Current forms of artificial intelligence are already capable of accurately detecting fractures on X-rays that are difficult to observe with the naked eye. These are the findings of a study conducted by a professor of radiology at Boston University School of Medicine.
The algorithm used proved to be capable of quickly and automatically detecting fractures of limbs, pelvis, torso, lumbar spine and thoracic cage. When combined with the expertise of specialists, it reduced the number of fractures missed by 29% while improving precision by 5%.
Using this algorithm, diagnoses could be made more reliably and, in particular, more rapidly than human interpretation. The first benefit of such a technology would be to reduce the waiting time in hospitals, especially in emergency departments.
According to those who worked on this study, these findings concerning the diagnosis of fractures could potentially be applied in a similar fashion to various diseases and disorders. The idea is not to replace doctors but to assist them in their work in an intelligent way.
Detailed results of the study can be found on the website Radiology. – AFP Relaxnews