Multiple-Kernel Support Vector Machine for Predicting Internet Gaming Disorder Using Multimodal Fusion of PET, EEG, and Clinical Features

Internet gaming disorder (IGD) has become an important social and psychiatric issue in recent years. To prevent IGD and provide the appropriate intervention, an accurate prediction method for identifying IGD is necessary. In this study, we investigated machine learning methods of multimodal neuroimaging data including Positron Emission Tomography (PET), Electroencephalography (EEG), and clinical features to enhance prediction accuracy. Unlike the conventional methods which usually concatenate all features into one feature vector, we adopted a multiple-kernel support vector machine (MK-SVM) to classify IGD. We compared the prediction performance of standard machine learning methods such as SVM, random forest, and boosting with the proposed method in patients with IGD (N = 28) and healthy controls (N = 24). We showed that the prediction accuracy of the optimal MK-SVM using three kinds of modalities was much higher than other conventional machine learning methods, with the highest accuracy being 86.5%, the sensitivity 89.3%, and the specificity 83.3%. Furthermore, we deduced that clinical variables had the highest contribution to the optimal IGD prediction model and that the other two modalities were also indispensable. We found that more efficient integration of multimodal data through kernel combination could contribute to better performance of the prediction model. This study is a novel attempt to integrate each method from different sources and suggests that integrating each method, such as self-administrated reports, PET, and EEG, improves the prediction of IGD.

Automated summary

This study used machine learning methods to analyze multimodal neuroimaging data and improve the prediction accuracy of Internet gaming disorder (IGD). The results showed that the multiple-kernel support vector machine method had higher accuracy in predicting IGD, and clinical variables contributed the most to the prediction model.