题型:阅读理解 题类:常考题 难易度:普通
黑龙江省双鸭山市第一中学2020届高三上学期英语12月月考试卷
Artificial intelligence can predict when patients with a heart disorder will die, according to scientists.
The software learned to analyze blood tests and scans of beating hearts to spot signs that the organ was about to fail. The team, from the UK's Medical Research Council, said the technology could save lives by finding patients that need more aggressive treatment. The results were published in the Journal of Radiology.
According to the researchers, high blood pressure in the lungs damages part of the heart, and about a third of patients die within five years after being diagnosed. There are treatments: drugs, injections straight into the blood vessels, a lung transplant. But doctors need to have an idea of how long patients might have left, in order to pick the right treatment.
The software was given scans of 256 patients' hearts, and blood test results. When this data was combined with eight years of patient health records, the artificial intelligence predicted when patients would die.
The software could look about five years into the future. It correctly predicted those who would still be alive after one year about 80% of the time. The figure for doctors is 60%.
The team now want to test the software works in other patients in different hospitals before assessing whether it should be made widely available to doctors. The researchers also want to use the technology in other forms of heart failure, such as cardiomyopathy, to see who might need a pacemaker or other forms of treatment.
Dr Mike Knapton, from the British Heart Foundation, said, "This exciting use of computer software in medical practice will help doctors in the future to make sure that patients are receiving the correct treatment before the condition deteriorates and leaves them needing a lung transplant. The next step is to test this technology in more hospitals with heart disease."
To the Editors: I am surprised to read that Dr. Strojnik ("Direct Detection of Exoplanets," September-October2023) states that we have not yet and cannot directly image exoplanets (外部行星). This is incorrect. NASA/IPAC has a list at exoplanetarchive.ipac.caltech.edu/does/imaging.html. One example is an image of 51 Eridani b. The planet is 2.6 times as massive as Jupiter and has the same radius (半径). Gerard Kriss Space Telescope Science Institute |
Dr. Gerard: I am pleased that my article brought a response. The phrase "planet detection" arouses in people's imaginations beautiful images of planets that are creative artistic representations of novel worlds. But a blur of brightness is not an image. Exoplanet researchers routinely call videos such as the one below of 51 Eridani b "direct images" because the planet's light has been separated from that of its star. "Directly imaged" is the standard language of exoplanet astronomy. But to an optical (光学的) scientist such as myself, there is a strong distinction between direct detection (the planet's light separated from the light of its star) and direct imaging (a proven picture of the exoplanet). From an optical researcher's perspective, a single bright spot simply is not an image. Indeed, even the word "direct" in direct detection is debatable from an optical researcher's point of view. The detection of the light of the exoplanet requires significant processing, adding multiple images and removing starlight based on theoretical models of the source signal. But the interpretation of a bright spot as a planet is only possible upon visual inspection and optimistic thinking. As an optical scientist, I cannot look at a single spot and call it an image of exoplanets. A trajectory (轨迹), or a series of bright points, is not an image of a planet, although it very likely represents something that nowadays is described as an exoplanet. Marija Strojnik |
试题篮