Can Contemporary Large Language Models Provide the Domain Knowledge Needed for Causal Inference? Evaluating Automated Causal Graph Discovery Through an ASCVD Case Study
Bibliographic record
Abstract
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.063 | 0.344 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.006 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".