Artificial Intelligence (AI) is set to revolutionise the way in which patients across the world are tested for COVID.

Teams at the University of Oxford have found an artificial intelligence (AI) test performed by the bedside in 10 minutes has been shown to quickly and safely triage patients coming to hospital for COVID-19. The new test will enable hospitals around the world without access to onsite laboratory facilities to quickly ascertain whether a patient is suffering from the virus and adapt the treatment accordingly with the expectation of saving significant number of lives.

During a three-month evaluation at the John Radcliffe Hospital in Oxford, the CURIAL-Rapide study showed that COVID-19 screening results were available 45 minutes after patients arrived in the emergency department – 16 minutes, or 26 per cent, faster than lateral flow tests (LFTs)

When compared against results of PCR testing, CURIAL-Rapide was more likely to identify COVID-19 patients than the LFTs, and correctly ruled out the infection 99.7 per cent of the time.

Lead researcher and NIHR Academic Clinical Fellow at the John Radcliffe Hospital Dr Andrew Soltan said: “Many of our patients coming to the ED are in the most vulnerable groups. CURIAL-Rapide is exciting because it uses new near-patient testing to collect all the data needed for a prediction by the bedside in 10 minutes, cutting out the time for transporting samples to a lab. This means infected patients are identified sooner, while patients being admitted with other conditions can be quickly and safely transferred to wards where they are less likely to be exposed.

“This technology can help hospitals run more smoothly and may make a particularly big difference for smaller hospitals where there isn’t a lab on site. CURIAL is an example of how the collaborative strength of the NHS, bringing together universities with hospital groups across the country, is helping to build an evidence base for safe and responsible use of clinical AI.”

The study found that the AI test performed consistently across 72,000 admissions to five UK hospitals, providing high-confidence negative results for uninfected patients up to 98.8 per cent of the time. As well as Oxford University Hospitals, the study was carried out with University Hospitals Birmingham NHS Foundation Trust, Portsmouth University Hospitals NHS Trust and Bedfordshire Hospitals NHS Foundation Trust.

The study also found that CURIAL-Rapide was 21 per cent more effective at identifying COVID-19 patients than LFTs between December 2020 and March 2021.

The AI screening test uses routine tests to screen emergency department patients for COVID-19. The new version of CURIAL uses only tests that can be performed at the bedside, achieving a 10-minute processing time without needing access to a laboratory.

During a three-month evaluation period at the John Radcliffe Hospital, CURIAL-Rapide results were available almost seven hours sooner than PCR results, and correctly ruled out COVID-19 for 58.5 per cent of negative patients who were triaged by a clinician to ‘COVID-19-suspected’ (amber) areas

OUH Consultant in Emergency Medicine and Ambulatory Care, Dr Alex Novak said: “The CURIAL studies are an exciting demonstration of the potential for AI-led diagnostic tools in acute clinical settings, with the power to rapidly translate into tangible benefits for patient care and optimise service performance at the frontline.”

Emergency medicine consultant at OUH Dr Ravi Pattanshetty added: “CURIAL has proven to be a very effective tool for both rapid front-door diagnosis of COVID-19 and to ease the patient flow through the hospital. This ultimately results in fewer hospital acquired infections and opens up an exciting prospect for future AI tools to help overburdened emergency departments.”

Dr Soltan, also a researcher at Oxford University’s Radcliffe Department of Medicine, added: “Lateral flow tests help identify cases sooner, giving high-confidence positive results. But negative results are more uncertain – in our evaluation LFTs gave negative results for almost half (43 per cent) of patients who went on to swab positive. CURIAL-Rapide complements LFDs with high-confidence negative results in minutes. Combining the two rapid tests gives the best performance, and both results are available within one hour.”

The study found that the AI test performed consistently across 72,000 admissions to five UK hospitals, providing high-confidence negative results for uninfected patients up to 98.8 per cent of the time. As well as Oxford University Hospitals, the study was carried out with University Hospitals Birmingham NHS Foundation Trust, Portsmouth University Hospitals NHS Trust and Bedfordshire Hospitals NHS Foundation Trust.

Follow us on twitter: @risksEmerging