AI stratification significantly improves treatment outcomes for COVID-19 patients

A recent study published in the journal Clinical Infectious Diseases has demonstrated that the use of an artificial intelligence tool has led to a significant reduction in mortality rates amongst hospitalised COVID-19 patients, including elderly and at-risk populations.¹

The tool is the outcome of a project named ‘Digital Control Centre for COVID-19’ by health innovation body, EIT Health, which was initiated in April 2020. Since then, the tool has undergone development and validation, and has shown early success in the stratification and personalisation of treatment for patients with serious COVID-19 leading to improved treatment responses and, ultimately, a 50% reduction in mortality rates.

As of early August, there have been over 18 million cases of COVID-19 worldwide, and it has led to the death of over 689,000 people.² The main cause of death for patients with COVID-19 is respiratory failure, however many patients experiencing respiratory symptoms can be effectively treated if adequate care is provided at the right timepoint.³

“In many countries, we are seeing deaths from COVID-19 fall as a result of the highly committed work of our healthcare professionals. Additionally, a greater understanding of the trajectory of the disease and its impact on humans, and the availability of better equipment and technology have armed us in the fight against the disease. Health innovation has been a crucial component of our growing strength of response to COVID-19, and has afforded us the opportunity to bring new solutions to improve our ability to overcome the impact of the disease. I am very proud of the early results demonstrated by our ‘Digital Control Centre for COVID-19’ project, which has been rapidly implemented and is already showing its potential to save lives. We look forward to further validation and will work to make it available for as many patients as possible across the globe,” said Jan-Philipp Beck, CEO of EIT Health.

The observational cohort study was conducted amongst 786 patients admitted to Hospital Clinic, Barcelona. Results also demonstrated that the tool was able to predict, with 90% accuracy, the trajectory of the disease in individual patients to allow for timely and appropriate treatment. Use of the tool led to improvements in patients’ condition at day five amongst 93.9% of patients treated with a personalised therapy approach.

The tool works by analysing the data of hospitalised patients with COVID-19 who are experiencing respiratory symptoms, and defining three distinct clinical pattern stratifications which reflect differing symptom complications – inflammation, co-infection and thrombosis. Early knowledge of these symptomatic patterns conferring various clinical complications lead to differing therapeutic approaches and subsequent personalised treatment decisions. 

Researchers at Hospital Clinic Barcelona-IDIBAPS created the artificial intelligence solution capable of analysing, in real time, more than a trillion anonymised data points of COVID-19 patients, identifying clinical patterns and suggesting personalised treatments. This provides a real-time control centre for all COVID-19 patients admitted to hospital, under the supervision of an expert in infectious diseases.

“The artificial-intelligence system that we have built is capable of supporting clinicians in the early diagnosis of patients more prone to develop complications, thus we have been able to provide timely and personalised treatments. This ‘Central Control System’ can be used for multiple applications beyond COVID-19 and represents a clear example of how AI can improve medicine and health outcomes,” said Carolina García-Vidal, Hospital Clínic de Barcelona.

The solution will now be validated and expanded to other hospitals within the EIT Health network, including other Spanish hospitals (Mutua de Terrassa and Hospital Germans Trias i Pujol), the Netherlands (Erasmus MC) and Belgium (University Hospital UZ Leuven, KU Leuven).

To find out more about the EIT Health project, please visit eithealth.eu/project/digital-control-centre-for-covid-19.

References

1. Garcia-Vidal, C., Moreno-García, E., Hernández-Meneses, M., Puerta-Alcalde, P., Chumbita, M., Garcia-Pouton, N., Linares, L., Rico, V., Cardozo, C., Martínez, J.A., García, F., Mensa, J., Castro, P., Nicolás, J.M., Muñoz, J., Vidal, D. and Soriano, A. (2020). Personalized therapy approach for hospitalized patients with COVID-19. Clinical Infectious Diseases.
2. European Centre for Disease Prevention and Control. COVID-19 situation update worldwide, as of 3 August 2020. Available at: ecdc.europa.eu/en/geographical-distribution-2019-ncov-cases. Last accessed: August 2020.
3. Vincent, J.-L. and Taccone, F.S. (2020). Understanding pathways to death in patients with COVID-19. The Lancet Respiratory Medicine.