Intervention Effect Of Transcranial Magnetic Stimulation On The Microstate Of Male Heroin Addicts

Substance use disorder is a social and health problem that exists in various countries.The EEG microstate time series level in the resting state with eyes closed is an important indicator to reflect the state of the individual brain.A large number of studies have proved the relationship between substance use disorder patients and healthy individuals.Differences in microstate levels also account for changes and impairments in brain structure in substance use disorder patients.However,the existing studies on the microstates of patients with substance use disorders have focused on methamphetamine and nicotine,so are there differences in the levels of microstates between patients with heroin use disorder and healthy individuals?iTBS is a high-frequency stimulation mode.Studies have confirmed that rTMS can cause changes in individual microstates.At the same time,studies have shown that rTMS can reduce cravings and improve cognitive function and sleep in patients with heroin use disorder.So can iTBS treatment improve microstate levels in patients with heroin use disorder? K-means clustering analysis in machine learning is often used to solve the problem of classification and identification of similar groups.Can the K-means clustering algorithm be used to illustrate the effectiveness of iTBS in intervening microstates in patients with heroin use disorder? In this study,the resting-state EEG signals were collected to explore the difference indicators of microstate between heroin addicts and healthy individuals.After 11 days of iTBS treatment,the difference indicators between the two were selected as features,and the K-means clustering algorithm was used to analyze the differences between the two.Heroin abstinent and healthy individuals before and after the intervention were classified to illustrate the effectiveness of the treatment.Experiment 1 explored the differences in microstate levels between heroin addicts and healthy individuals.By collecting resting-state EEG signals of 30 heroin addicts and 30 healthy individuals,microstate analysis and independent samples t-test were performed.The experimental results show that the occurrence frequency and coverage time of microstate category A in heroin abstainers are significantly lower than those in healthy individuals.In experiment two,32 heroin abstainers were subjected to iTBS intervention for 11 consecutive days,their resting-state EEG signals were collected before and after the intervention,and EEG signals were collected from 35 healthy individuals,followed by microstate analysis.The resulting difference indicators(the number of occurrences and the percentage of coverage time of microstate category A)were used as the characteristics of cluster analysis,and the K-means clustering algorithm was used to classify heroin abstinent and healthy individuals before and after the intervention into three categories.The experimental results show that: compared with before the intervention,the cluster center of the addiction group after the intervention is closer to the healthy group,and when the heroin group and healthy individuals after the intervention are grouped together,the F1-score is 83%,that is,after the intervention.The heroin group was more similar to the healthy group,proving the effectiveness of iTBS in intervening heroin abstinent microstates.This study uses a combination of resting-state EEG microstate analysis and clustering algorithms in machine learning to discover specific differences in microstate indicators between heroin addicts and healthy individuals,and uses Kmeans cluster analysis in machine learning.It proves the effectiveness of iTBS in intervening microstate of heroin addicts,and provides a new method for the diagnosis and intervention effect of heroin addiction in the future.