MétaCan
Menu
← Back to cohort
Record W4417151762 · doi:10.64898/2025.11.30.25341311

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

2025· article· W4417151762 on OpenAlexaff
Yash Mali, Kayoung Heo, Jincheng Chen, Kamyar Keramatian, Gayatri Saraf, Marco Solmi, Edwin M. Tam, Sagar V. Parikh, Ayal Schaffer, Serge Beaulieu, Raymond Ng, Lakshmi N. Yatham, John-Jose Nuñez

Bibliographic record

VenuemedRxiv · 2025
Typearticle
Language
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsUniversity of TorontoUniversity of OttawaMcGill UniversityUniversity of British Columbia
Fundersnot available
KeywordsChatbotGuidelineConsistency (knowledge bases)Logistic regressionBipolar disorderLanguage modelBase (topology)

Abstract

fetched live from OpenAlex

Abstract 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.

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)0.007
metaresearch head score (Gemma)0.028
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.009
Threshold uncertainty score0.039

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.028
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0090.003

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 head0.138
GPT teacher head0.469
Teacher spread0.331 · 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 designSimulation or modeling
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuemedRxiv→Same topicDigital Mental Health Interventions→French-language works237,207→