{"id":2332,"date":"2021-01-15T17:00:17","date_gmt":"2021-01-15T17:00:17","guid":{"rendered":"https:\/\/thenextweb.com\/?p=1334307"},"modified":"2021-01-15T17:00:17","modified_gmt":"2021-01-15T17:00:17","slug":"new-self-supervised-ai-models-scan-x-rays-to-predict-prognosis-of-covid-19-patients","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=2332","title":{"rendered":"New self-supervised AI models scan X-rays to predict prognosis of COVID-19 patients"},"content":{"rendered":"\n
<\/div>\n

Researchers from Facebook and NYU Langone Health have created AI models that scan X-rays to predict how a COVID-19 patient\u2019s condition will develop.<\/p>\n

The team says that their system can forecast whether a patient may need more intensive care resources up to four days in advance. They believe hospitals could use it to anticipate demand for resources and avoid sending at-risk patients home too early.<\/p>\n

Their approach differs from most previous attempts to predict COVID-19 deterioration by applying machine learning techniques to X-rays.<\/p>\n

These typically use supervised training and single timeframe images. This method has shown promise, but its potential is constrained by the time-intensive process of manually labeling data.<\/p>\n

[Read: How Netflix shapes mainstream culture, explained by data<\/a>]<\/em><\/p>\n

These limits led the researchers to use self-supervised learning instead.<\/p>\n

They first pre-trained their system on two public X-ray datasets, using a self-supervised learning technique called Momentum Contrast (MoCO). This allowed them to use a large quantity of non-COVID X-ray data to train their neural network to extract information from the images.<\/p>\n

Predicting COVID-19 deterioration<\/h2>\n

They used the pre-trained model to build classifiers that predict if a COVID-19 patient\u2019s condition will likely worsen. They then fine-tuned the model with an extended version of the NYU COVID-19 dataset.<\/p>\n

This smaller dataset set of around 27,000 X-ray images from 5,000 patients was given labels indicating whether the patient\u2018s condition deteriorated within 24, 48, 72, or 96 hours of the scan.<\/span><\/p>\n

The team built one classifier that predicts patient deterioration based on a single X-ray. Another makes its forecasts using a sequence of X-rays, by aggregating the image features through a Transformer model. A third model estimates how much supplemental oxygen patients might need by analyzing one X-ray.<\/p>\n

They say using a sequence of X-rays is particularly valuable, as they\u2019re more accurate for long-term predictions. This approach also accounts for the evolution of infections over time.<\/p>\n

Their study showed the models were effective at predicting ICU needs, mortality forecasts, and overall adverse event predictions in the longer-term (up to 96 hours):<\/span><\/p>\n

\n
\n
\n
\n

Our multi-image model performance surpassed that of all single-image models. In comparison to radiologists, our multi-image prediction model was comparable in its ability to predict patient deterioration and stronger in its ability to predict mortality.<\/span><\/p>\n<\/blockquote>\n

The team has open-sourced the pre-trained models<\/a> so that other researchers and hospitals can fine-tune them with their own COVID patient data \u2014 using a single GPU.<\/p>\n<\/div>\n<\/div>\n<\/div>\n

You can read the study paper<\/a> on the preprint server Axiv.org.<\/p>\n

Published January 15, 2021 \u2014 17:00 UTC <\/p>\n

Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Researchers from Facebook and NYU Langone Health have created AI models that scan X-rays to predict how a COVID-19 patient\u2019s condition will develop. The team says that their system can forecast whether a patient may…<\/p>\n","protected":false},"author":1,"featured_media":2333,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/2332"}],"collection":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2332"}],"version-history":[{"count":0,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/2332\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/media\/2333"}],"wp:attachment":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2332"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2332"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2332"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}