This research proposes scalable genomic data pipelines in the cloud to support precision oncology. By integrating patient-specific sequencing data with curated medical databases, the platform enables real-time, personalized cancer treatment recommendations within clinical decision support systems.

Leonard Arthur Beckford, Florence Helena Windermere, Tobias Michael Falkner, Victoria Mae Levingston, Richard Owen Stanbridge

This paper introduces blockchain-based encryption methods for secure medical image transmission across cloud networks. Emphasizing efficiency and confidentiality, the model safeguards diagnostic data from breaches while ensuring accessibility and traceability across medical centers in distributed healthcare environments.

Graham Percy Hargrove, Isla Josephine Cromwell, Benedict Raynor Tomlinson, Harriet Eloise Grimsby, Henry Maxwell Pennington

This work presents a post-operative monitoring system using cloud-synced wearables to track patient recovery. AI models analyze vital signs and movement to detect anomalies, triggering alerts to healthcare professionals and enabling faster responses and better outcomes for post-surgical patients.

Nathaniel Julian Cavendish, Daisy Madeleine Frobisher, Hugo Quentin Alderidge, Charlotte Eliza Fernwood, Felix Dominic Tilling

This study presents a federated AI framework for pandemic surveillance using decentralized healthcare cloud systems. It enables secure collaboration among hospitals and agencies, offering real-time epidemic trend analysis and coordination tools while ensuring data sovereignty and minimizing exposure of sensitive health information.

Julian Charles Mortimer, Clara Annabel Redgrave, Edward Montague Sherborne, Penelope Louise Yates, Oscar William Featherstone

This paper introduces a cloud-enabled natural language processing (NLP) framework that automates the extraction of medical insights from unstructured electronic health records. The system enhances clinical decision-making and research efforts by identifying key entities, conditions, and procedures with minimal manual input.

Archibald Louis Treadwell, Evangeline Iris Mallory, Sebastian George Littman, Florence Eleanor Barrington, Miles Augustus Kingsley

This study explores a cloud-enabled ensemble learning system that processes multimodal biomedical imaging to support clinical diagnosis. By combining data from various imaging sources, the framework enhances diagnostic accuracy and assists radiologists with real-time, interpretable outputs through secure and scalable computation.

Maxwell Ethan Hollister, Beatrice Lorraine Ashcroft, Frederick Simon Calloway, Violet Georgina Henley, Charles Vincent Dunsmore

This research proposes a federated learning model to analyze cloud-hosted biomedical datasets while preserving patient privacy. By training models locally and sharing only encrypted parameters, institutions collaborate on predictive health analytics without transferring sensitive patient records or violating data governance policies.

Elijah Marcus Rutherford, Isabella Jane Trevelyan, Hugo Leonard Penn, Matilda Frances Grosvenor, George Winston Balmoral