Dataset Information

Identifying and mitigating biases in EHR laboratory tests.

ABSTRACT: Electronic health record (EHR) data show promise for deriving new ways of modeling human disease states. Although EHR researchers often use numerical values of laboratory tests as features in disease models, a great deal of information is contained in the context within which a laboratory test is taken. For example, the same numerical value of a creatinine test has different interpretation for a chronic kidney disease patient and a patient with acute kidney injury. We study whether EHR research studies are subject to biased results and interpretations if laboratory measurements taken in different contexts are not explicitly separated. We show that the context of a laboratory test measurement can often be captured by the way the test is measured through time. We perform three tasks to study the properties of these temporal measurement patterns. In the first task, we confirm that laboratory test measurement patterns provide additional information to the stand-alone numerical value. The second task identifies three measurement pattern motifs across a set of 70 laboratory tests performed for over 14,000 patients. Of these, one motif exhibits properties that can lead to biased research results. In the third task, we demonstrate the potential for biased results on a specific example. We conduct an association study of lipase test values to acute pancreatitis. We observe a diluted signal when using only a lipase value threshold, whereas the full association is recovered when properly accounting for lipase measurements in different contexts (leveraging the lipase measurement patterns to separate the contexts). Aggregating EHR data without separating distinct laboratory test measurement patterns can intermix patients with different diseases, leading to the confounding of signals in large-scale EHR analyses. This paper presents a methodology for leveraging measurement frequency to identify and reduce laboratory test biases.

SUBMITTER: Pivovarov R

PROVIDER: S-EPMC4194228 | biostudies-literature | 2014 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying and mitigating biases in EHR laboratory tests.

Pivovarov Rimma R Albers David J DJ Sepulveda Jorge L JL Elhadad Noémie N

Journal of biomedical informatics 20140413

Electronic health record (EHR) data show promise for deriving new ways of modeling human disease states. Although EHR researchers often use numerical values of laboratory tests as features in disease models, a great deal of information is contained in the context within which a laboratory test is taken. For example, the same numerical value of a creatinine test has different interpretation for a chronic kidney disease patient and a patient with acute kidney injury. We study whether EHR research ...[more]

PMID: 24727481

Similar Datasets

Project description:On the behest of the Office of Science and Technology Policy in the White House, six institutions, including ours, have created an open research dataset called COVID-19 Research Dataset (CORD-19) to facilitate the development of question-answering systems that can assist researchers in finding relevant research on COVID-19. As of May 27, 2020, CORD-19 includes more than 100,000 open access publications from major publishers and PubMed as well as preprint articles deposited into medRxiv, bioRxiv, and arXiv. Recent years, however, have also seen question-answering and other machine learning systems exhibit harmful behaviors to humans due to biases in the training data. It is imperative and only ethical for modern scientists to be vigilant in inspecting and be prepared to mitigate the potential biases when working with any datasets. This article describes a framework to examine biases in scientific document collections like CORD-19 by comparing their properties with those derived from the citation behaviors of the entire scientific community. In total, three expanded sets are created for the analyses: 1) the enclosure set CORD-19E composed of CORD-19 articles and their references and citations, mirroring the methodology used in the renowned "A Century of Physics" analysis; 2) the full closure graph CORD-19C that recursively includes references starting with CORD-19; and 3) the inflection closure CORD-19I, that is, a much smaller subset of CORD-19C but already appropriate for statistical analysis based on the theory of the scale-free nature of the citation network. Taken together, all these expanded datasets show much smoother trends when used to analyze global COVID-19 research. The results suggest that while CORD-19 exhibits a strong tilt toward recent and topically focused articles, the knowledge being explored to attack the pandemic encompasses a much longer time span and is very interdisciplinary. A question-answering system with such expanded scope of knowledge may perform better in understanding the literature and answering related questions. However, while CORD-19 appears to have topical coverage biases compared to the expanded sets, the collaboration patterns, especially in terms of team sizes and geographical distributions, are captured very well already in CORD-19 as the raw statistics and trends agree with those from larger datasets.

