• Corpus ID: 9554729

Sick Patients Have More Data: The Non-Random Completeness of Electronic Health Records

@article{Weiskopf2013SickPH,
  title={Sick Patients Have More Data: The Non-Random Completeness of Electronic Health Records},
  author={Nicole Gray Weiskopf and Alex Rusanov and Chunhua Weng},
  journal={AMIA ... Annual Symposium proceedings. AMIA Symposium},
  year={2013},
  volume={2013},
  pages={
          1472-7
        }
}
As interest in the reuse of electronic health record (EHR) data for research purposes grows, so too does awareness of the significant data quality problems in these non-traditional datasets. In the past, however, little attention has been paid to whether poor data quality merely introduces noise into EHR-derived datasets, or if there is potential for the creation of spurious signals and bias. In this study we use EHR data to demonstrate a statistically significant relationship between EHR… 

Figures and Tables from this paper

On the Nature of Informative Presence Bias in Analyses of Electronic Health Records
TLDR
It is shown that informative presence bias can occur in a broader range of settings than previously thought, and that simple adjustment for the number of visits as a confounder may not fully correct for bias.
Controlling for Informed Presence Bias Due to the Number of Health Encounters in an Electronic Health Record.
TLDR
Simulated and empirical data are used to illustrate the conditions under which bias can arise and how conditioning on the number of health-care encounters can be one way to remove this bias.
Practice of Epidemiology Controlling for Informed Presence Bias Due to the Number of Health Encounters in an Electronic Health Record
TLDR
Simulated and empirical data are used to illustrate the conditions under which bias can arise and how conditioning on the number of health-care encounters can be one way to remove this bias.
How and when informative visit processes can bias inference when using electronic health records data for clinical research
TLDR
It is suggested that an informative visit process can exaggerate an association but cannot induce one, and careful study design can, mitigate the potential bias when some noninformative visits are included.
Constructing Epidemiologic Cohorts from Electronic Health Record Data
  • B. Williams
  • Medicine
    International journal of environmental research and public health
  • 2021
TLDR
Three aspects of machinery development of high salience to EHR-based epidemiology are focused on: selecting study participants; defining “baseline” and assembly of baseline characteristics; and follow-up for future outcomes.
A New Insight Into Missing Data in Intensive Care Unit Patient Profiles: Observational Study
TLDR
It is demonstrated that the presence or absence of LT measurements is informative and can be considered a potential predictor of in-hospital and 30-day mortality and has predictive power beyond the measured data themselves.
Cardiovascular disease risk prediction for people with type 2 diabetes in a population-based cohort and in electronic health record data
TLDR
EHR-estimated HRs of demographic and major clinical risk factors for CVD were mostly consistent with the estimates from a national cohort, despite high incidences and absolute risks of total CVD outcome in the EHR samples.
Informative presence and observation in routine health data: A review of methodology for clinical risk prediction
TLDR
The work included in this review has demonstrated theoretical and empirical benefits of incorporating IP and IO, and therefore it is recommended that applied health researchers consider incorporating these methods in their work.
Hidden in plain sight: bias towards sick patients when sampling patients with sufficient electronic health record data for research
TLDR
The relationship between patient health and quantity of data is demonstrated, which may result in a systematic bias towards the selection of sicker patients for research studies and limit the external validity of research conducted using electronic health record data.
On Missingness Features in Machine Learning Models for Critical Care: Observational Study (Preprint)
TLDR
Improved model performance in retrospective tasks was observed on including missingness features and a detailed understanding of how these features affect model performance may lead to their informed use in clinical settings especially for administrative tasks like length of stay prediction where they present the greatest benefit.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 24 REFERENCES
Caveats for the use of operational electronic health record data in comparative effectiveness research.
TLDR
A list of caveats is developed to inform would-be users of such data as well as provide an informatics roadmap that aims to insure this opportunity to augment comparative effectiveness research can be best leveraged.
Review: Accuracy of Data in Computer-based Patient Records
TLDR
It is concluded that knowledge of data accuracy in CPRs is not commensurate with its importance and further studies are needed, and methodological guidelines for studying accuracy are proposed that address shortcomings of the current literature.
Review: Electronic Health Records and the Reliability and Validity of Quality Measures: A Review of the Literature
TLDR
The authors reviewed empirical studies of EHR data quality, published from January 2004, with an emphasis on data attributes relevant to quality measurement, to focus on the quality of data from specific EHR components and important data attributes for quality measurement such as granularity, timeliness, and comparability.
Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research
TLDR
Researchers interested in the reuse of EHR data for clinical research are recommended to consider the adoption of a consistent taxonomy of E HR data quality, to remain aware of the task-dependence of dataquality, and to integrate work on data quality assessment from other fields.
White Paper: Advancing the Framework: Use of Health Data - A Report of a Working Conference of the American Medical Informatics Association
TLDR
A taxonomy developed to focus definitions and terminology in the evolving field of health data applications is introduced and it is recommended that public and private sector organizations elevate consideration of a national framework on the uses of healthData to a top priority.
Missing data: our view of the state of the art.
TLDR
2 general approaches that come highly recommended: maximum likelihood (ML) and Bayesian multiple imputation (MI) are presented and may eventually extend the ML and MI methods that currently represent the state of the art.
Relationship between nursing documentation and patients' mortality.
  • S. Collins, K. Cato, D. Vawdrey
  • Medicine
    American journal of critical care : an official publication, American Association of Critical-Care Nurses
  • 2013
TLDR
For the first time, nursing documentation patterns have been linked to patients' mortality and findings were consistent with the hypothesis that some features of nursing documentation within electronic health records can be used to predict mortality.
White Paper: Toward a National Framework for the Secondary Use of Health Data: An American Medical Informatics Association White Paper
TLDR
The nation requires a framework for the secondary use of health data with a robust infrastructure of policies, standards, and best practices that can guide and facilitate widespread collection, storage, aggregation, linkage, and transmission of healthData.
Systematic review of scope and quality of electronic patient record data in primary care
TLDR
The lack of standardised methods for assessment of quality of data in electronic patient records makes it difficult to compare results between studies, and studies should present data quality measures with clear numerators, denominators, and confidence intervals.
...
1
2
3
...