Facebook Uses AI To Predict If COVID-19 Patients Will Need More Care (cnet.com) 31
Facebook is harnessing the power of artificial intelligence to help doctors predict whether they will need more resources, such as extra oxygen to care for COVID-19 patients in hospitals. CNET reports: The social network said Friday it developed two AI models, one based on a single chest X-ray, and another from a series X-rays, that could help forecast if a patient infected by the coronavirus is likely to get worse. A third model predicts the amount of extra oxygen a COVID-19 patient might need. Facebook's AI models generally did a better job than a human when it came to forecasting up to four days in advance if a patient will need more intensive care resources.
Partnering with with New York University Langone Health's Predictive Analytics Unit and Department of Radiology, Facebook's AI research is another example of how tech companies are trying to help the health industry battle COVID-19. [...] Facebook's models rely on a technique in which AI learns on its own rather than depending on data labelled by humans, which can be a time-consuming process. The social network and NYU are publishing their research and open sourcing the AI models.
Partnering with with New York University Langone Health's Predictive Analytics Unit and Department of Radiology, Facebook's AI research is another example of how tech companies are trying to help the health industry battle COVID-19. [...] Facebook's models rely on a technique in which AI learns on its own rather than depending on data labelled by humans, which can be a time-consuming process. The social network and NYU are publishing their research and open sourcing the AI models.
Fuck facebook (Score:4, Insightful)
Why anyone allows themselves to be sucked into that PII gravity well is beyond me. So they occasionally throw a bone from their tens of billions of dollars war chest (all earned by monetizing YOU) to an interesting cause. Not worth it.
No thanks.
Re: (Score:1)
Re: (Score:2)
amazing.
facebook practicing medicine without a license
Rather then beg billionaires to advance science (Score:2)
Smart (Score:3)
Re: (Score:2)
It is known exactly why people are susceptible to COVID-19 but the governments aren't listening ( https://www.theguardian.com/li... [theguardian.com] ).
People die from COVID-19 when their immune systems are weak, their immune systems are weak mostly because they don't get enough vitamin D which is gotten predominately from sunlight hitting fat on the skin and creating it.
I've got this... (Score:3)
Aw hell (Score:1)
Help California (Score:2)
Why doesn't Facebook develop an AI to help its home state of California's vaccine rollout? Seems California F'd up the vaccine rollout badly. Instead of prioritizing the most vulnerable (seniors, health care workers, immunocompromised people, customer facing workers) they just made it available to anyone over 65 .. and worse they did it in a manner that means mainly the wealthy will get it. The poor are not going to be able to get it if there is a crowd of people who don't even need it (wealthy seniors can
Re: (Score:2)
Over 65 isn't senior?
AI-powered COVID-19 ads (Score:3)
Why (Score:1)
What kind of AI is it? (Score:2)
It will be needed (Score:2)
With roughly 135,000 people in hospitals across the country due to covid, and approximately 3,700 people dying each day from covid, this might be something useful, for once, coming out of FB.
I see (Score:2)
And i have to watch a few funeral ads before?
Dumb (Score:2)
Or you could just tell people to get their vitamin D level checked FFS.
newhope.com/vitamins-and-supplements/new-study-points-why-vitamin-d-works-covid-19
Well done, Facebook! (Score:4, Informative)
Researchers in the UK did something similar (predicting who would be most seriously affected) back in September, not using X-rays, but using eight parameters commonly collected at admission to hospital [bmj.com] ("Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score").
Then the "University of Minnesota [itnonline.com] develops AI algorithm to analyze chest X-rays for COVID-19" (also reported here [umn.edu]: "New U of M Algorithm Analyzes Chest X-rays for COVID-19". This model was deployed within Epic, a commercial electronic medical records product, which may explain the paucity of journal articles.
And then Northwestern Memorial Hospital [rsna.org] and Northwestern University in Chicago, USA, developed "DeepCOVID-XR: An Artificial Intelligence Algorithm to Detect COVID-19 on Chest Radiographs Trained and Tested on a Large US Clinical Dataset". (Which doesn't make predictions about, e.g., need for oxygen.)
But I'm sure Facebook's model is very nice, too.
Re: (Score:1)
no offence but (Score:2)
Good job! (Score:1)