Nonverbal Artificial Intelligence-Based Communication Robot for Staff in Disaster-Affected Care Facilities: An Exploratory ABAB Intervention Study (Preprint)
Bibliographic record
Abstract
Background: Medical and welfare facilities in the Noto region of Japan were severely affected by the 2024 Noto Peninsula earthquake and subsequent torrential rains. Staff working in these facilities were disaster survivors and frontline caregivers with limited psychological support. Nonverbal social robots may provide companionship and emotional comfort; however, their effects on the health-related quality of life (QoL) and well-being of care staff in disaster-affected settings remain unclear. Objective: This study explored whether introducing a nonverbal artificial intelligence communication robot was associated with changes in health-related QoL and well-being among care facility staff working under disaster conditions. Secondary objectives were to evaluate safety, acceptability, and intention to continue use. Methods: This pragmatic, exploratory pilot study used an ABAB design conducted between February 2025 and June 2025. After a 2-week baseline period, staff in dementia care, general care, and short-stay units underwent 2-week intervention, withdrawal, reintervention, and withdrawal phases. Questionnaires were administered at each phase end. The primary outcomes were health-related QoL (EQ-5D-5L), well-being (World Health Organization-5 Well‑Being Index), and positive mental health (Mental Health Continuum-Short Form). Friedman tests compared outcomes across the 5 phases, and effect sizes were expressed as Kendall W. Safety, acceptability, and intention to continue use were compared between the first and second intervention phases using Wilcoxon signed rank tests with Bonferroni adjustment and rank-biserial correlations as effect sizes. Results: Of the 58 staff who completed the baseline assessment, 49 (84.5%) were included in the analytic sample (25 in dementia care, 12 in general care, and 12 in short-stay units). Among these participants, 40 (81.6%) were women, and 38 (77.6%) reported disaster-related damage to their homes or families. In the pooled analysis, no phase effect was observed for the EQ-5D-5L (P=.10; Kendall W=0.032, negligible), the World Health Organization-5 Well‑Being Index (P=.70; Kendall W=0.016, negligible), or the Mental Health Continuum-Short Form (P=.44; Kendall W=0.022, negligible). No robot-related adverse events were reported. In the dementia care unit, nominal unadjusted differences were observed for "made me feel calm" (P=.045; rank-biserial correlation r=0.571, large), "like" (P=.03; r=0.559, large), and "felt at peace" (P=.02; r=0.718, large); however, none remained statistically significant after Bonferroni correction. Conclusions: The short-term use of a nonverbal artificial intelligence communication robot did not measurably improve health-related QoL or well-being among staff in disaster-affected care facilities. Deployment appeared feasible and was not associated with reported adverse events, but efficacy as a mental health support intervention remains unproven. Exploratory acceptability and interaction signals may inform future adequately powered studies.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 teacher head, 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".