Weighing Costs and Benefits of Delay and the Acceptance of Two Decision Support Tools in Mental Health Care: Scoping Study Using Quantitative and Qualitative Data
Notice bibliographique
Résumé
Background: Mental disorders are the leading cause of disability in young people (aged 12-30 years), and their incidence constitutes a major health crisis. Primary youth mental health services are struggling to keep up due to overwhelming demand, the complexity and severity of young people presenting for care, and a shortage of qualified mental health professionals (MHPs). Artificial intelligence (AI) tools have the potential to facilitate necessary improvements to diagnosis, triage, and care planning for young people with emerging mental disorders. Objective: The objective of the present scoping research was to examine beliefs and attitudes underlying MHP acceptance of AI tools in youth mental health services. Methods: In total, 57 MHPs (mean age 35.35, SD = 9.50 years, 72% female (n = 39)) with experience working with youth populations (age 12-30) took part in study 1 that involved completing a web-based survey about the acceptability of using AI in early intervention services. During study 2, 15 MHPs also participated in 1-hour semistructured Zoom interviews. Attitudes toward the use of 2 novel AI prototypes (both of which provide recommendations for care coordination based on previously published data analyses) in youth mental health were explored. Quantitative data were interpreted using descriptive statistics, and qualitative analysis followed the thematic analysis approach. Results: MHPs were more likely to agree than disagree that AI will improve youth mental health care overall (eg, n=37, 64% participants somewhat or strongly agree that the field of mental health will improve with AI). Despite voicing concerns regarding data security and privacy, MHPs also acknowledged a need for AI to improve the "signal-to-noise ratio" in services and address delays to care for those with severe and complex problems. Such problems were seen as pervasive across the youth mental health system and emphasize the serious costs of delaying the development and implementation of novel tools. All participating MHPs discussed the potential negative impacts of not adopting novel tools. Conclusions: MHP acceptance and uptake of novel AI tools in youth mental health services will be driven by a more complex cost-benefit analysis of both adopting and not adopting, rather than solely on their design. The costs of delay are clear, and so researchers and MHPs have a shared imperative to develop useful and meaningful clinical tools and to work jointly on integrating them into practice. Limitations of our sample (including low sample size limiting generalizability) notwithstanding, these findings should inform the future design and implementation of such tools.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,116 | 0,269 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,002 | 0,003 |
| Bibliométrie | 0,012 | 0,011 |
| Études des sciences et des technologies | 0,003 | 0,004 |
| Communication savante | 0,005 | 0,006 |
| Science ouverte | 0,002 | 0,005 |
| Intégrité de la recherche | 0,002 | 0,002 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,002 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».