Depression is a common reason for an increase in suicide cases worldwide. Thus, to mitigate the effects of depression, accurate diagnosis and treatment are needed. An electroencephalogram (EEG) is an instrument used to measure and record the brain's electrical activities. It can be utilized to produce the exact report on the level of depression. Previous studies proved the feasibility of the usage of EEG data and deep learning (DL) models for diagnosing mental illness. Therefore, this study proposes a DL-based convolutional neural network (CNN) called DeprNet for classifying the EEG data of depressed and normal subjects. Here, the Patient Health Questionnaire 9 score is used for quantifying the level of depression. The performance of DeprNet in two experiments, namely, the recordwise split and the subjectwise split, is presented in this study. The results attained by DeprNet have an accuracy of 0.9937, and the area under the receiver operating characteristic curve (AUC) of 0.999 is achieved when recordwise split data are considered. On the other hand, an accuracy of 0.914 and the AUC of 0.956 are obtained, while subjectwise split data are employed. These results suggest that CNN trained on recordwise split data gets overtrained on EEG data with a small number of subjects. The performance of DeprNet is remarkable compared with the other eight baseline models. Furthermore, on visualizing the last CNN layer, it is found that the values of right electrodes are prominent for depressed subjects, whereas, for normal subjects, the values of left electrodes are prominent.

Background: Depression is a debilitating mental health disorder, with a large treatment gap. Recent years have seen a surge in digital interventions to bridge this treatment gap. Most of these interventions are based on computerized cognitive behavioral therapy. Despite the efficacy of computerized cognitive behavioral therapy–based interventions, their uptake is low and dropout rates are high. Cognitive bias modification (CBM) paradigms provide a complementary approach to digital interventions for depression. However, interventions based on CBM paradigms have been reported to be repetitive and boring. Objective: In this paper, we described the conceptualization, design, and acceptability of serious games based on CBM paradigms and the learned helplessness paradigm. Methods: We searched the literature for CBM paradigms that were shown to be effective in reducing depressive symptoms. For each of the CBM paradigms, we ideated how to create a game so that the gameplay was engaging while the active therapeutic component remained unchanged. Results: We developed 5 serious games based on the CBM paradigms and the learned helplessness paradigm. The games include various core elements of gamification, such as goals, challenges, feedback, rewards, progress, and fun. Overall, the games received positive acceptability ratings from 15 users. Conclusions: These games may help improve the effectiveness and engagement levels of computerized interventions for depression.

BACKGROUND Depression is a debilitating mental health disorder, with a large treatment gap. Recent years have seen a surge in digital interventions to bridge this treatment gap. Most of these interventions are based on computerized cognitive behavioral therapy. Despite the efficacy of computerized cognitive behavioral therapy–based interventions, their uptake is low and dropout rates are high. Cognitive bias modification (CBM) paradigms provide a complementary approach to digital interventions for depression. However, interventions based on CBM paradigms have been reported to be repetitive and boring. OBJECTIVE In this paper, we described the conceptualization, design, and acceptability of serious games based on CBM paradigms and the learned helplessness paradigm. METHODS We searched the literature for CBM paradigms that were shown to be effective in reducing depressive symptoms. For each of the CBM paradigms, we ideated how to create a game so that the gameplay was engaging while the active therapeutic component remained unchanged. RESULTS We developed 5 serious games based on the CBM paradigms and the learned helplessness paradigm. The games include various core elements of gamification, such as goals, challenges, feedback, rewards, progress, and fun. Overall, the games received positive acceptability ratings from 15 users. CONCLUSIONS These games may help improve the effectiveness and engagement levels of computerized interventions for depression.