Machine learning predicts treatment response of COVID-19 patients
2021
Imperial College London, London, United Kingdom
This is the first study that examines daily changing clinical parameters of COVID-19 patients and uses AI to understand the clinical response to the rapidly changing needs of patients in intensive care units.
While the AI model was used to a retrospective cohort of patient data collected during the pandemics' first wave, the study demonstrates the ability of AI methods to predict patient outcomes using routine clinical information used by clinicians in intensive care units.
The new findings show that the AI model identified factors that determined which patients were likely to get worse and not respond to interventions such as proning. The researchers found that during the first wave of the pandemic, patients with blood clots or inflammation in the lungs, lower oxygen levels, lower blood pressure and lower lactate levels were less likely to benefit from being proned. Overall, proning improved oxygenation in only 44% of patients.
According to the authors, this approach of analysing each patient's data day by day, rather than just at admission, could be used to improve clinical practice guidelines.
Natural history, trajectory, and management of mechanically ventilated COVID-19 patients in the United Kingdom
Aldo A. Faisal, Brijesh V. Patel
Added on: 06-18-2021
[1] https://link.springer.com/article/10.1007/s00134-021-06389-z[2] https://www.technologynetworks.com/informatics/news/machine-learning-predicts-which-covid-19-patients-will-respond-to-treatment-348706
