AI-powered brain injury assessment machine developed in China

Chinese researchers develop an AI brain imaging machine for patients with brain injury to determine prognosis


Chinese researchers from the Chinese Academy of Sciences, in collaboration with doctors from the People's Liberation Army General Hospital and General Hospital of Guangzhou Military Command, have developed an artificial intelligence (AI) model to detect brain injury severity.

The AI-powered medical imaging machine aims to provide patients with an accurate assessment system to determine brain network functionality.

Ming Song, lead researcher from the Chinese Academy of Sciences, said: "We believe the model can make an accurate assessment and might help families of DOC patients understand the outcomes in advance and make an informed decision."

Visit Innovation Enterprise's Big Data & Analytics Innovation Summit in Beijing on November 21-22, 2018

According to Chinese news agency Xinhua, during the development of the model and in order to train the machine, there was a number of brain images recorded onto the system from approximately 63 patients with disorders of consciousness (DOC) after one month of their brain injury.

Following the data feed, the model then assessed the patients according to the information being recorded in the likelihood of recovery and provided a diagnosis. According to the research published in eLife, the machine had an accuracy count rate of 88% in 100 cases from the datasets from both hospitals.

"This study aimed to develop a multidomain prognostic model that combines resting state functional MRI with three clinical characteristics to predict one-year outcomes at the single-subject level," the report stated.

A 2015 report from the Chinese Journal of Traumatology, Current status of traumatic brain injury treatment in China, revealed that traumatic brain injury cases in 2015 in China accounted to three to four million with an average mortality rate of 30–40%.


 Written by Innovation Enterprise Digital Content Editor, Simorin Pinto

Old media vs new media small

Read next:

Infographic: Old media vs new media