How and when informative visit processes can bias inference when using electronic health records data for clinical research

Inherent Bias in Electronic Health Records: A Scoping Review of Sources of Bias

Objectives

1.1Biases inherent in electronic health records (EHRs), and therefore in medical artificial intelligence (AI) models may significantly exacerbate health inequities and challenge the adoption of ethical and responsible AI in healthcare. Biases arise from multiple sources, some of which are not as documented in the literature. Biases are encoded in how the data has been collected and labeled, by implicit and unconscious biases of clinicians, or by the tools used for data processing. These biases and their encoding in healthcare records undermine the reliability of such data and bias clinical judgments and medical outcomes. Moreover, when healthcare records are used to build data-driven solutions, the biases are further exacerbated, resulting in systems that perpetuate biases and induce healthcare disparities. This literature scoping review aims to categorize the main sources of biases inherent in EHRs.

Methods

1.2We queried PubMed and Web of Science on January 19th, 2023, for peer-reviewed sources in English, published between 2016 and 2023, using the PRISMA approach to stepwise scoping of the literature. To select the papers that empirically analyze bias in EHR, from the initial yield of 430 papers, 27 duplicates were removed, and 403 studies were screened for eligibility. 196 articles were removed after the title and abstract screening, and 96 articles were excluded after the full-text review resulting in a final selection of 116 articles.

Results

1.3Systematic categorizations of diverse sources of bias are scarce in the literature, while the effects of separate studies are often convoluted and methodologically contestable. Our categorization of published empirical evidence identified the six main sources of bias: a) bias arising from past clinical trials; b) data-related biases arising from missing, incomplete information or poor labeling of data; human-related bias induced by c) implicit clinician bias, d) referral and admission bias; e) diagnosis or risk disparities bias and finally, (f) biases in machinery and algorithms.

Conclusions

1.4Machine learning and data-driven solutions can potentially transform healthcare delivery, but not without limitations. The core inputs in the systems (data and human factors) currently contain several sources of bias that are poorly documented and analyzed for remedies. The current evidence heavily focuses on data-related biases, while other sources are less often analyzed or anecdotal. However, these different sources of biases add to one another exponentially. Therefore, to understand the issues holistically we need to explore these diverse sources of bias. While racial biases in EHR have been often documented, other sources of biases have been less frequently investigated and documented (e.g. gender-related biases, sexual orientation discrimination, socially induced biases, and implicit, often unconscious, human-related cognitive biases). Moreover, some existing studies lack causal evidence, illustrating the different prevalences of disease across groups, which does not per se prove the causality. Our review shows that data-, human- and machine biases are prevalent in healthcare and they significantly impact healthcare outcomes and judgments and exacerbate disparities and differential treatment. Understanding how diverse biases affect AI systems and recommendations is critical. We suggest that researchers and medical personnel should develop safeguards and adopt data-driven solutions with a "bias-in-mind" approach. More empirical evidence is needed to tease out the effects of different sources of bias on health outcomes.

Biases in Electronic Health Records Data for Generating Real-World Evidence: An Overview

Electronic Health Records (EHR) are increasingly being perceived as a unique source of data for clinical research as they provide unprecedentedly large volumes of real-time data from real-world settings. In this review of the secondary uses of EHR, we identify the anticipated breadth of opportunities, pointing out the data deficiencies and potential biases that are likely to limit the search for true causal relationships. This paper provides a comprehensive overview of the types of biases that arise along the pathways that generate real-world evidence and the sources of these biases. We distinguish between two levels in the production of EHR data where biases are likely to arise: (i) at the healthcare system level, where the principal source of bias resides in access to, and provision of, medical care, and in the acquisition and documentation of medical and administrative data; and (ii) at the research level, where biases arise from the processes of extracting, analyzing, and interpreting these data. Due to the plethora of biases, mainly in the form of selection and information bias, we conclude with advising extreme caution about making causal inferences based on secondary uses of EHRs.

Sources of Disparities in Surveillance Mammography Performance and Risk-Guided Recommendations for Supplemental Breast Imaging: A Simulation Study

BACKGROUND

Surveillance mammography is recommended for all women with a history of breast cancer. Risk-guided surveillance incorporating advanced imaging modalities based on individual risk of a second cancer could improve cancer detection. However, personalized surveillance may also amplify disparities.

