Digital talking therapy: does it work?

There has been an explosion of digital mental health interventions in recent years driven, in part, by the Covid pandemic alongside greater pressures on the health system which has made it harder to access traditional routes to support. However, finding information on their effectiveness isn’t easy.

When we started developing Rowan, we knew it had to be based on science and it had to be designed in such a way that meant it actually helps people. So we spent a lot of time researching the ingredients for effective digital talking therapy.

In this blog, we summarise what we found. This is not an exhaustive list but it does give a flavour of what we discovered.

Systematic review papers

We analysed well over 100 systematic review papers. These are authoritative accounts of existing evidence that make sense of large bodies of information to help answer questions about what works and what doesn’t.

1. Digital talking therapy, delivered by a conversational agent using AI technology, has positive effects on lifestyle and mental health. This was the conclusion of a review of high quality randomised control trials. (Li et al., 2023) 

2. In another review, all 13 studies reported a positive impact of an AI-based approach in treating mental health issues. (Sandhya Bhatt, 2024)

3. Another study highlights the promising role of digital talking therapy in alleviating depressive and anxiety symptoms among adults. It can deliver substantial improvements over a relatively brief treatment period. (Zhong et al., 2024) 

4. It is most effective when used alongside human face-to-face therapy. (Jabir et al., 2024)

5. To be successful, it’s important to build rapport. Digital talking therapy should create an inviting, empathetic environment and cultivate trust and connection. (Sandhya Bhatt, 2024). This is a crucial innovation which the team at Spicy Minds has prioritised in the development of Rowan.

6. With AI, the fear of being judged or labelled is minimised and people may feel more comfortable revealing their thoughts to a virtual human. (Sandhya Bhatt, 2024)

7. 86% of the studies carried out as part of one review indicated that this type of intervention is an effective tool for depression or anxiety. (Ahmed et al., 2023)

8. AI based conversational agents can effectively alleviate psychological distress. The most pronounced effects were seen in studies employing generative AI, using multimodal or voice-based conversational agents or delivering interventions via mobile applications and instant messaging platforms. (Li et al., 2023)

9. AI has great potential to offer social and psychological support in situations where real-world human interaction, such as connecting to friends or family members or seeking professional support, is not preferred or possible to achieve. (Haque M, Rubya S, 2023)

10. In the same review review, AI-delivered psychotherapy significantly improved depressive symptoms. (Haque M, Rubya S, 2023)

11. In one review, the majority of studies showed the potential of using AI alongside another psychological intervention, especially by providing patients with rapid and personalised automated feedback and guidance. (Gual-Montolio P., 2022)

To sum up

AI has been used for many years across many different industries but its use in the mental health sector is relatively new and has complex implications. We have put a lot of work into understanding all the latest research on this topic and it is evident that AI solutions show huge promise when they are done well. Nevertheless, further clinical and medical research is needed and we welcome this as we continue our quest to deliver an outstanding  and beneficial experience.

Bibliography

1. Yan Li, Surui Liang, Bingqian Zhu, Xu Liu, Jing Li, Dapeng Chen, Jing Qin, Dan Bressington (2023). Feasibility and effectiveness of artificial intelligence-driven conversational agents in healthcare interventions: A systematic review of randomized controlled trials. International Journal of Nursing Studies. https://doi.org/10.1016/j.ijnurstu.2023.104494

2. Sandhya Bhatt (2024). Digital Mental Health: Role of Artificial Intelligence in Psychotherapy. Annals of Neuroscience. doi: 10.1177/09727531231221612

3. Wenjun Zhong, Jianghua Luo, Hong Zhang (2024). The therapeutic effectiveness of artificial intelligence-based chatbots in alleviation of depressive and anxiety symptoms in short-course treatments: A systematic review and meta-analysis. Journal of Affective Disorders. https://doi.org/10.1016/j.jad.2024.04.057

4. Ahmad Ishqi Jabir, Xiaowen Lin, Laura Martinengo, Gemma Sharp, Yin-Leng Theng, Lorainne Tudor Car (2024). Attrition in Conversational Agent–Delivered Mental Health Interventions: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. doi: 10.2196/48168

5. Sandhya Bhatt (2024). Digital Mental Health: Role of Artificial Intelligence in Psychotherapy. Annals of Neuroscience. https://doi.org/10.1177/09727531231221612

6. Sandhya Bhatt (2024). Digital Mental Health: Role of Artificial Intelligence in Psychotherapy. Annals of Neuroscience. https://doi.org/10.1177/09727531231221612

7. Arfan Ahmed, Asmaa Hassan, Sarah Aziz, Alaa A Abd-alrazaq, Nashva Ali, Mahmood Alzubaidi, Dena Al-Thani, Bushra Elhusein, Mohamed Ali Siddig, Maram Ahmed, Mowafa Househ (2023). Chatbot features for anxiety and depression: A scoping review. Health Informatics Journal. doi: 10.1177/14604582221146719

8. Han Li, Renwen Zhang, Yi-Chieh Lee, Robert E. Kraut, David C. Mohr (2023). Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being. Npj Digital Medicine. https://doi.org/10.1038/s41746-023-00979-5

9. Haque M., Rubya S. (2023). An Overview of Chatbot-Based Mobile Mental Health Apps: Insights From App Description and User Reviews. JMIR mHealth and uHealth. doi: 10.2196/44838

10. Haque M., Rubya S. (2023). An Overview of Chatbot-Based Mobile Mental Health Apps: Insights From App Description and User Reviews. JMIR mHealth and uHealth. doi: 10.2196/44838

11. Gual-Montolio P, Jaén I, Martínez-Borba V, Castilla D, Suso-Ribera C. (2022). Using Artificial Intelligence to Enhance Ongoing Psychological Interventions for Emotional Problems in Real- or Close to Real-Time: A Systematic Review. International Journal of Environmental Research and Public Health. https://doi.org/10.3390/ijerph19137737