Caveats for the Use of Operational Electronic Health Record Data in Comparative Effectiveness Research

By William R. Hersh, M. Weiner, P. Embí, Judith R. Logan, Philip R. O. Payne, Elmer Victor Bernstam, Harold P. Lehmann, George Hripcsak, Timothy H. Hartzog, J. Cimino and 1 more. Medical Care, 2013

509 citations recorded by the source corpus.

The growing amount of data in operational electronic health record (EHR) systems provides unprecedented opportunity for its re-use for many tasks, including comparative effectiveness research (CER). However, there are many caveats to the use of such data. EHR data from clinical settings may be inaccurate, incomplete, transformed in ways that undermine their meaning, unrecoverable for research, of unknown provenance, of insufficient granularity, and incompatible with research protocols. However, the quantity and real-world nature of these data provide impetus for their use, and we develop a list of caveats to inform would-be users of such data as well as provide an informatics roadmap that aims to insure this opportunity to augment CER can be best leveraged.

Subfields: Health Information Management, Management Science and Operations Research, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/3869181a1300b574a5806f35d3b92665c529ae03

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Health Information Management

In Management Science and Operations Research

In Molecular Biology

Citations in the corpus

Identifying and Mitigating Biases in EHR Laboratory Tests (2014, unknown): “Automating feature selection from EHR variables is a difficult task, as the EHR is an inherently biased data source: EHR data are collected with the primary goal of delivering and documenting patient care, not with the primary goal of creating a curated research dataset [4] [5].”
A Harmonized Data Quality Assessment Terminology and Framework for the Secondary Use of Electronic Health Record Data (2016, background): “24–27 Transaction-oriented systems rarely include prespecified, unambiguous data definitions, and uniform (unbiased) data collection procedures.”
Extracting research-quality phenotypes from electronic health records to support precision medicine (2015, background): “EHRs derive from selected populations and their data contain biases [34,45,106]; in particular, they are biased toward sick individuals.”
The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment (2020, background): “125 EHR data captured in real time are often wrong (eg, incorrect diagnosis) or may have originated from a different patient.”
Graph embedding on biomedical networks: methods, applications and evaluations (2019, background): “, clinical notes, surgical records, discharge records) as EMRs (Hersh et al., 2013).”
Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine (2020, methodology): “Use of EHR in comparative effectiveness research (46) Reporting caveats in existing healthcare systems.”
Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review (2017, background): “As others have noted, EHR data come with many challenges.(4) EHRs include all patients that touch a medical system, primarily capture data only when patients are ill, and collect metrics that clinicians deem to be necessary at each clinic visit.”
Key challenges for delivering clinical impact with artificial intelligence (2019, unknown): “Adoption of unified data formats, such as Fast Healthcare Interoperability Resources [84], offer the potential for better aggregation of data, although improved interoperability does not necessarily fix the problem of inconsistent semantic coding in EHR data [85].”
Launching PCORnet, a national patient-centered clinical research network (2014, background): “17 Second, in order to achieve multi-institutional querying, PCORnet will have to deal with data harmonization.”
Harnessing multimodal data integration to advance precision oncology (2021, background): “The general limits of using health-care records to conduct research are widely discussed 109 : one challenge is unobserved patient outcomes, which can be handled for time- to-event analysis but requires excluding patients for categorical outcomes.”
Electronic health records to facilitate clinical research (2016, background): “Excessive or busy workloads may also contribute to errors in clinician data entry [43].”