METHODS

In simulated populations using inputs from the Breast Cancer Surveillance Consortium (BCSC), we investigated race- and ethnicity-based disparities. Disparities were decomposed into those due to primary breast cancer and treatment characteristics, social determinants of health (SDOH) and differential error in second cancer ascertainment by modeling populations with or without variation across race and ethnicity in the distribution of these characteristics. We estimated effects of disparities on mammography performance and supplemental imaging recommendations stratified by race and ethnicity.

RESULTS

In simulated cohorts based on 65,446 BCSC surveillance mammograms, when only cancer characteristics varied by race and ethnicity, mammograms for Black women had lower sensitivity compared with the overall population (64.1% vs. 71.1%). Differences between Black women and the overall population were larger when both cancer characteristics and SDOH varied by race and ethnicity (53.8% vs. 71.1%). Basing supplemental imaging recommendations on high predicted second cancer risk resulted in less frequent recommendations for Hispanic (6.7%) and Asian/Pacific Islander women (6.4%) compared with the overall population (10.0%).

CONCLUSIONS

Variation in cancer characteristics and SDOH led to disparities in surveillance mammography performance and recommendations for supplemental imaging.

IMPACT

Risk-guided surveillance imaging may exacerbate disparities. Decision-makers should consider implications for equity in cancer outcomes resulting from implementing risk-guided screening programs. See related In the Spotlight, p. 1479.

Statistical Considerations on the Use of RWD/RWE for Oncology Drug Approvals: Overview and Lessons Learned

Despite increasing utilization of real-world data (RWD)/real-world evidence (RWE) in regulatory submissions, their application to oncology drug approvals has seen limited success. Real-world data is most commonly summarized as a benchmark control for a single arm study or used to augment the concurrent control in a randomized clinical trial (RCT). While there has been substantial research on usage of RWD/RWE, our goal is to provide a comprehensive overview of their use in oncology drug approval submissions to inform future RWD/RWE study design. We will review examples of applications and summarize the strengths and weaknesses of each example identified by regulatory agencies. A few noteworthy case studies will be reviewed in detail. Operational aspects of RWD/RWE study design/analysis will be also discussed.

Missing data matter: an empirical evaluation of the impacts of missing EHR data in comparative effectiveness research

OBJECTIVES

The impacts of missing data in comparative effectiveness research (CER) using electronic health records (EHRs) may vary depending on the type and pattern of missing data. In this study, we aimed to quantify these impacts and compare the performance of different imputation methods.

MATERIALS AND METHODS

We conducted an empirical (simulation) study to quantify the bias and power loss in estimating treatment effects in CER using EHR data. We considered various missing scenarios and used the propensity scores to control for confounding. We compared the performance of the multiple imputation and spline smoothing methods to handle missing data.

RESULTS

When missing data depended on the stochastic progression of disease and medical practice patterns, the spline smoothing method produced results that were close to those obtained when there were no missing data. Compared to multiple imputation, the spline smoothing generally performed similarly or better, with smaller estimation bias and less power loss. The multiple imputation can still reduce study bias and power loss in some restrictive scenarios, eg, when missing data did not depend on the stochastic process of disease progression.

DISCUSSION AND CONCLUSION

Missing data in EHRs could lead to biased estimates of treatment effects and false negative findings in CER even after missing data were imputed. It is important to leverage the temporal information of disease trajectory to impute missing values when using EHRs as a data resource for CER and to consider the missing rate and the effect size when choosing an imputation method.

Estimating individualized treatment rules in longitudinal studies with covariate-driven observation times

The sequential treatment decisions made by physicians to treat chronic diseases are formalized in the statistical literature as dynamic treatment regimes. To date, methods for dynamic treatment regimes have been developed under the assumption that observation times, that is, treatment and outcome monitoring times, are determined by study investigators. That assumption is often not satisfied in electronic health records data in which the outcome, the observation times, and the treatment mechanism are associated with patients' characteristics. The treatment and observation processes can lead to spurious associations between the treatment of interest and the outcome to be optimized under the dynamic treatment regime if not adequately considered in the analysis. We address these associations by incorporating two inverse weights that are functions of a patient's covariates into dynamic weighted ordinary least squares to develop optimal single stage dynamic treatment regimes, known as individualized treatment rules. We show empirically that our methodology yields consistent, multiply robust estimators. In a cohort of new users of antidepressant drugs from the United Kingdom's Clinical Practice Research Datalink, the proposed method is used to develop an optimal treatment rule that chooses between two antidepressants to optimize a utility function related to the change in body mass index.

