MétaCan
Menu
Back to cohort
Record W4405799474 · doi:10.2196/63515

Evaluation of a Guided Chatbot Intervention for Young People in Jordan: Feasibility Randomized Controlled Trial

2024· article· en· W4405799474 on OpenAlexvenueno aff
Anne M. de Graaff, Rand Habashneh, Sarah Fanatseh, Dharani Keyan, Aemal Akhtar, Adnan Abualhaija, Muhannad Faroun, Ibrahim Said Aqel, Latefa Ali Dardas, Chiara Servili, Mark van Ommeren, Richard A. Bryant, Kenneth Carswell

Bibliographic record

VenueJMIR Mental Health · 2024
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsnot available
FundersWorld Health Organization
KeywordsPreprintRandomized controlled trialIntervention (counseling)MedicinePsychologyWorld Wide WebComputer scienceNursingSurgery

Abstract

fetched live from OpenAlex

BACKGROUND: Depression and anxiety are a leading cause of disability worldwide and often start during adolescence and young adulthood. The majority of young people live in low- and middle-income countries where there is a lack of mental health services. The World Health Organization (WHO) developed a guided, nonartificial intelligence chatbot intervention called Scalable Technology for Adolescents and youth to Reduce Stress (STARS) to reduce symptoms of depression and anxiety among young people affected by adversity. OBJECTIVE: The objective of this study was to evaluate the feasibility of the STARS intervention and study procedures among young people in Jordan. METHODS: A 2-arm, single-blind, feasibility randomized controlled trial was conducted among 60 young people aged 18 years to 21 years living in Jordan with self-reported elevated levels of psychological distress. Immediately after baseline, participants were randomized 1:1 into the STARS intervention or enhanced care as usual (ECAU). STARS consisted of 10 lessons in which participants interacted with a chatbot and learned several cognitive behavioral therapy strategies, with optional guidance by a trained e-helper through 5 weekly phone calls. ECAU consisted of a static web page providing basic psychoeducation. Online questionnaires were administered at baseline (week 0) and postassessment (week 8) to assess depression (Hopkins Symptom Checklist-25 [HSCL-25]), anxiety (HSCL-25), functional impairment (WHO Disability Assessment Schedule [WHODAS] 2.0), psychological well-being (WHO-Five Well-Being Index [WHO-5]), and agency (State Hope Scale). Process evaluation interviews with stakeholders were conducted after the postassessment. RESULTS: Participants were recruited in December 2022 and January 2023. Of 700 screening website visits, 160 participants were eligible, and 60 participants (mean age 19.7, SD 1.16 years; 49/60, 82% female) continued to baseline and were randomized into STARS (n=30) or ECAU (n=30). Of those who received STARS, 37% (11/30) completed at least 8 chatbot lessons, and 13% (4/30) completed all 5 support calls. The research protocol functioned well in terms of balanced randomization, high retention at postassessment (48/60, 80%), and good psychometric properties of the online questionnaires. Process evaluation interviews with STARS participants, ECAU participants, e-helpers, and the clinical supervisor indicated the acceptability of the study procedures and the STARS and ECAU conditions and highlighted several aspects that could be improved, including the e-helper support and features of the STARS chatbot. CONCLUSIONS: This study demonstrated the feasibility and acceptability of the STARS intervention and research procedures. A fully powered, definitive randomized controlled trial will be conducted to evaluate the effectiveness of STARS. TRIAL REGISTRATION: ISRCTN ISRCTN19217696; https://doi.org/10.1186/ISRCTN19217696.

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)0.004
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: Randomized trial
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.009
Threshold uncertainty score0.030

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.004
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0090.001

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 head0.090
GPT teacher head0.501
Teacher spread0.411 · 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 designRandomized trial
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

Citations9
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Mental HealthSame topicDigital Mental Health InterventionsFrench-language works237,207