Chinese researchers explore new methods to determine the level of consciousness left over from "plant man"

A new study by Chinese researchers has used language processing ability as an indicator, combining relevant neural characterization synods and machine learning methods to determine the level of consciousness left over from "plant people" and provide new references for patients' clinical diagnosis and treatmentthe study was conducted by Wang Liping Of the Center for Brain Science and Intelligent Innovation of the Chinese Academy of Sciences and the Mao Ying/Wu Xuehai team at Huashan Hospital affiliated with Fudan Universityresearchers, every year, nearly 100,000 patients in China due to brain trauma, stroke, ischemic hypoxic encephalopathy and other diseases into a coma, and then into a long-term consciousness disorder, that is, the traditional sense of the "plant man" stateAmong patients with consciousness disorders, the two most common types of non-reactive awakening syndrome and minimal consciousness state were the most common, and the residual consciousness level and recovery probability were higher in patients with the least consciousness state compared to those with non-reactive awakening syndromeHowever, at this stage, the patient's status identification mainly depends on the observation and scale score of experienced doctors, which has a certain subjectivity and high misdiagnosis ratethe study used simple, wide-ranging bedside electroencephaloelectric recording to capture the neural activity of patients with non-reactive awakening syndrome and minimal consciousness when receiving multiple levels of speech stimulation, and compared them with healthy peopleThe results showed that when the speech sequence containing words, words, sentence structure, etc., the patient group and the healthy subject group showed significant neuroresponse to the word hierarchy structure, but only the cerebellum activity of the healthy subject group significantly reflected the tracking of the word and sentence structureIn the individual analysis, the researchers found that 15 patients showed neural activity to track the structure of words and sentences, and six of them showed significant level semen awareness after 100 days of electroencephalogramWhen dealing with multi-level language sequences, the healthy subjectgroup showed more cerebellum micro-states associated with advanced cognitive processing, while the patient group had a higher probability of appearing in the cerebellum ousterendic state associated with sensory information processingresearchers say machine learning models based on neuroactivity indicators such as "tracking" responses and electroencephalopathy under the above-mentioned language paradigm can more accurately predict the recovery of individuals in patients after 100 days of cerebellum recordingThe research team further introduced a new batch of patient data to generalize the prediction function of the model, and successfully re-demonstrated the accurate classification and prediction effectthe research team says it will further improve the clinical outcome, adaptation and automation of the results in future studies(
Bio valleyBioon.com)