Facebook claims its AI can predict four days in advance if the condition of a coronavirus patient will deteriorate, just by looking at a single chest x-ray
- Facebook and NYU built AI to predict the evolution of patients with COVID
- It was formed with thousands of chest X-rays with and without COVID
- The software is based on a series of three machine learning models
- One predicts deterioration with one scan and another uses scan sequences
- The third model is able to predict whether supplemental oxygen will be needed
Facebook claims to have designed software capable of predicting whether a coronavirus patient’s health will deteriorate or need oxygen just by scanning their chest x-rays.
Working with New York University (NYU), the social media firm says the system can calculate these developments in four days.
Together they have built three machine learning models to help doctors better prepare as cases around the world continue to increase.
One model is designed to predict deterioration using a single chest x-ray, another does the same but using a series of X-rays and the third uses an x-ray to determine if and how much extra oxygen a patient may need.
Scroll down to see the video
Facebook and NYU built three machine learning models to help doctors better prepare as cases around the world continue to rise. One model is designed to predict deterioration by a single chest x-ray, another does the same but by a series of X-rays
The coronavirus has maintained a strong position in the world for over a year, starting in Wuhan, China.
There are more than 93 million cases worldwide and about two million people have lost their lives due to the virus.
However, the United States has had the largest weight with more than 23 million cases and more than 389,000 deaths.
As cases continue to rise, scientists and technology companies are working on innovative ways to detect symptoms before they take a deadly turn.
The third uses an x-ray to determine if and how much extra oxygen a patient may need. AI can make predictions four days in advance based on X-rays.
Facebook and NYU have five researchers who have worked on coronavirus prediction software.
“Our model that uses sequential chest X-rays can predict up to four days (96 hours) in advance if a patient may need intensive care solutions, usually exceeding the predictions of human experts,” the authors said in a publication on the blog posted Friday.
The team first “pretended” the model with a public chest X-ray database to MIMIC-CXR-JPG and CheXpert.
The system then formed into NYU coronavirus chest X-rays, which included a total of 26,383 images of 4,914 patients, allowing the models to label the condition of a worsening patient with 24, 48, 72 or 96 hours of the scan in question.
“Based on reader studies we conducted with radiologists at NYU Langone, our models that used X-ray imaging sequences outperformed human experts in predicting ICU needs and mortality predictions, and general predictions of long-term adverse events (up to 96 hours), ”the team shares on the blog.
“Being able to predict whether a patient will need oxygen resources would also be the first and could help hospitals as they decide how to allocate resources in the coming weeks and months.”
Facebook claims to have designed software capable of predicting whether the health of a coronavirus patient will deteriorate or need oxygen just by scanning their chest x-rays
William Moore, MD, professor of radiology at NYU Langone Health, shares in a statement: “We have been able to show that with the use of this AI algorithm, serial chest x-rays can predict the need for a escalation of care in patients with COVID -19. ‘
“Because COVID-19 remains a major public health problem, the ability to predict a patient’s need to elevate care (e.g., admission to the ICU) will be essential for hospitals.”