Abstract
Purpose To identify cerebral radiomic features related to the diagnosis of Internet gaming disorder (IGD) and construct a radiomics-based machine-learning model for IGD diagnosis. Methods A total of 59 treatment-naïve subjects with IGD and 69 age- and sex-matched healthy controls (HCs) were recruited and underwent anatomic and diffusion-tensor magnetic resonance imaging (MRI). The features of the morphometric properties of gray matter and diffusion properties of white matter were extracted for each participant. After excluding the noise feature with single-factor analysis of variance, the remaining 179 features were included in an all-relevant feature selection procedure within cross-validation loops to identify features with significant discriminative power. Random forest classifiers were constructed and evaluated based on the identified features. Results No overall differences in the total brain volume (1,555,295.64 ± 152,316.31 mm3 vs. 154,491.19 ± 151,241.11 mm3), total gray (709,119.83 ± 59,534.46 mm3 vs. 751,018.21 ± 58,611.32 mm3) and white (465,054.49 ± 51,862.65 mm3 vs. 470,600.22 ± 47,006.67 mm3) matter volumes, and subcortical region volume (63,882.71 ± 5110.42 mm3 vs. 64,764.36 ± 4332.33 mm3) between the IGD and HC groups were observed. The mean classification accuracy was 73%. An altered cortical shape in the bilateral fusiform, left rostral middle frontal (rMFG), left cuneus, left parsopercularis (IFG), and regions around the right uncinate fasciculus (UF) and left internal capsule (IC) contributed significantly to group discrimination. Conclusions: Our study found the brain morphology alterations between IGD subjects and HCs through a radiomics-based machine-learning method, which may help revealing underlying IGD-related neurobiology mechanisms.
Highlights
While Internet use has made life easier, maladaptive Internet use can have unhealthy consequences, including psychological problems [1]
There is a debate regarding whether Internet gaming could produce a true clinical addiction, emerging evidence shows that Internet gaming disorder (IGD) subjects share similar neurobiological alternations with substance use and other behavioral addiction diseases such as gambling, in craving, cognitive control, and reward systems
It included the following eight questions: (1) Do you feel absorbed in the Internet? (2) Do you feel satisfied with Internet use if you increase your amount of online time? (3) Have you failed to control, reduce, or quit Internet use repeatedly? (4) Do you feel nervous, temperamental, depressed, or sensitive when trying to reduce or quit Internet use repeatedly? (5) Do you stay online longer than originally intended? (6) Have you taken the risk of losing a significant job, relationship, educational, or career opportunity because of the Internet? (7) Have you lied to your family members or others to hide the truth of your involvement with the Internet?
Summary
While Internet use has made life easier, maladaptive Internet use can have unhealthy consequences, including psychological problems [1]. There is a debate regarding whether Internet gaming could produce a true clinical addiction, emerging evidence shows that IGD subjects share similar neurobiological alternations with substance use and other behavioral addiction diseases such as gambling, in craving, cognitive control, and reward systems. The clinical diagnosis and evaluation of IGD are based on the integration of self-, parent-, and teacher-behavioral reports and the assessment of behavioral problems [3–6]. Given the subjective nature of these scales and the overlap of IGD with other psychiatric diseases, imaging-based parameters may provide a useful objective adjunct to the clinical evaluation of IGD [7,8]. In the context of the developing field of psycho-radiology, machine learning is concerned with the automated discovery of regularities in brain imaging data through the use of pattern recognition algorithms to develop classifiers that can be used to predict disorders in individuals
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
