A Personalized, Texting-Based Conversational Agent to Address Sleep Disturbance in Individuals Who Have Survived Breast Cancer: Protocol for a Pilot Waitlist Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Sleep disturbance is one of the most common health concerns reported by individuals who have survived breast cancer (BC) and is associated with poor quality of life (QoL) and greater mortality after treatment. Cognitive behavioral therapy for insomnia (CBTi) has shown efficacy for improving sleep and QoL for this population. Considered the gold standard for insomnia treatment, CBTi can be delivered remotely, including via digital intervention. Despite the potential for wider dissemination of CBTi via digital means, these modalities have unique challenges, including technology barriers and poor adherence. We developed a conversational agent (CA) to deliver CBTi via a SMS text messaging intervention, supported by mobile-ready web content. Named "Cecebot," this CA delivers sleep education, implements sleep compression, provides just-in-time interventions for sleep-disrupting behaviors, and includes enhanced support for physical activity (PA) beyond what is typically included in CBTi. This represents a novel modality for a CBTi and PA intervention among individuals who have survived BC. OBJECTIVE: We aim to examine the safety and acceptability of the Cecebot intervention, developed by an academic partnership between Dr Reding's research team and Moby Inc, for individuals who have survived BC and experience symptoms of insomnia, and to explore its efficacy. METHODS: This trial will recruit 60 individuals who have survived BC and are experiencing moderate to severe sleep disturbance. Participants will be assigned to the Cecebot intervention or waitlist control group at a 1:1 ratio. The treatment group will receive the Cecebot intervention during weeks 1-6 of the study, while the waitlist control condition will receive the Cecebot intervention during weeks 6-12. The Cecebot intervention uses SMS text messaging technology paired with a Fitbit. Participants will be assessed at baseline, week 6, and week 12. Measurements will include feasibility and acceptability and will explore the effect of the Cecebot intervention. Feasibility will be assessed through recruitment, enrollment, and retention rates. Acceptability will be evaluated using a satisfaction survey and open-ended responses. Quantitative analysis, such as t test, Fisher exact tests, and generalized linear models, will be used to assess feasibility, baseline group differences, and the outcomes of the intervention. RESULTS: Recruitment of participants began in Fall 2024. The completion of data collection is anticipated to be by Fall 2025. CONCLUSIONS: The study results will give insight into the potential for an SMS text messaging-based CA to improve sleep in individuals who have survived BC and experience sleep disturbances. TRIAL REGISTRATION: ClinicalTrials.gov NCT06392789; https://clinicaltrials.gov/study/NCT06392789. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/62712.
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 | 0.017 | 0.018 |
| Meta-epidemiology (narrow) | 0.005 | 0.003 |
| Meta-epidemiology (broad) | 0.009 | 0.004 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.005 | 0.008 |
| Insufficient payload (model declined to judge) | 0.065 | 0.009 |
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".