Randomized trials and evidence in medicine: A commentary on Deaton and Cartwright

Concato, John; Horwitz, Ralph I.

doi:10.1016/j.socscimed.2018.04.010

Cited by 13 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RCTs are widely considered the “gold standard” for clinical trials but there is significant concern that the lay public (and sometimes researchers) put too much trust in RCTs over other methods and that their status is exaggerated [73,74]. Disturbingly, findings from flawed RCTs have overturned policy decisions when they contradicted better evidence from observational study findings [75].…”

Section: Discussionmentioning

confidence: 99%

“…A comprehensive analysis of ten of the most influential and cited RCTs worldwide found that they did not meet minimal quality standards - with multiple sources of unexamined and undeclared sources of bias - and called into question the robustness of their results [76]. There is significant concern that the lay public and sometimes researchers put too much trust in RCTs over other methods and that their status is exaggerated [73,74]. This especially concerning when findings from flawed RCTs have preferentially influenced policy over those from correct observational study findings [75].…”

Section: Figure 12mentioning

confidence: 99%

See 1 more Smart Citation

Evidence Supports a Causal Model for Vitamin D in COVID-19 Outcomes

Davies

Garami

Byers

2020

Preprint

View full text Add to dashboard Cite

We analyse global data for COVID-19 deaths and recoveries and show that outbreak severity displays a striking latitude relationship with a northern hemisphere bias. Transmission rates can be explained by seasonal weather conditions, but this does not account for observed variations in fatality rates. Many factors point to Vitamin D as a candidate explanation but historical controversy surrounding Vitamin D studies and the lack of a coherent framework for causal inference has hampered acceptance of this explanation despite a wealth of evidence in its favour.We analyse global COVID-19 data using Causal Inference, constructing two contrasting directed acyclic graph (DAG) models, one causal and one acausal, and set out clearly multiple predictions made by each model. We show that observed data strongly match predictions made by the causal model but largely contradict those of the acausal model. We explore historic evidence further supporting the causal model.We review biochemical mechanisms that may explain the various ways in which vitamin D acts. We detail the mechanisms by which the SARS-Cov-2 virus causes the disease and known pathways that involve Vitamin D and show how these both protect against viral infection, as well as ameliorating disease symptoms in COVID-19 and other respiratory diseases.We examine the factors that govern confidence in causal inference models and conclude that a high level of confidence in a causal beneficial role for Vitamin D is justified.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Figure 12mentioning

confidence: 99%

Evidence Supports a Causal Model for Vitamin D in COVID-19 Outcomes

Davies

Garami

Byers

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Sanson-Fisher, Bonevski, Green, and D'Este (2007) show that experiments are fundamentally too limited in scope to consider impact evaluations, such as women's empowerment. Concato and Horwitz (2018) survey the consensus in medicine. 19 It has switched away from reliance on RCTs as the "gold standard," which they say was the party line in the 1990s in medicine.…”

Section: Post-script 2019mentioning

confidence: 99%

Randomization and Social Policy Evaluation Revisited

Heckman

2020

View full text Add to dashboard Cite

show abstract

“…The need for personalized evidence follows from recognition that treatment effect heterogeneity across patients is the rule rather than exception in healthcare [4][5][6][7][8][9][10]. While randomized controlled trials (RCTs) are the gold standard for evidence generation, with treatment effect heterogeneity it is difficult for RCTs to generate personalized evidence for many patients [4,[11][12][13][14]. Comparative effectiveness research (CER) using large observational databases has been suggested as an alternative to develop personalized evidence [1,2,[15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Assessing the ability of an instrumental variable causal forest algorithm to personalize treatment evidence using observational data: the case of early surgery for shoulder fracture

Brooks

Chapman

Floyd

et al. 2022

BMC Med Res Methodol

View full text Add to dashboard Cite

Background Comparative effectiveness research (CER) using observational databases has been suggested to obtain personalized evidence of treatment effectiveness. Inferential difficulties remain using traditional CER approaches especially related to designating patients to reference classes a priori. A novel Instrumental Variable Causal Forest Algorithm (IV-CFA) has the potential to provide personalized evidence using observational data without designating reference classes a priori, but the consistency of the evidence when varying key algorithm parameters remains unclear. We investigated the consistency of IV-CFA estimates through application to a database of Medicare beneficiaries with proximal humerus fractures (PHFs) that previously revealed heterogeneity in the effects of early surgery using instrumental variable estimators. Methods IV-CFA was used to estimate patient-specific early surgery effects on both beneficial and detrimental outcomes using different combinations of algorithm parameters and estimate variation was assessed for a population of 72,751 fee-for-service Medicare beneficiaries with PHFs in 2011. Classification and regression trees (CART) were applied to these estimates to create ex-post reference classes and the consistency of these classes were assessed. Two-stage least squares (2SLS) estimators were applied to representative ex-post reference classes to scrutinize the estimates relative to known 2SLS properties. Results IV-CFA uncovered substantial early surgery effect heterogeneity across PHF patients, but estimates for individual patients varied with algorithm parameters. CART applied to these estimates revealed ex-post reference classes consistent across algorithm parameters. 2SLS estimates showed that ex-post reference classes containing older, frailer patients with more comorbidities, and lower utilizers of healthcare were less likely to benefit and more likely to have detriments from higher rates of early surgery. Conclusions IV-CFA provides an illuminating method to uncover ex-post reference classes of patients based on treatment effects using observational data with a strong instrumental variable. Interpretation of treatment effect estimates within each ex-post reference class using traditional CER methods remains conditional on the extent of measured information in the data.

show abstract

Randomized trials and evidence in medicine: A commentary on Deaton and Cartwright

Cited by 13 publications

References 54 publications

Evidence Supports a Causal Model for Vitamin D in COVID-19 Outcomes

Evidence Supports a Causal Model for Vitamin D in COVID-19 Outcomes

Randomization and Social Policy Evaluation Revisited

Assessing the ability of an instrumental variable causal forest algorithm to personalize treatment evidence using observational data: the case of early surgery for shoulder fracture

Contact Info

Product

Resources

About