page contents

This time, the AI technology absolutely made a contribution, and the accuracy rate can reach 99.6%.

                           86d05cd6251543f0a3c0133eb76921b4.png  

It is reported that a new study published by researchers at the University of Louisiana today in "IEEE" shows that they have developed an AI model that can predict seizures an hour in advance, with a success rate of 99.6%.

You know, according to incomplete statistics, there are about 50 million epilepsy patients worldwide. In general, there is little warning when epileptic seizures recur, and 70% of patients can control seizures through drugs. Detecting seizures in advance can greatly improve patients' quality of life and allow enough time for them to cope with their illness.

I believe that everyone is no stranger to artificial intelligence. It is a new technical science that researches and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. The definition of artificial intelligence can be divided into two parts, namely "artificial" and "intelligent". "Manual" is easier to understand and less controversial. Sometimes we have to consider what can be made by manpower, or whether the level of intelligence of the person is high enough to create artificial intelligence, and so on. But in general, "artificial systems" are artificial systems in the usual sense.

In fact, there have been other researches that used brain EEG tests to analyze brain activity to develop predictive models, but because of different brain activity patterns, it is more difficult and requires manual extraction. However, the new research combines the extraction of brain features and the classification process, which is processed by an automated system, which is faster and more accurate.

At the same time, a deep learning algorithm is also introduced to collect the brain activity characteristics recorded by different electrode points, which further improves the prediction accuracy. Researchers tested 22 patients and found that the model had a prediction accuracy of 99.6% and a false alarm rate of 0.004 times per hour.

Finally, the researchers also said that they are developing a chip that can be placed in a smart watch and a sensor embedded in a helmet to help patients with epilepsy, and this time the AI is absolutely successful.


Source: C114 China Communications Network ,translated by Google Translate

Statement: this information is reprinted from authoritative news media. Reprinted for the purpose of transmitting more information and academic exchange, it is not used for commercial purposes, and does not mean to agree with its views or confirm its description. The content of this article is for reference only. If you violate the rights and interests of a third party, please contact us and we will deal with it as soon as possible.         

推荐

  • QQ空间

  • 新浪微博

  • 人人网

  • 豆瓣

取消
技术支持: 机器人行业建站
  • Home
  • 手机
  • 地址
  • QQ