2011
DOI: 10.5210/disco.v6i0.3581
|View full text |Cite
|
Sign up to set email alerts
|

Bias Associated with Mining Electronic Health Records

Abstract: Large‐scale electronic health record research introduces biases compared to traditional manually curated retrospective research. We used data from a community‐acquired pneumonia study for which we had a gold standard to illustrate such biases. The challenges include data inaccuracy, incompleteness, and complexity, and they can produce in distorted results. We found that a naïve approach approximated the gold standard, but errors on a minority of cases shifted m… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
50
0
1

Year Published

2013
2013
2021
2021

Publication Types

Select...
4
4

Relationship

1
7

Authors

Journals

citations
Cited by 68 publications
(51 citation statements)
references
References 5 publications
0
50
0
1
Order By: Relevance
“…At the same time, we are better defining potential limitations of EHRderived data [20] and developing ways to address them [21] [22]. Sharing of data from disparate EHR systems to enable populationbased research [9] is a logical and widely anticipated extension.…”
Section: Introductionmentioning
confidence: 99%
“…At the same time, we are better defining potential limitations of EHRderived data [20] and developing ways to address them [21] [22]. Sharing of data from disparate EHR systems to enable populationbased research [9] is a logical and widely anticipated extension.…”
Section: Introductionmentioning
confidence: 99%
“…As Hripcsak et al (2011) note, overlooking data errors or omissions may lead to misleading results as extreme outliers, for instance, may have a disproportionate influence on findings. Traditionally in retrospective research, the researcher will manually inspect cases for accuracy and completeness and will correct data where necessary.…”
Section: Methodological Issuesmentioning
confidence: 96%
“…However, in order to capitalize on these opportunities, a number of challenges must be surmounted. A major challenge in secondary research of EHRs is data quality, namely completeness and accuracy (Hripcsak, Knirsch, Zhou, Wilcox, & Melton, 2011;Orueta et al, 2012;Spooner & Kirkendall, 2012;Teasdale, Bates, Kmetik, Suzewits, & Bainbridge, 2007;Tolar & Balka, 2012;Weiner, Lyman, Murphy, & Weiner, 2007;Weiskopf & Weng, 2012), discrepancies/inconsistencies in data (Orueta et al, 2012;Weiner et al, 2007) and interoperability (Jensen et al, 2012;Spooner & Kirkendall, 2012). There are also significant ethical issues, such as privacy and informed consent, that emerge in secondary research of EHRs (see, e.g.…”
Section: Methodological Issuesmentioning
confidence: 99%
“…These observational data (rather than experimental data) are more process-related and frequently lack outcome data needed for effective research [21]. Clinical data are also biased by the incentives for clinicians to "upcode", by the non-random assignment of treatments, by systematic differences between patients and the general population, by the healthcare system complexity causing multiple confounders, and the large variability of measurement instruments and methods [40,41]. The quality of data is often problematic or insufficient for research applications [42][43][44].…”
Section: B Motivations and Challenges For Clinical Data Reusementioning
confidence: 99%