Cardiovascular health researchers aim to create new knowledge through discoveries that improve health, longevity, and well-being. Methods to ask and answer hypothesis-driven research questions span the spectrum from observational reports of individuals and groups to testing of interventions through large-scale randomized trials. There is a large range in quality across this spectrum, with observational studies being particularly at risk for bias.
The article by McGuinness et al1 in this issue of JAMA Cardiology introduces the Risk of Bias in Nonrandomized Studies of Interventions (ROBINS-I) tool to our readers. The authors are leaders in the field of causal inference, including in the Cochrane Risk of Bias tool for randomized trials, and the ROBINS-I tool logically extends this previous work.2 The ROBINS-I tool is a substantial improvement over the current standard, the Newcastle-Ottawa Scale,3 which relies on a star rating that can mask major methodological flaws that limit internal validity. Instead, the ROBINS-I tool relies on a transparent framework that evaluates sources of bias.