MétaCan
Menu
Back to cohort
Record W7103418229

Can Contemporary Large Language Models Provide the Domain Knowledge Needed for Causal Inference? Evaluating Automated Causal Graph Discovery Through an ASCVD Case Study

2025· article· en· W7103418229 on OpenAlexaff

Bibliographic record

VenueDOAJ (DOAJ: Directory of Open Access Journals) · 2025
Typearticle
Languageen
FieldMathematics
TopicAdvanced Causal Inference Techniques
Canadian institutionsInstitute of Population and Public Health
Fundersnot available
KeywordsCausal inferenceDirected acyclic graphInferenceConsistency (knowledge bases)PopulationPublic healthBaseline (sea)Population healthEpidemiology
DOInot available

Abstract

fetched live from OpenAlex

Maryam Aziz, M Alan Brookhart Department of Population Health Sciences, Duke University School of Medicine, Durham, NC, USACorrespondence: M Alan Brookhart, Department of Population Health Sciences, Duke University School of Medicine, DUMC 104023, Durham, NC, 27710, USA, Email alan.brookhart@duke.eduPurpose: Directed acyclic graphs (DAGs) are critical in epidemiology and public health research for guiding study design and minimizing bias. Yet, developing DAGs for causal inference requires substantial domain knowledge. Given the vast amounts of training data for large language models (LLMs), this study assesses the effectiveness of prompt engineering for LLMs to generate DAGs that depict causal relationships in population health using OpenAI’s GPT-4o and GPT-o1.Methods: We consider a hypothetical study on statins vs no treatment for prevention of cardiovascular disease in a general adult population. We assessed four types of prompt engineering strategies: zero-shot, one-shot, instruction based, and chain of thought (CoT) prompts. Generated DAGs were assessed based on consistency, acyclicity, accuracy of sources, completeness (based on ASCVD risk score criteria), and adherence to the prompt.Results: We found that all generated DAGs were acyclic, except for one run using the instruction-based prompt. Additionally, more than half of the DAGs included 6/7 of the ASCVD criteria, though race was absent from all. Overall, CoT resulted in the most complete DAGs and one-shot provided the most consistency across runs and adherence to the task in the prompt. The zero-shot prompt performed notably better on GPT-o1 compared to GPT-4o, consistently providing justifications and sources for variable inclusion.Conclusion: While the findings suggest that LLMs have a baseline capacity to generate DAGs that adhere to basic epidemiological conventions, we also found several limitations including lack of justification, systematic omission of race, and frequent source hallucination, highlighting the need for human oversight and expertise. We conclude that contemporary LLMs cannot replace a domain expert’s judgment but may serve as a brainstorming or pre-analysis tool for DAG development when guided by well-engineered prompts.Keywords: artificial intelligence, cardiovascular disease, prompt engineering, directed acyclic graphs

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)0.063
metaresearch head score (Gemma)0.344
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.937
Threshold uncertainty score0.333

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0630.344
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0030.006
Open science0.0030.003
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0040.000

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 head0.543
GPT teacher head0.658
Teacher spread0.115 · 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.

Study designSimulation or modeling
DomainMethods
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 venueDOAJ (DOAJ: Directory of Open Access Journals)Same topicAdvanced Causal Inference TechniquesFrench-language works237,207