Key points from article :
Machine-learning tool that can predict when a COVID patient will deteriorate.
Helps customise individual's treatment to avoid the worst outcome.
3 trillion pieces of structured and anonymised data from 2,000 patients was analysed.
Goal was to train it to recognise patterns and check what treatments were the most effective.
"There are patients with an inflammatory response, patients with coagulopathies and patients who develop super infections," Carol Garcia-Vidal, researcher.
Each group needs different drugs and thus a personalised treatment.
AI system has been developed into a real-time dashboard display on physicians' computers.
The tool enables patients to be classified and offered a more personalised treatment.
The predictions are 90% accurate.
Study by Hospital Clinic in Barcelona.
