Facebook claims to have designed software capable of predicting if a coronavirus patient's health will deteriorate or will need oxygen just by scanning their chest X-rays. Working with New York University (NYU), the social media firm says the system can calculate such developments four days. Together they have built three machine-learning models to assist doctors better prepare as cases around the world continue to rise. One model is designed to predict deterioration using a single chest X-ray, another does the same but through a series of X-rays and the third uses an X-ray to determine if and how much supplemental oxygen a patient may need. Facebook and NYU built three machine-learning models to assist doctors better prepare as cases around the world continue to rise.
Artificial intelligence researchers at Facebook claim they have developed software that can predict the likelihood of a Covid patient deteriorating or needing oxygen based on their chest X-rays. Facebook, which worked with academics at NYU Langone Health's predictive analytics unit and department of radiology on the research, says that the software could help doctors avoid sending at-risk patients home too early, while also 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 have developed three machine-learning "models" in total, that are all slightly different. One tries to predict patient 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 how much supplemental oxygen (if any) a patient might need. "Our model using sequential chest X-rays can predict up to four days (96 hours) in advance if a patient may need more intensive care solutions, generally outperforming predictions by human experts," the authors said in a blog post published Friday.
While deep learning models become more widespread, their ability to handle unseen data and generalize for any scenario is yet to be challenged. In medical imaging, there is a high heterogeneity of distributions among images based on the equipment that generate them and their parametrization. This heterogeneity triggers a common issue in machine learning called domain shift, which represents the difference between the training data distribution and the distribution of where a model is employed. A high domain shift tends to implicate in a poor performance from models. In this work, we evaluate the extent of domain shift on three of the largest datasets of chest radiographs. We show how training and testing with different datasets (e.g. training in ChestX-ray14 and testing in CheXpert) drastically affects model performance, posing a big question over the reliability of deep learning models.
An artificial intelligence (AI) system accurately identified key findings in chest X-rays of patients in the emergency department suspected of having pneumonia in just 10 seconds, researchers from Intermountain Healthcare and Stanford University reported at the European Respiratory Society's International Congress 2019. Traditionally, it takes physicians 20 minutes or more to identify pneumonia from chest X-rays. "In this initial study, we've demonstrated the algorithm's potential by validating it on patients in the emergency departments at Intermountain Healthcare," said Jeremy Irvin, a Ph.D. student at Stanford. "Our hope is that the algorithm can improve the quality of pneumonia care at Intermountain, from improving diagnostic accuracy to reducing time to diagnosis." Early diagnosis could lead to treatment starting earlier, which is vital for severely ill patients, the researchers noted.
With Covid-19 cases surging in parts of the U.S. at the start of flu season, developers of artificial intelligence tools are about to face their biggest test of the pandemic: Can they help doctors differentiate between the two respiratory illnesses, and accurately predict which patients will become severely ill? Numerous AI models are promising to do exactly that by sifting data on symptoms and analyzing chest X-rays and CT scans. For now, the increased availability of coronavirus testing means AI is unlikely to be relied upon for frontline detection and diagnosis. But it will become increasingly important for figuring out how aggressively to treat patients and which ones are likely to need intensive care beds, ventilators, and other equipment that could become scarce if there's a Covid-flu "twindemic." "That's on the forefront of everyone's mind right now," said Anna Yaffee, an emergency medicine physician at Emory University who helped build an online symptom checker to assess Covid-19 patients.