Dr. Dan Ponticiello, 43, and Dr. Gabriel Gomez, 40, intubate the patient with coronavirus disease (COVID-19) in the COVID-19 ICU at Providence Mission Hospital in Mission Viejo, California. , January 8, 2021.
Lucy Nicholson | Reuters
Artificial intelligence researchers at Facebook say they have developed software that can predict the likelihood that a Covid patient will deteriorate or need oxygen based on chest x-rays.
Facebook, which has worked with researchers in the predictive analytics unit and radiology department at NYU Langone Health, says the software could help doctors avoid sending at-risk patients home too early, while helping hospitals plan the request. of oxygen.
The 10 researchers involved in the study – five from Facebook AI Research and five from the NYU School of Medicine – said they had developed three “models” of machine learning in total, which are slightly different.
One tries to predict patient damage based on a single chest X-ray, another does the same with an X-ray sequence, and a third uses a single X-ray to predict how much extra oxygen (if any) he might need. a patient.
“Our model using sequential chest X-rays can predict up to four days (96 hours) in advance whether a patient may need intensive care solutions, generally exceeding the predictions of human experts,” the authors said in -a blog post on Friday.
William Moore, a professor of radiology at NYU Langone Health, said in a statement: “We have been able to show that, using this AI algorithm, serial chest radiographs can predict the need to escalate care in patients with Covid-19. “
He added: “As Covid-19 continues to be a major public health issue, the ability to predict a patient’s need for increased care – for example, admission to the ICU – will be essential for hospitals.”
To learn how to make predictions, the AI system was fed two sets of non-Covid patient chest radiographs and a data set of 26,838 chest radiographs from 4,914 Covid patients.
The researchers said they used an AI technique called “impulse contrast” to train a neural network to extract information from chest X-ray images. A neural network is a vaguely computer-inspired computing system that can detect patterns and recognize the relationships between large amounts of data.
The research was published by Facebook this week, but experts have already questioned how effective AI software can be in practice.
“From a machine learning perspective, we should study how well this translates into new, unseen data from different hospitals and patient populations,” said Ben Glocker, who is researching machine learning for imaging at Imperial College London. by email. “From my written readings, it seems that all the data (training and testing) comes from the same hospital.”
Researchers Facebook and NYU said: “These models are not products, but rather research solutions, designed to help hospitals in the coming days and months with resource planning. While hospitals have their own unique data sets, they often do not have the computing power to train deep learning models from scratch. “
“We are open-sourcing our pre-trained models (and publishing our results) so that hospitals with limited computing resources can adjust the models using their own data,” they added.