5/14/25
Combining AI and Human Support in Mental Health: A Digital Intervention with Comparable Effectiveness to Human-Delivered Care
AI can deliver mental health support as well as humans can.
Back to Resources
Summary
ieso's peer-reviewed study found that a digital intervention combining an AI-driven conversational agent with human clinical support produced clinically meaningful reductions in generalized anxiety comparable to human-delivered care. Across 299 participants, per-protocol GAD-7 scores dropped 7.4 points (d=1.6) over a median of six hours of use, with improvements sustained at one-month follow-up. The intervention was statistically superior to a waiting control group and non-inferior to both face-to-face and remote typed CBT, while requiring significantly less clinician time. The findings support scaling AI-plus-human support to expand access to evidence-based mental healthcare.
Mental health issues are on the rise globally. Cognitive Behavioral Therapies (CBT) can improve the lives of people with anxiety and depression. However, because there aren’t enough therapists available, many people struggle to get the high-quality care they need. The escalating global demand for mental health services exceeds existing clinical capacity. Scalable digital solutions will be essential to expand access to high-quality mental healthcare.
Our peer-reviewed study evaluated the effectiveness of a digital intervention to alleviate mild, moderate, and severe symptoms of generalized anxiety. This structured, evidence-based program was designed to maximize engagement and effectiveness by combining an Artificial Intelligence (AI) driven conversational agent to deliver content with human clinical oversight and user support.
The digital intervention was compared to three propensity-matched real-world patient comparator groups:
- waiting control
- face-to-face cognitive behavioral therapy (CBT)
- remote typed-CBT
Endpoints for effectiveness, engagement, acceptability, and safety were collected before, during, and after the intervention, and at one-month follow-up.
Participants (n=299) used the program for a median of 6 hours over 53 days. There was a large clinically meaningful reduction in anxiety symptoms for the intervention group (per-protocol (n=169): change on GAD-7 = -7.4, d = 1.6; intention-to-treat (n=299): change GAD-7 = -5.4, d = 1.1) that was statistically superior to the waiting control group, non-inferior to human-delivered care, and was sustained at one-month follow-up.
By combining AI and human support, the digital intervention achieved clinical outcomes comparable to human-delivered care while significantly reducing the required clinician time.
These findings highlight the immense potential of technology to scale effective evidence-based mental healthcare, address unmet need, and ultimately impact quality of life and economic burden globally.
Read the full peer-reviewed paper here.
ABOUT THE AUTHOR
Clare Palmer, PhD
Director of Evidence Generation
Latest Articles
6/4/26
ieso Welcomes James Dold as Head of Sales
A healthcare leader with clinical roots, James Dold brings over 20 years of experience across behavioral health, value-based care, strategic partnerships, and care delivery to ieso as Head of Sales.
6/1/26
Mental Health Isn’t Separate From Women’s Health - So Why Is It Still Treated That Way?
As women’s health companies expand care services, mental health can't sit on the sidelines. Embedded support reflects the reality of how women experience their health in an interconnected and overlapping way.
5/20/26
Digital GI Care Has an ROI Ceiling. Mental Health Is How You Break Through It.
Digital GI platforms have closed major access gaps and proven real ROI. The unaddressed mental health burden in IBS and IBD populations is capping how much further those outcomes can go.
5/7/26
The Mental Health AI Market is Crowded. Evidence is Still Rare.
A new Hemingway Report market map shows conversational AI in mental health is moving fast, but clinical evidence remains the clearest differentiator.