MétaCan
Menu
Back to cohort
Record W7162951678 · doi:10.2196/89166

Nonverbal Artificial Intelligence-Based Communication Robot for Staff in Disaster-Affected Care Facilities: An Exploratory ABAB Intervention Study (Preprint)

2025· article· en· W7162951678 on OpenAlexvenueno aff
Daijiro Haba, Riko Miyashita, Takao Kondo, Keita TATSUKAWA, Fumiya Oohashi, Aya Kitamura, Chizuko Konya, Hiromi Sanada, Masaru Matsumoto

Bibliographic record

VenueJMIR Formative Research · 2025
Typearticle
Languageen
FieldPsychology
TopicSocial Robot Interaction and HRI
Canadian institutionsnot available
Fundersnot available
KeywordsNonverbal communicationIntervention (counseling)Exploratory researchRobotHuman–robot interactionEye contact

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: Qualitative
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.171
Threshold uncertainty score0.899

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.167
GPT teacher head0.517
Teacher spread0.351 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractno

Explore more

Same venueJMIR Formative ResearchSame topicSocial Robot Interaction and HRIFrench-language works237,207