently while maintaining HIPAA compliance and reducing operational complexity.

Isabelle Catherine Renner, Julian Thomas Wexler, Edgar Lawrence Whitmore, Celeste Annabelle Clifton, Malcolm Vincent Bowden

This paper develops a cloud-powered diagnostic model that utilizes longitudinal health data for proactive chronic disease management. It enables real-time monitoring, early symptom detection, and predictive alerts, significantly improving quality of care for patients with long-term conditions like diabetes, hypertension, and heart disease.

Theodore James Walden, Fiona Meredith Paxton, Gregory Louis St. James, Aurora Lillian Beckett, Henry Wallace Tinsley

This paper introduces an NLP-enhanced framework for analyzing cloud-hosted electronic health records. It extracts clinical insights from unstructured data to identify risk patterns, aiding in personalized treatment plans and reducing diagnostic errors through semantic interpretation of patient histories and physician notes.

Douglas Peter Kinsley, Naomi Juliette Fairchild, Roland Timothy Godfrey, Beatrice Evelyn Moors, Simon Edward Layton

This research presents a distributed simulation system for protein-ligand binding prediction, hosted across federated cloud environments. The approach accelerates drug discovery by allowing concurrent processing of molecular interactions, improving candidate screening efficiency for pharmaceutical companies and biomedical research laboratories.

Quentin Richard Lomax, Harriet Josephine Fairley, Sebastian Douglas Marwick, Matilda Grace Lefevre, Tobias Charles Halford

This work proposes an AI-driven triage system deployed on cloud platforms. It processes real-time patient data streams in emergency departments to support fast and accurate triage, reducing wait times and improving critical care outcomes through predictive modeling and patient prioritization algorithms.

Julian Frederick Harrow, Charlotte Emily Redgrave, Oliver Francis Whittaker, Genevieve Alice Barrow, Edward Nathaniel Sterling

This paper proposes a privacy-preserving federated learning framework to analyze cancer imaging data stored across multiple hospitals. Without transferring raw data, the model collaboratively learns prognosis patterns, ensuring patient confidentiality and supporting precision oncology through decentralized artificial intelligence integration.

Lawrence Daniel Vickers, Amelia Florence Baird, Marcus William Houghton, Stephanie Louise Calder, Nathaniel James Prescott

This paper introduces a synchronized edge-cloud platform using deep neural networks for remote health monitoring of elderly individuals. The system detects anomalies in vital signs in real-time, enabling timely medical response and improving the safety of aging-in-place care environments.

Jonathan Maxwell Boyd, Eleanor Scarlett Hume, Dominic Charles Bainbridge, Lydia Rose Connolly, Patrick Louis Fenwick