Project description:ObjectiveSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) emerged as a global pandemic in early 2020 with rapidly evolving approaches to diagnosing the clinical illness called coronavirus disease (COVID-19). The primary objective of this scoping review is to synthesize current research of the diagnostic accuracy of history, physical examination, routine laboratory tests, real-time reverse transcription-polymerase chain reaction (rRT-PCR), immunology tests, and computed tomography (CT) for the emergency department (ED) diagnosis of COVID-19. Secondary objectives included a synopsis of diagnostic biases likely with current COVID-19 research as well as corresponding implications of false-negative and false-positive results for clinicians and investigators.MethodsA Preferred Reporting Items for Systematic Reviews and Meta-Analyses-Scoping Review (PRISMA-ScR)-adherent synthesis of COVID-19 diagnostic accuracy through May 5, 2020, was conducted. The search strategy was designed by a medical librarian and included studies indexed by PubMed and Embase since January 2020.ResultsA total of 1,907 citations were screened for relevance. Patients without COVID-19 are rarely reported, so specificity and likelihood ratios were generally unavailable. Fever is the most common finding, while hyposmia and hypogeusia appear useful to rule in COVID-19. Cough is not consistently present. Lymphopenia is the mostly commonly reported laboratory abnormality and occurs in over 50% of COVID-19 patients. rRT-PCR is currently considered the COVID-19 criterion standard for most diagnostic studies, but a single test sensitivity ranges from 60% to 78%. Multiple reasons for false-negatives rRT-PCR exist, including sample site tested and disease stage during which sample was obtained. CT may increase COVID-19 sensitivity in conjunction with rRT-PCR, but guidelines for imaging patients most likely to benefit are emerging. IgM and IgG serology levels are undetectable in the first week of COVID-19, but sensitivity (range = 82% to 100%) and specificity (range = 87% to 100%) are promising. Whether detectable COVID-19 antibodies correspond to immunity remains unanswered. Current studies do not adhere to accepted diagnostic accuracy reporting standards and likely report significantly biased results if the same tests were to be applied to general ED populations with suspected COVID-19.ConclusionsWith the exception of fever and disorders of smell/taste, history and physical examination findings are unhelpful to distinguish COVID-19 from other infectious conditions that mimic SARS-CoV-2 like influenza. Routine laboratory tests are also nondiagnostic, although lymphopenia is a common finding and other abnormalities may predict severe disease. Although rRT-PCR is the current criterion standard, more inclusive consensus-based criteria will likely emerge because of the high false-negative rate of PCR tests. The role of serology and CT in ED assessments remains undefined.

Project description:BackgroundLarge sample sets of whole genome sequencing with deep coverage are being generated, however assembling datasets from different sources inevitably introduces batch effects. These batch effects are not well understood and can be due to changes in the sequencing protocol or bioinformatics tools used to process the data. No systematic algorithms or heuristics exist to detect and filter batch effects or remove associations impacted by batch effects in whole genome sequencing data.ResultsWe describe key quality metrics, provide a freely available software package to compute them, and demonstrate that identification of batch effects is aided by principal components analysis of these metrics. To mitigate batch effects, we developed new site-specific filters that identified and removed variants that falsely associated with the phenotype due to batch effect. These include filtering based on: a haplotype based genotype correction, a differential genotype quality test, and removing sites with missing genotype rate greater than 30% after setting genotypes with quality scores less than 20 to missing. This method removed 96.1% of unconfirmed genome-wide significant SNP associations and 97.6% of unconfirmed genome-wide significant indel associations. We performed analyses to demonstrate that: 1) These filters impacted variants known to be disease associated as 2 out of 16 confirmed associations in an AMD candidate SNP analysis were filtered, representing a reduction in power of 12.5%, 2) In the absence of batch effects, these filters removed only a small proportion of variants across the genome (type I error rate of 3%), and 3) in an independent dataset, the method removed 90.2% of unconfirmed genome-wide SNP associations and 89.8% of unconfirmed genome-wide indel associations.ConclusionsResearchers currently do not have effective tools to identify and mitigate batch effects in whole genome sequencing data. We developed and validated methods and filters to address this deficiency.

Dataset Information

Identifying and mitigating biases in EHR laboratory tests.

Publications

Identifying and mitigating biases in EHR laboratory tests.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets