Project - SLAIDER

SLAIDER is a clinical decision support tool, based on digital twin technology to support the management and support of respiratory emergency admissions. Using SLAIDER, doctors can prioritise respiratory admissions through continuous prediction of mortality risk, better understanding of variation and progression of disease, and identification of patient decline before it occurs. In principle, this will allow earlier clinical interventions – leading to improved patient outcome, particularly in patients who are initially admitted with low or moderate severity conditions. The SLAIDER technology is underpinned by several AI models, overlaid by a computer-based clinical decision support tool - through which individuals interact with the system.

The initial development of AI approaches and demonstrator tools was led by Prof Lu Liu in the initial SLAIDER project. The current project (SLAIDER-QA) led by Dr Free, is moving the SLAIDER technology closer to clinical implementation and deployment by refining the key AI models so they will work across different hospitals and sub-groups. We will achieve this through an initial model evaluation, then by undertaking targeted AI model tuning and refinement where weaknesses have been identified.

References

  1. Gao R, Free RC, Anjum A, Sun X, Woltmann G, Liu L. A Clinical Data Based Framework for Predicting Mortality and Length-of-Stay in Pneumonia Patients. 2024 International Conference on Ubiquitous Computing and Communications (IUCC), 2024, p. 63–9. https://doi.org/10.1109/IUCC65928.2024.00026.

People

  • Lu Liu - PI original SLAIDER project/Co-PI SLAIDER-QA
  • Ashiq Anjum - Co-PI
  • Gerrit Woltmann - Co-PI
  • Chris Brightling - Co-PI
  • Sherif Gonem - Co-PI
  • Rui Gao - Research Associate
  • Xiang Sun - Research Associate
  • Amjad Ali - Research Associate

Links

Funding

  • Self-learning AI-based digital twins for accelerating clinical care in respiratory emergency admissions (2023-2025, EP/Y018281/1, EPSRC/UKRI, L. Liu, £620K)
  • Advanced AI-based Digital Twins For Emergency Respiratory Care (2025-2026, MRC, R. Free, £246K)