MétaCan
Menu
← Back to cohort
Record W4403904124 · doi:10.2196/64869

Development of a Voice-Activated Virtual Assistant to Improve Insomnia Among Young Adult Cancer Survivors: Mixed Methods Feasibility and Acceptability Study

2024· article· en· W4403904124 on OpenAlexvenueno aff
Hunter Groninger, Hannah Arem, Lylian Ayangma, Lisa Gong, Eric S. Zhou, Daniel Greenberg

Bibliographic record

VenueJMIR Formative Research · 2024
Typearticle
Languageen
FieldMedicine
TopicCancer survivorship and care
Canadian institutionsnot available
FundersNational Cancer Institute
KeywordsPreprintFocus (optics)Focus groupVirtual agentInsomniaPsychologyGerontologyMedicineComputer scienceHuman–computer interactionWorld Wide WebPsychiatrySociology

Abstract

fetched live from OpenAlex

BACKGROUND: Up to 75% of young adult cancer survivors (YACS) experience chronic insomnia, negatively affecting physical and emotional health and overall quality of life. Cognitive behavioral therapy for insomnia (CBT-I) is a gold-standard intervention to address insomnia. To improve CBT-I access and treatment adherence, screen-based digital CBT-I platforms have been developed. However, even with these digital products, widespread uptake of CBT-I remains limited, and new strategies for CBT-I delivery are warranted. OBJECTIVE: The objective of this study is to understand how YACS experience insomnia and how they might incorporate technology-delivered CBT-I into a daily routine and test the feasibility and acceptability of a novel screen-free voice-activated virtual assistant-delivered CBT-I prototype. METHODS: Eligible participants-ages 18-39, living with a history of cancer (any type, any stage), self-reporting on average less sleep than National Sleep Foundation recommendations, and English-speaking-were recruited from a major urban cancer center, 2 regional oncology clinics, and 2 cancer survivorship support groups. We conducted 4 focus groups to understand the YACS experience of insomnia, their routine use of technology at home, particularly voice-activated virtual assistants such as Amazon Alexa, and input on how CBT-I might be delivered at home through a smart speaker system. We developed a prototype device to deliver key elements of CBT-I at home along with circadian lighting and monitoring of post-bedtime device use, collected YACS user perspectives on this prototype, and then conducted a single-arm feasibility and acceptability study. RESULTS: In total, 26 YACS (6-7 participants per group) experiencing insomnia participated in focus groups to share experiences of insomnia during cancer survivorship and to provide input regarding a CBT-I prototype. Common triggers of insomnia included worry about disease management and progression, disease-related pain and other symptoms, choices regarding personal device use, and worry about the impact of poor sleep on daily functioning. In total, 12 participants completed device prototype testing, engaging with the prototype 94% of the assigned times (twice daily for 14 days; meeting predetermined feasibility cutoff of engagement ≥70% of assigned times) and rating the prototype with an overall mean score of 5.43 on the Satisfaction subscale of the Usability, Satisfaction, and Ease of Use scale (range 4.42-7; exceeding the predetermined cutoff score for acceptability of 5.0). All participants completing the study reported they would be interested in using the prototype again and would recommend it to someone else with insomnia. CONCLUSIONS: YACS were highly engaged with our voice-activated virtual assistant-delivered CBT-I prototype and found it acceptable to use. Following final device development, future studies should evaluate the efficacy of this intervention among YACS. TRIAL REGISTRATION: ClinicalTrials.gov NCT05875129; https://clinicaltrials.gov/study/NCT05875129.

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 imitation

Not 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.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.009
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.051

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.009
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.000

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 head0.072
GPT teacher head0.467
Teacher spread0.395 · 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 source (direct Gemma or distilled Codex), 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

Citations5
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative Research→Same topicCancer survivorship and care→French-language works237,207→