Evidence synthesis for constructing directed acyclic graphs (ESC-DAGs): a novel and systematic method for building directed acyclic graphs

Ferguson, Karl; McCann, Mark; Katikireddi, Srinivasa Vittal; Thomson, Hilary; Green, Michael J.; Smith, Daniel J.; Lewsey, James

doi:10.1093/ije/dyz150

Cited by 117 publications

(118 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of developing DAGs and SCC models forces investigators to explicitly articulate assumptions about the causal relationships relevant to the research question of interest, making it transparent to other investigators [44,68] [69]. DAGs may include mediators, which lie on the causal path between the exposure and outcome; a weakened immunity is the mediator by which alcohol consumption causes active-TB.…”

Section: Plausibilitymentioning

confidence: 99%

Assessing causality in epidemiology: revisiting Bradford Hill to incorporate developments in causal thinking

et al. 2020

Self Cite

View full text Add to dashboard Cite

The nine Bradford Hill (BH) viewpoints (sometimes referred to as criteria) are commonly used to assess causality within epidemiology. However, causal thinking has since developed, with three of the most prominent approaches implicitly or explicitly building on the potential outcomes framework: directed acyclic graphs (DAGs), sufficient-component cause models (SCC models, also referred to as ‘causal pies’) and the grading of recommendations, assessment, development and evaluation (GRADE) methodology. This paper explores how these approaches relate to BH’s viewpoints and considers implications for improving causal assessment. We mapped the three approaches above against each BH viewpoint. We found overlap across the approaches and BH viewpoints, underscoring BH viewpoints’ enduring importance. Mapping the approaches helped elucidate the theoretical underpinning of each viewpoint and articulate the conditions when the viewpoint would be relevant. Our comparisons identified commonality on four viewpoints: strength of association (including analysis of plausible confounding); temporality; plausibility (encoded by DAGs or SCC models to articulate mediation and interaction, respectively); and experiments (including implications of study design on exchangeability). Consistency may be more usefully operationalised by considering an effect size’s transportability to a different population or unexplained inconsistency in effect sizes (statistical heterogeneity). Because specificity rarely occurs, falsification exposures or outcomes (i.e., negative controls) may be more useful. The presence of a dose-response relationship may be less than widely perceived as it can easily arise from confounding. We found limited utility for coherence and analogy. This study highlights a need for greater clarity on BH viewpoints to improve causal assessment.

show abstract

Section: Plausibilitymentioning

confidence: 99%

Assessing causality in epidemiology: revisiting Bradford Hill to incorporate developments in causal thinking

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In 2013, Sauer and VanderWeele offered a list of core considerations, but highlighted a need for a 'disciplined approach to developing DAGs'. 17 Ferguson et al (2019) responded by offering a structured protocol to aid with building DAGs, 18 but there remains little advice on various practical considerations, including the reporting of:…”

Section: Figures and Tablesmentioning

confidence: 99%

“…In 2013, Sauer and VanderWeele offered a list of core considerations, but highlighted a need for a ‘disciplined approach to developing DAGs’. 17 Ferguson et al (2019) responded by offering a structured protocol to aid with building DAGs, 18 but there remains little advice on various practical considerations, including the reporting of: estimands of interest, DAGs, implied adjustment set(s) and results thereof, and the spatial arrangement of variables, and the justification for including or omitting dependencies.…”

Section: Introductionmentioning

confidence: 99%

Use of directed acyclic graphs (DAGs) in applied health research: review and recommendations

