Google is able to detect 26 skin diseases accurately
Google has announced that its own artificial intelligence system is able to detect 26 skin diseases accurately such as dermatologists according to the site VentureBeat specialized in technical news, where dermatology is one of the most common diseases in the world, after colds And fatigue and headaches.
It is estimated that 25 percent of all treatments offered to patients worldwide are for skin diseases, and up to 37 percent of patients seen in the clinic have at least one skin complaint.
This trend prompted Google researchers to create an artificial intelligence system capable of detecting the most common skin diseases in primary care.
Google explained in a new research paper that the system is able to detect 26 skin diseases accurately when presented with images and descriptive data about the patient's condition, and claims to be on an equal footing with U.S.-accredited dermatologists.
Google software engineer Yuan Liu and Google Health's technical program manager Peggy Bui wrote: We have developed a deep learning system (DLS) to treat the most common skin diseases in primary health care.
"This study highlights the potential of DLS to increase the capacity of general practitioners who did not have additional specialized training to accurately diagnose dermatology," they added.
Google explained that dermatologists do not give a single diagnosis of any skin disease, but rather create a neat list of possible diagnoses to be systematically narrowed through subsequent laboratory tests, imaging, procedures and consultations.
Google follows the same method, processing inputs that include one or more clinical images of skin abnormalities and up to 45 types of metadata, such as age, , and symptoms.