India logs 18,930 new Covid-19 cases with 35 fatalities making the active cases rise to 1, 19,457 in the last 24 hours. Currently, the diagnosis of COVID-19 is based on nucleic acid testing, or commonly known as the PCR tests. However, these tests produce false negatives and the results can also be affected by hysteresis, which is when the physical effects of an illness lag behind their cause.
Artificial intelligence (AI) offers an opportunity to rapidly screen and effectively monitor COVID-19 cases on a large scale. This process not only reduces the burden on doctors but also is quick and efficient. Recently, researchers have created a new AI tool that can detect COVID-19. The software analyses chest CT scans and uses deep learning algorithms to accurately diagnose the presence of viruses. The accuracy rate of these scans is 97.86% and it is currently the most successful COVID-19 diagnostic tool from all around the world.
Researchers from the University of Leicester (Leicester, UK) who developed the new AI tool will now further develop this technology.The Covid computer may eventually replace the need for radiologists to diagnose COVID-19 in clinics and hospitals. The software is claiming to even be deployed in portable devices such as smartphones. It is also believed by the researchers that the device will also be adapted and expanded to detect and diagnose other chronic and acute diseases such as breast cancer, Alzheimer’s Disease, as well as cardiovascular diseases.
Taking it to the press release, Professor Yudong Zhang, Professor of Knowledge Discovery and Machine Learning at the University of Leicester said, "Our research focuses on the automatic diagnosis of COVID-19 based on a random graph neural network. The results show that our method can find suspicious regions in the chest images automatically and make accurate predictions based on the representations."
"The accuracy of the system means that it can be used in the clinical diagnosis of COVID-19, which may help to control the spread of the virus. We hope that, in the future, this type of technology will allow for automated computer diagnosis without the need for manual intervention, in order to create a smarter, efficient healthcare service," the professor further added.