Artificial Intelligence-Based Mobile Phone Apps for Child Mental Health: Comprehensive Review and Content Analysis.

Background: Mobile phone apps powered by artificial intelligence (AI) have emerged as powerful tools to address mental health challenges faced by children.

Objective: This study aimed to comprehensively review AI-driven apps for child mental health, focusing on their availability, quality, readability, characteristics, and functions.

Methods: This study systematically analyzed AI-based mobile apps for child mental health. Quality was evaluated using the Mobile Application Rating Scale, which assessed various dimensions of app quality, including subjective quality, engagement, functionality, aesthetics, and information. An automatic readability index calculator was implemented to assess readability by using the count of words, syllables, and sentences to generate a score indicative of the reading difficulty level. Content analysis was conducted to examine the apps' availability, characteristics, and functionality.

Results: Out of 369 apps initially identified, 27 met the eligibility criteria for inclusion. The quality of the apps was assessed using Mobile Application Rating Scale, with an average score of 3.45 out of 5 (SD 0.5), indicating a need for quality improvement. The readability analysis revealed suboptimal scores, with an average grade level of 6.62 (SD 2.2) for in-app content and 9.93 (SD 2.6) for app store descriptions. These results, combined with a monotonous user interface, suggest that many apps lack a child-friendly design, potentially hindering their usability and engagement for young users. Content analysis categorized the apps into 3 functional groups-chatbot-based apps (15 apps), journal logging apps (9 apps), and psychotherapeutic treatment apps (3 apps). While 20 out of 27 apps (74%) used clinically validated technologies, rigorous clinical tests of the apps were often missing, with only 2 apps undergoing clinical trials. Of the 27 apps analyzed, only 7 (26%) were free to use, while the majority, 20 apps, required a subscription or one-time payment. Among the paid apps, the average cost was US $20.16 per month, which may pose a financial barrier and limit accessibility for some users, particularly those from lower-income households.

Conclusions: AI-based mental health apps hold significant potential to address the unique challenges of child mental health but face critical limitations in design, accessibility, and validation. To fully realize their benefits, future research and development should focus on integrating child-centric design principles, ensuring affordability, and prioritizing rigorous clinical testing. These efforts are essential to harness the power of AI technologies in creating equitable, effective, and engaging solutions for improving child mental health outcomes.