EUVIMEDEUVIMED entdecken
LeitlinieOpen Access · CC BY-NC 4.0

A Chatbot for the Management of Bipolar Disorder: Using Retrieval-Augmented Generation With an Open-Weight Large Language Model to Answer Clinical Questions Based on the CANMAT and ISBD 2018 Guidelines for Bipolar Disorder: Un dialogueur pour la prise en charge du trouble bipolaire : utiliser la génération augmentée par récupération avec un grand modèle de langage (GML) à poids ouverts pour répondre aux questions cliniques fondées sur les lignes directrices de 2018 de CANMAT et de l'ISBD relatives au trouble bipolaire

Yash Mali iD, Zejiao Zeng iD, Kayoung Heo, Grace Zhang, Antarip Kashyap, Jincheng Chen, Kamyar Keramatian iD, Gayatri Saraf iD, Marco Solmi iD, Edwin Tam iD, Sagar V Parikh, Ayal Schaffer iD und 4 weitere

The Canadian Journal of Psychiatry · 11.06.2026

DOI: 10.1177/07067437261457232 ↗

Kurz gefasst

Leitlinie in der Zeitschrift The Canadian Journal of Psychiatry, online erschienen am 11.06.2026. Verfasst von Yash Mali und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of British Columbia, Vancouver, Canada. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Amazon Web Services.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Clinical practice guidelines support evidence-based care but are often underused due to complexity, time constraints, and navigation challenges. We investigated whether a conversational agent (chatbot) using an open-weight large language model (LLM) with retrieval-augmented generation (RAG) could provide guideline-consistent answers for bipolar disorder management based on the full 2018 Canadian Network for Mood and Anxiety Treatments (CANMAT) and ISBD guidelines, comparing against a system using only the base LLM.

Method

We developed a multi-step RAG-based chatbot that retrieves relevant guideline sections and generates responses using Llama 3.3 70B. Twenty-one clinical vignettes spanning all guideline sections were created. Six expert psychiatrists generated queries and were presented with paired responses without labels from 2 systems: one using the base Llama 3.3 70B model, the other RAG-enhanced. Responses were rated for guideline consistency on a 3-point scale, and were analyzed using mixed-effects ordinal logistic regression.

Results

Experts evaluated 126 responses, of which 110 (87.3%) were rated as correct as or more correct than the baseline system. The RAG system produced 80 answers (63.5%) rated fully consistent with the guidelines versus 24 (19.0%) for baseline, and only 10 answers with major deviation (7.9%) versus 48 (38.1%) for baseline. Ordinal regression showed RAG responses were significantly more likely to be more correct (OR = 9.1, 95% CI [5.3-16.3], P < 0.001), which was consistent across all raters. Preference ratings favoured RAG answers in 78.7% of cases. Performance varied by vignette, with some errors in both retrieval and reasoning.

Conclusion

The use of RAG with an open-weight model helped produce answers consistent with the CANMAT guidelines across vignettes that required adapting or combining guideline text, suggesting a proof-of-concept of a bipolar guideline chatbot. We identified areas to improve results and evaluation. Future work should explore additional retrieval strategies and LLMs, and test in more naturalistic settings.

Schlagwörter

Stichwörter der Autor:innen

NLPartificial intelligencebipolar disordermachine learning

Autor:innen und Institutionen

  • Department of Computer Science, University of British Columbia, Vancouver, Canada.
  • Department of Psychiatry, University of British Columbia, Vancouver, Canada.
  • Department of Linguistics, University of British Columbia, Vancouver, Canada.
  • Department of Psychiatry, University of Ottawa, Ottawa, Canada.
  • Department of Psychiatry, University of Michigan, Ann Arbor, USA.
  • Department of Psychiatry, University of Toronto, Toronto, Canada.

ORCID-Profile: Yash Mali, Zejiao Zeng, Kamyar Keramatian, Gayatri Saraf, Marco Solmi, Edwin Tam, Ayal Schaffer, Serge Beaulieu, Lakshmi N Yatham, John-Jose Nunez

Förderung

  • Amazon Web Services

Zitieren

APA

Mali, Y., Zeng, Z., Heo, K., Zhang, G., Kashyap, A., Chen, J., Keramatian, K., Saraf, G., Solmi, M., Tam, E., Parikh, S. V., Schaffer, A., Beaulieu, S., Ng, R., Yatham, L. N., & Nunez, J. J. (2026). A Chatbot for the Management of Bipolar Disorder: Using Retrieval-Augmented Generation With an Open-Weight Large Language Model to Answer Clinical Questions Based on the CANMAT and ISBD 2018 Guidelines for Bipolar Disorder: Un dialogueur pour la prise en charge du trouble bipolaire : utiliser la génération augmentée par récupération avec un grand modèle de langage (GML) à poids ouverts pour répondre aux questions cliniques fondées sur les lignes directrices de 2018 de CANMAT et de l'ISBD relatives au trouble bipolaire. The Canadian Journal of Psychiatry. https://doi.org/10.1177/07067437261457232

Vancouver

Mali Y, Zeng Z, Heo K, Zhang G, Kashyap A, Chen J, et al. A Chatbot for the Management of Bipolar Disorder: Using Retrieval-Augmented Generation With an Open-Weight Large Language Model to Answer Clinical Questions Based on the CANMAT and ISBD 2018 Guidelines for Bipolar Disorder: Un dialogueur pour la prise en charge du trouble bipolaire : utiliser la génération augmentée par récupération avec un grand modèle de langage (GML) à poids ouverts pour répondre aux questions cliniques fondées sur les lignes directrices de 2018 de CANMAT et de l'ISBD relatives au trouble bipolaire. The Canadian Journal of Psychiatry. 2026. doi:10.1177/07067437261457232

BibTeX
@article{Mali2026,
  author = {Mali, Yash and Zeng, Zejiao and Heo, Kayoung and Zhang, Grace and Kashyap, Antarip and Chen, Jincheng and Keramatian, Kamyar and Saraf, Gayatri and Solmi, Marco and Tam, Edwin and Parikh, Sagar V and Schaffer, Ayal and Beaulieu, Serge and Ng, Raymond and Yatham, Lakshmi N and Nunez, John-Jose},
  title = {A Chatbot for the Management of Bipolar Disorder: Using Retrieval-Augmented Generation With an Open-Weight Large Language Model to Answer Clinical Questions Based on the CANMAT and ISBD 2018 Guidelines for Bipolar Disorder: Un dialogueur pour la prise en charge du trouble bipolaire : utiliser la génération augmentée par récupération avec un grand modèle de langage (GML) à poids ouverts pour répondre aux questions cliniques fondées sur les lignes directrices de 2018 de CANMAT et de l'ISBD relatives au trouble bipolaire},
  journal = {The Canadian Journal of Psychiatry},
  year = {2026},
  doi = {10.1177/07067437261457232}
}
Kostenlos starten →