Tennant

Harrison

Murray

et al. 2019

Preprint

View full text Add to dashboard Cite

BACKGROUND: Directed acyclic graphs (DAGs) are an increasingly popular approach for identifying confounding variables that require adjustment when estimating causal effects. This review examined the use of DAGs in applied health research to inform recommendations for improving their transparency and utility in future research. METHODS: Original health research articles published during 1999-2017 mentioning "directed acyclic graphs" or similar or citing DAGitty were identified from Scopus, Web of Science, Medline, and Embase. Data were extracted on the reporting of: estimands, DAGs, and adjustment sets, alongside the characteristics of each article's largest DAG. RESULTS: A total of 234 articles were identified that reported using DAGs. A fifth (n=48, 21%) reported their target estimand(s) and half (n=115, 48%) reported the adjustment set(s) implied by their DAG(s). Two-thirds of the articles (n=144, 62%) made at least one DAG available. Diagrams varied in size but averaged 12 nodes (IQR: 9-16, range: 3-28) and 29 arcs (IQR: 19-42, range: 3-99). The median saturation (i.e. percentage of total possible arcs) was 46% (IQR: 31-67, range: 12-100). 37% (n=53) of the DAGs included unobserved variables, 17% (n=25) included super-nodes (i.e. nodes containing more than one variable, and a 34% (n=49) were arranged so the constituent arcs flowed in a consistent direction. CONCLUSIONS: There is substantial variation in the use and reporting of DAGs in applied health research. Although this partly reflects their flexibility, it also highlight some potential areas for improvement. This review hence offers several recommendations to improve the reporting and use of DAGs in future research.

show abstract

“…Our approach to developing the DAG using a systematic literature review was consistent with many of the tenants of DAG development discussed elsewhere. 26,59 Our quantitative assessment of the DAG structure suggested that the evidence-based DAG was a reasonable representation of relationships among variables in a real data set. Furthermore, as demonstrated through our pilot analysis, environmental epidemiologists can apply our evidence-based DAG to transparently, reproducibly, and efficiently investigate longitudinal associations between complex environmental exposures and cardiometabolic health outcomes adjusting for one of three identified sets of covariates.…”

Section: Discussionmentioning

confidence: 96%

Development and application of an evidence-based directed acyclic graph to evaluate the associations between metal mixtures and cardiometabolic outcomes

Riseberg

Melamed

Ka³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Exposure to individual metals (and metalloids; hereafter 'metals') is associated with adverse cardiometabolic outcomes. Specifying analytic models to assess relationships among metal mixtures and cardiometabolic outcomes requires evidence-based models of the (assumed) causal structures; however, such models have not been previously published. Methods: We conducted a systematic literature review to develop an evidence-based directed acyclic graph (DAG) identifying relationships among metals, cardiometabolic health indicators, and potential confounders. To evaluate the consistency of the DAG with data from 1797 participants in the San Luis Valley Diabetes Study (SLVDS; mean age=54 years, 53% women, 48% Hispanic), we tested conditional independence statements suggested by the DAG and by 100 DAGs with the same structure but randomly permuted nodes using linear (continuous outcomes), logistic (dichotomous outcomes), or Bayesian kernel machine regression (BKMR; statements with metal coexposures) models. Based on minimally sufficient adjustment sets identified by the DAG, we specified BKMR models assessing associations between urinary metal mixtures and cardiometabolic outcomes in the SLVDS population. Results: Twenty-nine articles met the inclusion criteria for the systematic review. From these articles, we developed an evidence-based DAG with 382 testable conditional independence statements (71% supported by SLVDS data). Only 3% of the DAGs with randomly permuted nodes indicated more agreement with the data than our evidence-based DAG. Applying the evidence-based DAG in a pilot analysis, we did not observe evidence for an association among metal mixtures and cardiometabolic outcomes. Conclusions: We developed, tested, and applied an evidence-based approach to analyze associations between metal mixtures and cardiometabolic health.

show abstract

Evidence synthesis for constructing directed acyclic graphs (ESC-DAGs): a novel and systematic method for building directed acyclic graphs

Cited by 117 publications

References 33 publications

Assessing causality in epidemiology: revisiting Bradford Hill to incorporate developments in causal thinking

Assessing causality in epidemiology: revisiting Bradford Hill to incorporate developments in causal thinking

Use of directed acyclic graphs (DAGs) in applied health research: review and recommendations

Development and application of an evidence-based directed acyclic graph to evaluate the associations between metal mixtures and cardiometabolic outcomes

Contact Info

Product

Resources

About