Why the study?
Despite advances in medical data science, issues around data quality have received comparatively little attention, prompting an illustration of what can go wrong when medical analytics rely on poor quality data.
Key points are not available for this paper at this time.
Design
Case study demonstration
Highlights the critical importance of data quality, showing that imprecise blood pressure measurements can severely distort the estimated benefits of interventions on cardiovascular mortality.
In the current era of big biomedical data, the field of medical data science has made many advances in predictive modelling and medical decisions derived from electronic health records. Issues around data quality have received comparatively much less attention. To create awareness around the importance of high quality data, we set out to develop a number of case studies that illustrate what can go wrong when medical analytics and decision making is based on poor quality data. In this short paper, we focus on imprecise data. Specifically, we demonstrate how even relatively small random measurement errors in blood pressure data may lead to a gross overestimation of the impact of a blood pressure lowering intervention on cardiovascular mortality.
No takes yet. Share an insight, caveat, or question.
Delva et al. (2022) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: