On the morning of August 16, Beijing time, it is reported that at present, scientists have recently developed an AI algorithm that can detect early symptoms of epileptic patients, even those that may be ignored by experienced senior doctors. The results showed that the AI algorithm found 538 cases of FCD symptoms in the scan, including 112 cases that could not be detected by radiologists. The AI algorithm can detect patients with a rare disease with an accuracy rate of more than 60%. In contrast, MRI does not find any hidden symptoms. This rare disease is epilepsy. It is said that the incidence rate of epilepsy in British and American residents is 1%. This disease will lead to uncontrolled brain current bursts in the patient's brain, thus causing spasms and convulsions. Anyone may have convulsions, but it does not mean that they must have epilepsy. Usually, epileptic patients may have convulsions more than once before diagnosis. When the brain suddenly breaks out, epilepsy will occur, leading to the interruption of brain operation. When some patients have seizures, people still remain alert and can sense the surrounding environment. However, some patients will completely lose consciousness and be in an extremely dangerous situation. Sometimes patients with epilepsy may have unusual feelings, cognition and activities, or their bodies may be stiff and fall down on the floor and keep twitching. At any age, stroke, brain infection, head injury or hypoxia at birth may induce epilepsy. In more than 50% of cases, doctors cannot find the specific cause, and relevant epilepsy drugs cannot completely cure it, but it helps to stop or reduce seizures, If the drug treatment is still ineffective, the patient can only choose brain surgery. One of the causes of epilepsy is drug-resistant focal cerebral cortical dysplasia (FCD), which is a subtle abnormality of the brain that leads to the failure of brain signal transmission. Epilepsy can be treated by surgery, but the changes caused by the disease to the brain are very subtle, and even experienced radiologists may ignore the signs of the disease when performing MRI scans. However, based on an AI algorithm developed by the research team of University College London in the UK, 63% of FCD symptoms can be detected, which is difficult for medical personnel to detect before and is also one of the important factors inducing seizures. Researchers say that their AI model can provide the best chance for more epilepsy patients to undergo brain surgery. It is reported that there are about 600000 epileptic patients in the UK, but only 20-30% of the patients do not respond to drugs. Brain cells or neuronal cells usually form an organized cell layer to form the cerebral cortex. For patients with FCD, their brain cells are disordered, resulting in a higher risk of convulsions. Among children with epilepsy undergoing surgical control, FCD symptoms are the most common cause, and FCD is the third most common cause for adults who need surgical treatment. However, it is difficult for medical staff to detect FCD symptoms by MRI scanning. In the latest study, researchers from 2