Lead Organisation: Applied Quantum Computing Limited
Project Partners: University College London Evelina London Children’s Hospital and King’s College London, NQCC
Clinicians in Intensive Care Units (ICUs) face overwhelming volumes of patient data under extreme time constraints. Rapid identification of the most pressing risks and supporting evidence from disparate sources is critical to save lives and the prevention or mitigation of long-term disabilities, however, this area of intensive care is currently insufficiently supported by existing technology.
This project explored the potential to use hybrid quantum‑classical risk‑event prediction models to augment existing classical models, evaluating performance across a range of longitudinal and static datasets. The project developed a model that generates clinically valuable predictions while building interdisciplinary expertise between health data science and quantum computing. The primary output was a prototype hybrid quantum‑classical model capable of supporting ICU risk prediction, with the potential for publication as a research paper.