This breakthrough AI can detect lung diseases with 98% accuracy
%2Favatars%2FseRriXmiCDz3.png&w=96&q=75)
%2F2022%2F11%2F07%2Fimage%2Fjpeg%2FPKkzakeeykeJKVoyi5McaMNbBvdCepafEMpRBfBx.jpg&w=3840&q=75)
Researchers at the University of West Scotland (UWS) believe that groundbreaking artificial intelligence (AI) could help reduce winter stresses and demands on hospitals. The innovative approach, using AI, would automatically diagnose lung diseases, such as pneumonia and tuberculosis.
The research was published in the journal Computer Methods and Programs in Biomedicine.
Both tuberculosis and pneumonia can be serious infections that affect the lungs. The diagnosis of lung diseases usually requires various different diagnostic tests. This often includes X-rays, blood tests, ultrasounds and CT scans. The tests often take a long time before seeing results and can be costly.
The use of AI in hospitals is both quick and effective
The innovative artificial intelligence software was created by UWS, with the equipment originally being created to quickly detect Covid-19 from X-ray images. Unlike the diagnostic tests that can take a long time before getting results, the AI software can detect numerous lung diseases within a few minutes, and it has an accuracy rate of about 98%.
Due to Covid, there have been shortages of hospital workers, and the research team wants this new AI to help alleviate some of the stress, while still being accurate. “Systems such as this could prove to be crucial for busy medical teams worldwide,” said Naeem Ramzan, a professor and researcher at the University of the West of Scotland.
“There is no doubt that hospital departments across the globe are under pressure and the outbreak of Covid-19 exacerbated this, adding further strain to pressured departments and staff. There is a real need for technology that can help ease some of these pressures and detect a range of different diseases quickly and accurately, helping free up valuable staff time,” Ramzan continued.
Improving efficiency
Although the pandemic exacerbated the strain on hospital departments, researchers believe AI could improve the efficiency. The research team wants to incorporate AI with diagnostic tools to provide cost-effective, fast results. One example given is to combine X-ray imaging with artificial intelligence development.
“X-ray imaging is a relatively cheap and accessible diagnostic tool that already assists in the diagnosis of various conditions, including pneumonia, tuberculosis and Covid-19. Recent advances in AI have made automated diagnosis using chest X-ray scans a very real prospect in medical settings,” Ramzan stated.
How the technique works
The new equipment uses the X-ray imaging, and compares it to a database of thousands of images from patients with pneumonia, tuberculosis and Covid. Then, it uses an AI process called deep convolutional neural network (CNN), which is a type of deep learning used for processing data, to make a diagnosis. The convolutional neural network is an algorithm that analyzes the images.
During the testing phase of the study, the technique was 98% accurate, proving to be a precise method to diagnose patients with lung diseases.
“Hospitals around the world are under sustained stress,” said Milan Radosavljevic, vice principal of research, innovation and engagement and a professor at University of West Scotland. He considers this AI technique a prospective breakthrough for assisting hospital around the world. “I am excited about the potential of this innovative technology, which could help streamline diagnostic processes and reduce strain on staff,” Radosavljevic stated.
The researchers at UWS want to see if the AI technique can be used to diagnose other diseases, using both diagnostic testing and artificial intelligence combined.
SHOW COMMENT (1)
/2023/09/24/image/jpeg/LbEWVi9Dqey9YK0OQQHLWcm6Fwci9Kgmhp4SL6OG.jpg "10 ancient civil engineering projects still in use")
/2023/09/29/image/jpeg/CgvojW8A2ZSvSGUgZfeXG2VUxdfycbnyJv0q38d3.jpg "DNA traces found in 6 million-year-old sea turtle fossil")
/2023/09/29/image/jpeg/RrX2kEmmZ1o1RMmyyPOMj1PXeGrCpPz5yv0xHs1e.jpg "As Cybertruck nears launch, rival Rivian hopeful of co-existence")
/2023/09/22/image/jpeg/hd1J991kaJ0so68o8OVeU417E9Bzrj97quX6S7wI.jpg "How much water is there on the Moon? Maybe not enough")
/2023/08/26/image/png/ny1gzL2fwjRLIco8gac58tlSGZKREl4XSp340YAB.png "12 science, tech, and engineering newsletters you need to check out")
/2023/09/29/image/jpeg/8xosgjZ67SF6roiiwn6ib9jmCpwBCes6wGXo835Q.jpg "Research reveals microplastic invasion in secluded cave")
/2023/08/25/image/png/5hf1N5LFzyDY4pUpvoJ0BtpujwCPfsL68t1cAIVj.png "Why is anti-piracy software Denuvo stirring controversy?")
/2023/09/29/image/jpeg/voFjWPgxbHXwheGsIQF2L0gAW0jbujHVnN2I2wEN.jpg "GE Aerospace’s Sensiworm made flying safer!")
/2023/09/29/image/jpeg/yVsayzDNtxHyk3cS8n0D6vGxBV7qEZPqNkBUesAg.jpg "Around the world with no emissions with Solar Airship One")
/2023/09/21/image/jpeg/KSYsTrNRY77vCRGQzEDgxQo3CmUW36h1aX2tqBPX.jpg "7 of the maddest ship designs ever conceived by engineers")