Estimation of marginal structural models under irregular visits and unmeasured confounder: calibrated inverse probability weights

Clinical information collected in electronic health records (EHRs) is becoming an essential source to emulate randomized experiments. Since patients do not interact with the healthcare system at random, the longitudinal information in large observational databases must account for irregular visits. Moreover, we need to also account for subject-specific unmeasured confounders which may act as a common cause for treatment assignment mechanism (e.g. glucose-lowering medications) while also influencing the outcome (e.g. Hemoglobin A1c). We used the calibration of longitudinal weights to improve the finite sample properties and to account for subject-specific unmeasured confounders. A Monte Carlo simulation study is conducted to evaluate the performance of calibrated inverse probability estimators using time-dependent treatment assignment and irregular visits with subject-specific unmeasured confounders. The simulation study showed that the longitudinal weights with calibrated restrictions improved the finite sample bias when compared to the stabilized weights. The application of the calibrated weights is demonstrated using the exposure of glucose lowering medications and the longitudinal outcome of Hemoglobin A1c. Our results support the effectiveness of glucose lowering medications in reducing Hemoglobin A1c among type II diabetes patients with elevated glycemic index ([Formula: see text]) using stabilized and calibrated weights.

Defining measures of kidney function in observational studies using routine health care data: methodological and reporting considerations

The availability of electronic health records and access to a large number of routine measurements of serum creatinine and urinary albumin enhance the possibilities for epidemiologic research in kidney disease. However, the frequency of health care use and laboratory testing is determined by health status and indication, imposing certain challenges when identifying patients with kidney injury or disease, when using markers of kidney function as covariates, or when evaluating kidney outcomes. Depending on the specific research question, this may influence the interpretation, generalizability, and/or validity of study results. This review illustrates the heterogeneity of working definitions of kidney disease in the scientific literature and discusses advantages and limitations of the most commonly used approaches using 3 examples. We summarize ways to identify and overcome possible biases and conclude by proposing a framework for reporting definitions of exposures and outcomes in studies of kidney disease using routinely collected health care data.

Association of Disparities in Family History and Family Cancer History in the Electronic Health Record With Sex, Race, Hispanic or Latino Ethnicity, and Language Preference in 2 Large US Health Care Systems

IMPORTANCE

Clinical decision support (CDS) algorithms are increasingly being implemented in health care systems to identify patients for specialty care. However, systematic differences in missingness of electronic health record (EHR) data may lead to disparities in identification by CDS algorithms.

OBJECTIVE

To examine the availability and comprehensiveness of cancer family history information (FHI) in patients' EHRs by sex, race, Hispanic or Latino ethnicity, and language preference in 2 large health care systems in 2021.

DESIGN, SETTING, AND PARTICIPANTS

This retrospective EHR quality improvement study used EHR data from 2 health care systems: University of Utah Health (UHealth) and NYU Langone Health (NYULH). Participants included patients aged 25 to 60 years who had a primary care appointment in the previous 3 years. Data were collected or abstracted from the EHR from December 10, 2020, to October 31, 2021, and analyzed from June 15 to October 31, 2021.

EXPOSURES

Prior collection of cancer FHI in primary care settings.

MAIN OUTCOMES AND MEASURES

Availability was defined as having any FHI and any cancer FHI in the EHR and was examined at the patient level. Comprehensiveness was defined as whether a cancer family history observation in the EHR specified the type of cancer diagnosed in a family member, the relationship of the family member to the patient, and the age at onset for the family member and was examined at the observation level.

