AI-enabled self-referral system could close access gap for ethnic and gender minorities in mental health treatment

AI-enabled self-referral system could close access gap for ethnic and gender minorities in mental health treatment

In a recent observational study published in Natural medicine, researchers evaluated the impact of an artificial intelligence (AI)-based self-referral chatbot on the diversity and volume of patient referrals by gender, ethnicity, and sexual orientation. They found that compared to control services, services using an AI chatbot had a significant increase in referrals, especially among minorities, potentially due to the human-free nature of the bot.

AI-enabled self-referral system could close access gap for ethnic and gender minorities in mental health treatment
Study: Bridging the mental health treatment accessibility gap with a personalized chatbot for self-referral. Image Credit: Chinnapong/Shutterstock.com

Background

Mental health, recognized as a global priority by the World Health Organization, faces increasing challenges among the world’s population. Limited access to mental health care persists due to structural issues such as insufficient funding and staffing. In addition, people with mental health problems often face barriers such as stigma, negative attitudes and structural barriers, especially those from minority backgrounds and disadvantaged backgrounds. The initial step in mental health care involves seeking help and referrals, which are critical for timely support and prevention of adverse outcomes. However, evidence suggests that individuals from minority groups face greater barriers and stigma in accessing care.

Digital technologies, including AI, present potential solutions to address these challenges, offering flexibility and reduced stigma. While digital technologies show promise for improving the effectiveness of mental health care, their subtle impact on various help-seeking demographics remains less studied. Digital solutions such as chatbots can help people overcome barriers and improve accessibility.

Therefore, the researchers in the present study introduced “Limbic Access,” a personalized AI-enabled chatbot designed for self-referral in mental health care, aiming to optimize the referral process by autonomously gathering patient information. The impact of the chatbot was evaluated through an observational study.

About the research

The present retrospective observational study investigated the impact of Limbic Access on treatment recommendations for anxiety and depression in the National Health Service for the treatment of anxiety and depression in the United Kingdom. The chatbot collected clinical information using standardized questionnaires such as the Patient Health Questionnaire (PHQ-9) and the Generalized Anxiety Disorder Assessment (GAD-7) and used a semi-standardized structure. AI-driven adaptability helped personalize empathic responses and further personalize data collection based on the patient’s mental health status, optimizing engagement and efficiency.

Analyzing data from ~129,400 patients across 28 services (14 with the chatbot and 14 controls), the study compared referral patterns before and after the implementation of the chatbot. Services with an online web referral form were selected as controls. While the chatbot approach offered customization, the online web form did not. Controls were matched for various variables, including demographic characteristics. The mechanisms underlying the potential difference in AI chatbot referrals were explored by analyzing the qualitative feedback provided by 42,332 individuals after completing referrals.

Statistical analysis included chi-square tests, logistic regression, one-way analysis of variance, and sensitivity analyses.

Results and discussion

Services using an AI chatbot showed a significant 15% increase in total referrals compared to a 6% increase in control services over the same period. The two approaches do not differ in their base demographic composition. Referrals from non-binary individuals showed a significant increase of 179% in services using the personalized self-referral chatbot, as opposed to a 5% decrease in control services. Furthermore, referrals were found to increase across genders in services using the chatbot – 16% for men and 18% for women compared to 5% and 6% respectively for control services. No significant variation was observed in the number of referrals based on individuals’ sexuality.

The use of an AI chatbot led to a significant 29% increase in ethnic minority referrals, surpassing the 10% increase seen in matched control services. White individuals also experienced a 15 percent increase, significantly higher than the 4 percent increase in matching services.

Detailed analysis revealed a 39% increase for Asian and Asian British groups, a 40% increase for Black and Black British and a 15% increase for mixed ethnic groups in services using the chatbot for self-referral, outperforming the respective control services. However, the difference was not significant for mixed ethnic and other ethnic groups compared to matched controls.

Qualitative data analysis using natural language processing revealed distinct patterns across demographics. Overall, 89% of feedback was positive, emphasizing convenience, hope and reduced stigma. Notably, gender minority individuals emphasized the lack of human involvement, addressing potential stigma and judgment.

Asian and black ethnic groups mentioned increased self-actualization but expressed less hope. Neutral feedback was higher for Asian and Black ethnic groups, indicating potential barriers to seeking mental health support. The human-coded analysis confirmed these findings, highlighting the relevance and robustness of the observed patterns.

The overall increase in referrals and improved diversity with the use of the chatbot did not appear to negatively impact clinical assessment wait times or the number of assessments. This shows that the quality of care is maintained. An additional study comparing an AI chatbot, a generic chatbot, and a standard web form showed that a custom AI-enabled chatbot significantly outperformed the overall user experience.

Conclusion

The current study highlights the potential role of AI-based chatbots in improving digital self-referral formats and access to mental health services. In the future, these findings could inform global health strategies and initiatives to reduce the burden of mental illness as well as inequalities in access to health care.

Leave a Comment

Your email address will not be published. Required fields are marked *