Machine learning lessons predict path for ICU COVID patients

摘要

A team led by Imperial College London has developed an AI model to predict the trajectory of Covid-19 patients in intensive care units(ICUs). The machine learning approach makes predictions about how conditions might progress, and whether patients respond positively to 'proning', the process of turning a patient onto their front to improve lung oxygenation. When ineffective, it can delay the start of sequential treatments such as extracorporeal membrane oxygenation (ECMO), a life-support machine that supports the heart and lungs. Researchers said that by using AI to analyse patients' data daily, guidelines in clinical practice could be improved and applied to future waves of the pandemic as well as treatment of similar diseases. Dr Brijesh Patel, clinical science lead at Imperial's Department of Surgery & Cancer and senior intensivist at Royal Brompton Hospital said ECMO has associated risks and is the last resort for many patients, after all other less invasive interventions have failed.