Scientists from the Swiss Federal Institute of Technology have trained artificial intelligence to detect heart defects in newborns with 80-90% accuracy. Research results published In International Journal of Computer Vision (IJCV).
Researchers began training the artificial intelligence by feeding hundreds of videos taken during ultrasound examinations of the hearts of 192 newborns into the algorithms. In addition, the data set included moving images of beating hearts taken from different angles, as well as information about the diagnoses made by experienced pediatric cardiologists based on these images.
To test the diagnostic performance of the completed model, the researchers provided a second set of ultrasound images of baby hearts that the algorithms had not previously analyzed. The results showed that the AI model was able to make a correct diagnosis in approximately 80-90% of cases. Additionally, the new algorithm accurately determined the severity of the disease with 65-85% accuracy.
According to the researchers, healthcare institutions with highly trained specialists could use this model in the future to reduce staff workload and increase diagnostic accuracy.
Previous scientists I learnedHow much fish should you eat a day for heart health?
What are you thinking?
Source: Gazeta
Barbara Dickson is a seasoned writer for “Social Bites”. She keeps readers informed on the latest news and trends, providing in-depth coverage and analysis on a variety of topics.