An Empathy-Driven, Conversational Artificial Intelligence Agent (Wysa) for Digital Mental Well-Being: Real-World Data...

Area of Science:

• Digital mental health
• Artificial intelligence in healthcare
• Psychiatry and psychology

Background:

• Major depression impacts nearly 5% of the global population, causing significant psychosocial impairment.
• Barriers to mental healthcare include personnel shortages, long wait times, stigma, and underfunding.
• AI-enabled mobile apps offer scalable, supplementary support for mental well-being, complementing traditional therapy.

Purpose of the Study:

• To evaluate the real-world effectiveness and engagement of Wysa, an AI-driven, text-based conversational mobile app.
• To assess the app's impact on users self-reporting symptoms of depression.

Main Methods:

• A mixed-methods approach analyzed data from anonymous global users of the Wysa app.
• Users self-reported depression symptoms via the Patient Health Questionnaire-9.
• Quantitative analysis compared depression score improvements between high and low app usage groups; qualitative analysis reviewed user feedback.

Main Results:

• High Wysa users showed significantly greater average improvement in depression scores (mean 5.84) compared to low users (mean 3.52) (P=.03).
• The study observed a moderate effect size (0.63) for the app's impact.
• 67.7% of user feedback indicated the app experience was helpful and encouraging.

Conclusions:

• Real-world data suggests the Wysa app is a promising tool for improving depression symptoms and user engagement.
• Further validation with larger sample sizes and longer study durations is warranted.
• AI-based mobile applications can serve as accessible, supplementary mental health support.