[ad_1]
Dr Dan Ponticiello, 43, and Dr Gabriel Gomez, 40, intubate a patient with coronavirus disease (COVID-19) at the COVID-19 ICU at Providence Mission Hospital in Mission Viejo, Calif., On January 8, 2021.
Lucy Nicholson | Reuters
Facebook artificial intelligence researchers say they have developed software that can predict the likelihood that a Covid patient will deteriorate or need oxygen based on their chest x-rays.
Facebook, which has worked with academics from the Predictive Analytics Unit and Department of Radiology at NYU Langone Health on the research, says the software could help doctors avoid sending at-risk patients home too soon, while helping hospitals plan for oxygen demand.
The 10 researchers involved in the study – five from Facebook AI Research and five from the NYU School of Medicine – said they developed a total of three “models” of machine learning, all of which are slightly different.
One tries to predict the patient’s deterioration based on a single chest x-ray, another does the same with a sequence of x-rays and a third uses a single x-ray to predict the amount of supplemental oxygen (if any) that a patient might need. .
“Our model using sequential chest x-rays can predict up to four days (96 hours) in advance whether a patient may need more intensive care solutions, typically exceeding the predictions of human experts,” the authors said in a blog post posted on Friday.
William Moore, professor of radiology at NYU Langone Health, said in a statement: “We were able to show that with the use of this AI algorithm, serial chest x-rays can predict the need for escalation of care. in patients with Covid-19. “
He added: “As Covid-19 continues to be a major public health problem, the ability to predict a patient’s need for increased care – for example, admission to intensive care – will be essential for patients. hospitals. “
In order to learn how to make predictions, the AI system received two data sets of chest x-rays from non-Covid patients and one data set of 26,838 chest x-rays from 4,914 Covid patients.
The researchers said they used an AI technique called ‘momentum contrast’ to train a neural network to extract information from chest x-ray images. A neural network is a computer system loosely based on the human brain that can spot patterns and recognize relationships between vast amounts of data.
The research was published by Facebook this week, but experts have already wondered how effective AI software can be in practice.
“From a machine learning perspective, one should study to what extent this translates into new invisible data from different hospitals and patient populations,” said Ben Glocker, who studies machine learning for imaging. at Imperial College London, by email. “From my quick read, it looks like all the data (training and testing) comes from the same hospital.”
Researchers from Facebook and NYU said, “These models are not products, but rather research solutions, intended to help hospitals in the days and months to come to plan their resources. Although hospitals have their own datasets, they often don’t have the computational power to train deep learning models from scratch. “
“We are opening up our pre-trained models (and publishing our results) so that hospitals with limited computing resources can refine the models using their own data,” they added.
[ad_2]
Source link