The role of statistics in the era of big data: Electronic health records for healthcare research

Abstract

The transferring of medical records into huge electronic databases has opened up opportunities for research but requires attention to data quality, study design and issues of bias and confounding.

Data Resource Profile: The Virtual Cardio-Oncology Research Initiative (VICORI) linking national English cancer registration and cardiovascular audits

“…Through this, the VICORI programme will further knowledge into biological mechanisms, treatment effects and the effectiveness of health care delivery for both cancer and cardiac disease patients. 15 …”

Large datasets, bias and model‐oriented optimal design of experiments

“…Many authors in Ref 15 . argues that analysis of big dataset is effected by issues of bias and confounding, selection bias and other sampling problems (see, for example, Sharpes 14 for electronic health records). Often the causal effect of interest can only be measured on the average and great care has to be taken about the background population, for example, it is possible to consider and analyse every message on Twitter and use it to draw conclusions about the public opinion, but it is known that Twitter users are not representative of the whole population.…”

Filling the Gap Between Potential and Actual Usefulness of Electronic Health Record (EHR) Data as Patient-Level Evidence

“…Clearly, changes are needed in order for health services and care policy researchers to reliably take advantage of the information-rich potential of these data sources. 7 The authors of the papers presented here showcased in detail a remarkable degree of experience and expertise that is needed in order to fruitfully draw usable robust evidence from abundant, fine-grain, unrefined and disjoint EHR data-bases. There is a clear need for further coordinated investments in data management, pre-processing, and analysis of these routinely collected data.…”