Zejiao Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zejiao Zeng has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Antarip Kashyap
University of British Columbia
2 shared publications- Ayal Schaffer
Department of Psychiatry, Sunnybrook Health Sciences Centre, Toronto, ON, Canada
2 shared publications - Gayatri Saraf
University of Ottawa
2 shared publications Jincheng Chen
University of British Columbia
2 shared publications- John-Jose Nunez
BC Cancer, Vancouver, BC, Canada
2 shared publications - Kamyar Keramatian
University of British Columbia
2 shared publications
Latest Publications
- Open Access
- 11 June 2026
- Published by SAGE Publications in The Canadian Journal of Psychiatry
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
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.
- 11 June 2026
- Published by SAGE Publications in The Canadian Journal of Psychiatry
Open AccessA 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
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.
- Open Access
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
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 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 two systems: one using the base Llama 3.3 70B model, the other RAG-enhanced. Responses rated guideline consistency on a three-point scale, and were analyzed using mixed-effects ordinal logistic regression. Results: Experts evaluated 126 responses, of which 110 (87.3%) were rated as more or as correct as 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 favored 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 viability 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.
Open AccessA 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
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 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 two systems: one using the base Llama 3.3 70B model, the other RAG-enhanced. Responses rated guideline consistency on a three-point scale, and were analyzed using mixed-effects ordinal logistic regression. Results: Experts evaluated 126 responses, of which 110 (87.3%) were rated as more or as correct as 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 favored 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 viability 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.