Loading...
Loading...
Contributors:
Dataset URI:
10.6084/m9.figshare.34052991.v4Background: The prevalence of common mental health problems, such as depression and anxiety, represents one of the leading causes of years lived with disability. However, a substantial gap remains in access to traditional treatment. Artificial intelligence–based conversational systems represent an alternative to provide emotional support and psychoeducation. Nevertheless, their design raises relevant ethical, clinical, and technological challenges, which require rigorous user-centered software engineering approaches.Objective: To explore patients’ and therapists’ views on functional and non-functional requirements for a conversational agent that supports mental health care.Methods: We used a qualitative descriptive exploratory design. We held semi-structured interviews with 12 participants (8 patients and 4 psychologists) from a private mental health clinic in Peru. We used descriptive thematic analysis to identify needs and concerns and organized them as patient and therapist functional and non-functional requirements and use cases.Results: We identified six descriptive themes from the interviews: access and communication, structured self-help, monitoring and follow-up, privacy and trust, crisis safety, and governance and safe use. We linked 246 unique qualitative quotes to proposed requirements. Based on these findings, we developed 55 requirements (39 functional and 16 non-functional) for patients and therapists. Patient-related requirements focused on empathetic communication, practical exercises, privacy, and crisis support. Therapist-related requirements focused on patient monitoring, clinical summaries, risk alerts, and professional oversight. We also developed 15 proposed use cases, organized into five groups, to show how the requirements could work together.Conclusion: Interviews with patients and therapists helped identify requirements for a conversational agent used alongside mental health care. These findings can guide future system development but do not show whether the proposed functions are usable, safe, or effective in clinical practice.
Keyword(s):
Conversational agents; Digital health; Mental health; Mental health services; Qualitative research.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)