Patients’ and Health Care Professionals’ Expectations of Virtual Therapeutic Agents in Outpatient Aftercare: Qualitative Survey Study
Bibliographic record
Abstract
BACKGROUND: Depression is a serious mental health condition that can have a profound impact on the individual experiencing the disorder and those providing care. While psychotherapy and medication can be effective, there are gaps in current approaches, particularly in outpatient care. This phase is often associated with a high risk of relapse and readmission, and patients often report a lack of support. Socially interactive agents represent an innovative approach to the provision of assistance. Often powered by artificial intelligence, these virtual agents can interact socially and elicit humanlike emotions. In health care, they are used as virtual therapeutic assistants to fill gaps in outpatient aftercare. OBJECTIVE: We aimed to explore the expectations of patients with depression and health care professionals by conducting a qualitative survey. Our analysis focused on research questions related to the appearance and role of the assistant, the assistant-patient interaction (time of interaction, skills and abilities of the assistant, and modes of interaction) and the therapist-assistant interaction. METHODS: A 2-part qualitative study was conducted to explore the perspectives of the 2 groups (patients and care providers). In the first step, care providers (n=30) were recruited during a regional offline meeting. After a short presentation, they were given a link and were asked to complete a semistructured web-based questionnaire. Next, patients (n=20) were recruited from a clinic and were interviewed in a semistructured face-to-face interview. RESULTS: The survey findings suggested that the assistant should be a multimodal communicator (voice, facial expressions, and gestures) and counteract negative self-evaluation. Most participants preferred a female assistant or wanted the option to choose the gender. In total, 24 (80%) health care professionals wanted a selectable option, while patients exhibited a marked preference for a female or diverse assistant. Regrading patient-assistant interaction, the assistant was seen as a proactive recipient of information, and the patient as a passive one. Gaps in aftercare could be filled by the unlimited availability of the assistant. However, patients should retain their autonomy to avoid dependency. The monitoring of health status was viewed positively by both groups. A biofeedback function was desired to detect early warning signs of disease. When appropriate to the situation, a sense of humor in the assistant was desirable. The desired skills of the assistant can be summarized as providing structure and emotional support, especially warmth and competence to build trust. Consistency was important for the caregiver to appear authentic. Regarding the assistant-care provider interaction, 3 key areas were identified: objective patient status measurement, emergency suicide prevention, and an information tool and decision support system for health care professionals. CONCLUSIONS: Overall, the survey conducted provides innovative guidelines for the development of virtual therapeutic assistants to fill the gaps in patient aftercare.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".