Dem Dx Triage Support Platform for Ophthalmology Referrals

Background A steady increase in the use of Ophthalmology services over the past 2 decades combined with a forecasted shortfall of trained ophthalmologists, make the optimisation of patient triage vital if delivery of care is to be maintained or improved.

No globally recognised triaging system for Ophthalmic emergencies yet exists and physician-defined risk stratification is currently considered as gold standard care.

Aims and objectives This project aims to train and test machine learning algorithms on Dem Dx s novel Triage Platform and assess how well it supports allied healthcare professionals (AHPs) to perform triage and improve operational efficiency in the Ophthalmology Emergency Department.

Methods and timeline for delivery The 24-month project divides broadly in three stages and includes: Stage 1: train and test period for the Triage Platform s ML algorithms using live Electronic Medical Record data from Moorfields Eye Hospital combined with SNOMED CT data input by the triage consultant in Dem Dx.

Stage 2: assessment of the Triage Platform s ML algorithms performance, safety and usability when applied by inexperienced healthcare providers in simulated scenarios derived from real cases.

Stage 3: multi-centre, prospective, quasi-experimental study to evaluate the accuracy and clinical effectiveness of the triage platform s AI algorithms Anticipated impact and dissemination It is expected that the Dem Dx Triage Platform will increase the efficiency and safety of triage performed by nurses and allied healthcare professionals in ophthalmology services and improve the patient experience by reducing wait and consultation times.

The product is also likely to reduce the number of inappropriate referrals to Ophthalmology and promote better integration with tertiary care.