Development of a generative AI agent for family support in implementing family-based treatment for children and adolescents with anorexia nervosa
Entwicklung eines generativen KI-Agents zur Familienunterstützung bei der Umsetzung der familienbasierten Behandlung für Kinder und Jugendliche mit Anorexia nervosa
Frontiers in Digital Health · 09.03.2026 · 8
DOI: 10.3389/fdgth.2026.1759690 ↗Auf einen Blick
Ein domänenspezifischer generativer KI-Agent lieferte in einer Expertenprüfung überwiegend FBT-konforme Antworten für Familien von Kindern und Jugendlichen mit Anorexia nervosa. 91,6 % der 477 Antworten waren klinisch angemessen.
Fragestellung
Kann ein generativer KI-Agent Familien bei der Umsetzung der familienbasierten Behandlung (FBT) für Kinder und Jugendliche mit Anorexia nervosa situationsspezifisch unterstützen?
Methode
Expertenprüfung eines RAG-Systems mit FBT-Wissensbasis, NLP-Pipeline und Sicherheitsregeln; 6 Kliniker:innen bewerteten 477 simulierte FBT-Anfragen.
Ergebnisse
Von 477 Anfragen waren 57,0 % FBT-bezogen, 24,5 % allgemeines AN-Wissen, 16,5 % elterliche psychische Belastung und 1,8 % andere Themen. Klinisch angemessen: 91,6 % (437/477).
Einschränkungen
Expertenprüfung; im Abstract werden keine Studien zu Usability, Versorgungseffekten oder klinischen Outcomes berichtet.
Schlussfolgerung der Autor:innen
Das Sicherheits-gesteuerte RAG-System erzeugte überwiegend FBT-konforme Antworten mit essensbezogener Anleitung und empathischer Unterstützung. Weitere Studien sind nötig, um Auswirkungen zu prüfen.
Kernaussagen
- 91,6 % der 477 Antworten waren klinisch angemessen
- Sicherheitsprobleme traten selten auf
- Weitere Studien zu Nutzen und Auswirkungen sind erforderlich
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Digital Health, online erschienen am 09.03.2026. Verfasst von Mana Hanzawa und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Okayama University Hospital Medical Center for Children, Okayama, Japan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Foundation Mishima Haeundae Memorial Foundation.
Themen: Kinderkrankenpflege
Abstract (Originalsprache)
Introduction
Family-based treatment (FBT) is a first-line psychotherapy for children and adolescents with anorexia nervosa (AN). However, families must understand the principles of FBT, provide meal support, and manage their children's pathological behaviors. Difficulties occur outside clinic hours when it is impossible to consult professionals. This “support gap” increases caregivers’ psychological distress and threatens their treatment continuity. To the best of our knowledge, this is the first domain-specific generative artificial intelligence (AI) agent designed to provide situation-specific, FBT-concordant advice and psychological support.
Methods
The system integrates three components: (1) an FBT-specific knowledge base constructed from treatment manuals, family guides, guideline-compliant resources, and a clinical Q&A corpus; (2) a multistage natural language processing pipeline using Retrieval-Augmented Generation (RAG), with intent and sentiment analyses; and (3) safety guardrails that prohibit unsolicited numerical goals or direct hospitalization recommendations and standardized escalation to clinicians. When strong negative emotions are detected, empowerment messages are dynamically incorporated to maintain caregivers’ confidence. Six clinicians with expertise with pediatric mental health authored queries that simulated common FBT-related concerns and evaluated each response for clinical appropriateness and safety, and classified problems as information insufficiency, not FBT concordant, or escalation insufficiency.
Results
Of the 477 queries, 57.0% were FBT-related, 24.5% were general AN, 16.5% were parental psychological distress, and 1.8% were related to other topics. The clinically appropriate response rate was 91.6% (437/477), including 92.3% for FBT-related questions, 88.0% for general knowledge, 93.7% for psychological distress, and 100.0% for other questions. Clinically inappropriate responses (8.4%) were mainly attributable to information insufficiency; not FBT concordant (1.8% of FBT-related responses) and escalation insufficiency (0.6% of all dialogs) rarely occurred.
Discussion
In this expert review, the safety-gated RAG system predominantly generated FBT-concordant responses that provided meal-level guidance and empathic empowerment-oriented support to families. By proceduralizing complex FBT concepts and presenting multiple response options for pathological behaviors, the system translates FBT principles into practical guidance supporting refeeding adherence, preserving family self-efficacy, and suggesting that domain-specific AI may help bridge structural limitations in FBT. Usability studies and randomized controlled trials are warranted to determine their impact on caregiver burden, self-efficacy, treatment adherence, and clinical outcomes.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pediatrics, Okayama University Hospital Medical Center for Children, Okayama, Japan.
- Department of Medical Informatics and Clinical Support Technology Development, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan.
- Department of Pediatrics, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan.
- Clinical Psychology Section, Department of Medical Support, Okayama University Hospital, Okayama, Japan.
- Department of Child Welfare, Notre Dame Seishin University, Okayama, Japan.
- Life Natural Science and Technology, Graduate School of Environmental, Okayama University, Okayama, Japan.
Förderung
- Foundation Mishima Haeundae Memorial Foundation
Zitieren
APA
Hanzawa, M., Hasei, J., Okada, A., Tanaka, C., Shigeyasu, Y., Fujii, C., Horiuchi, M., Sugihara, A., Takeuchi, K., Nakahara, R., Katayama, H., Takahashi, Y., Ozaki, T., & Tsukahara, H. (2026). Development of a generative AI agent for family support in implementing family-based treatment for children and adolescents with anorexia nervosa. Frontiers in Digital Health, 8. https://doi.org/10.3389/fdgth.2026.1759690
Vancouver
Hanzawa M, Hasei J, Okada A, Tanaka C, Shigeyasu Y, Fujii C, et al. Development of a generative AI agent for family support in implementing family-based treatment for children and adolescents with anorexia nervosa. Frontiers in Digital Health. 2026;8. doi:10.3389/fdgth.2026.1759690
BibTeX
@article{Hanzawa2026,
author = {Hanzawa, Mana and Hasei, Joe and Okada, Ayumi and Tanaka, Chie and Shigeyasu, Yoshie and Fujii, Chikako and Horiuchi, Makiko and Sugihara, Akiko and Takeuchi, Koichi and Nakahara, Ryuichi and Katayama, Hideki and Takahashi, Yasushi and Ozaki, Toshifumi and Tsukahara, Hirokazu},
title = {Development of a generative AI agent for family support in implementing family-based treatment for children and adolescents with anorexia nervosa},
journal = {Frontiers in Digital Health},
year = {2026},
volume = {8},
doi = {10.3389/fdgth.2026.1759690}
}
EUVIMED