Collecting Real-Life Psychophysiological Data via Wearables to Better Understand Child Behavior in a Children’s Psychiatric Center: Mixed Methods Study on Feasibility and Implementation
Bibliographic record
Abstract
Background: In the field of mental health care, the incorporation of wearable devices into routine clinical practice continues to face significant challenges, despite the presence of supporting scientific evidence. Crossing the wasteland between the trial world and the real world is full of obstacles that often only become apparent during the implementation process. Objective: The objective of this paper was to evaluate the feasibility of using wearables in real-world clinical settings for children with severe developmental problems to help understand and manage disruptive behavior and to gain insights for the development of forthcoming implementation strategies. Methods: A mixed methods design was used to examine two different aspects of the use of wearables in a clinical setting. The first quantitative part of this study focuses on the feasibility of using wearables to collect reliable data on psychophysiological measures during daily activities in children at a children's psychiatric center. The second qualitative part focuses on the evaluation of the implementation process using the Consolidated Framework for Implementation Research (CFIR) to identify essential steps to successfully incorporate wearable technology in clinical care for children with severe behavioral problems. Empatica E4 wristbands collected data on children's psychophysiological arousal (eg, heart rate [HR] and skin conductance level [SCL]). Staff reported aggressive behavior and daily activities. Data were processed and visualized in a dashboard. User experiences were assessed through interviews with clinical staff. The implementation process was evaluated using the CFIR. Results: A total of 30 children (27 boys and 3 girls, aged 6 to 14 y; mean age 9.3 y, SD 1.95) wore the wearable for 5 consecutive days. As expected, the children found it easy to wear the device and the clinical staff predominantly expressed positive attitudes toward its use. The data collection proceeded relatively smoothly, and the collected data were of sufficient quality. In total, 315 observations of aggressive behavior were reported, including 54 red incidents (from 18 unique participants) and 261 orange incidents (from 26 unique participants). An exploratory analysis on the association between psychophysiological measures and aggressive behavior revealed that children's HR was significantly higher during aggressive incidents compared to nonaggressive incidents (P=.007). Although not statistically significant, there was a trend suggesting higher peaks per minute during aggressive incidents (P=.07). No significant differences between aggressive and nonaggressive incidents were found for SCL and movement (P=.33 and P=.60). The most challenging CFIR domains in our study were the "characteristics of the intervention" and "the inner setting," reflected in the fact that that the majority of implementation activities were focused on these two domains. Conclusions: The use of wearables in a real-world study setting is considered feasible and valuable. However, for broader scaling in daily clinical practice, coherent actions on different domains of implementation are required.
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 | 0.078 | 0.062 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| 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".