RESULTS

Among 144 484 patients in the UHealth system, 53.6% were women; 74.4% were non-Hispanic or non-Latino and 67.6% were White; and 83.0% had an English language preference. Among 377 621 patients in the NYULH system, 55.3% were women; 63.2% were non-Hispanic or non-Latino, and 55.3% were White; and 89.9% had an English language preference. Patients from historically medically undeserved groups-specifically, Black vs White patients (UHealth: 17.3% [95% CI, 16.1%-18.6%] vs 42.8% [95% CI, 42.5%-43.1%]; NYULH: 24.4% [95% CI, 24.0%-24.8%] vs 33.8% [95% CI, 33.6%-34.0%]), Hispanic or Latino vs non-Hispanic or non-Latino patients (UHealth: 27.2% [95% CI, 26.5%-27.8%] vs 40.2% [95% CI, 39.9%-40.5%]; NYULH: 24.4% [95% CI, 24.1%-24.7%] vs 31.6% [95% CI, 31.4%-31.8%]), Spanish-speaking vs English-speaking patients (UHealth: 18.4% [95% CI, 17.2%-19.1%] vs 40.0% [95% CI, 39.7%-40.3%]; NYULH: 15.1% [95% CI, 14.6%-15.6%] vs 31.1% [95% CI, 30.9%-31.2%), and men vs women (UHealth: 30.8% [95% CI, 30.4%-31.2%] vs 43.0% [95% CI, 42.6%-43.3%]; NYULH: 23.1% [95% CI, 22.9%-23.3%] vs 34.9% [95% CI, 34.7%-35.1%])-had significantly lower availability and comprehensiveness of cancer FHI (P < .001).

CONCLUSIONS AND RELEVANCE

These findings suggest that systematic differences in the availability and comprehensiveness of FHI in the EHR may introduce informative presence bias as inputs to CDS algorithms. The observed differences may also exacerbate disparities for medically underserved groups. System-, clinician-, and patient-level efforts are needed to improve the collection of FHI.

Electronic medical records and biobanking

Biosample preservation for future research is a fundamental component of translational medicine. At the same time, the value of stored biosamples is largely determined by the presence of related clinical data and other information. Electronic medical records are a unique source of a large amount of information received over a long period of time. In this regard, genetic and other types of data obtained from the biosample analysis can be associated with phenotypic and other types of information stored in electronic medical records, which pushes the boundaries in large-scale genetic research and improves healthcare. The aim of this review was to analyze the literature on the potential of combining electronic medical records and biobank databases in research and clinical practice.

On the Nature of Informative Presence Bias in Analyses of Electronic Health Records

Electronic health records (EHRs) offer unprecedented opportunities to answer epidemiologic questions. However, unlike in ordinary cohort studies or randomized trials, EHR data are collected somewhat idiosyncratically. In particular, patients who have more contact with the medical system have more opportunities to receive diagnoses, which are then recorded in their EHRs. The goal of this article is to shed light on the nature and scope of this phenomenon, known as informative presence, which can bias estimates of associations. We show how this can be characterized as an instance of misclassification bias. As a consequence, we show 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. Additionally, where previous work has considered only underdiagnosis, investigators are often concerned about overdiagnosis; we show how this changes the settings in which bias manifests. We report on a comprehensive series of simulations to shed light on when to expect informative presence bias, how it can be mitigated in some cases, and cases in which new methods need to be developed.

OUP accepted manuscript

OBJECTIVE

Electronic health record (EHR)-derived data are extensively used in health research. However, the pattern of patient interaction with the healthcare system can result in informative presence bias if those who have poorer health have more data recorded than healthier patients. We aimed to determine how informative presence affects bias across multiple scenarios informed by real-world healthcare utilization patterns.

MATERIALS AND METHODS

We conducted an analysis of EHR data from a pediatric healthcare system as well as simulation studies to characterize conditions under which informative presence bias is likely to occur. This analysis extends prior work by examining a variety of scenarios for the relationship between a biomarker and a health event of interest and the healthcare visit process.

RESULTS

Using biomarker values gathered at both informative and noninformative visits when estimating the effect of the biomarker on the event of interest resulted in minimal bias when the biomarker was relatively stable over time but produced substantial bias when the biomarker was more volatile. Adjusting analyses for the number of prior visits within a fixed look-back window was able to reduce but not eliminate this bias.

DISCUSSION

These results suggest that bias may arise frequently in commonly encountered scenarios and may not be eliminated by adjusting for prior visit intensity.

CONCLUSION

Depending on the context, the estimated effect from analyses using data from all visits available may diverge from the true effect. Sensitivity analyses using only visits likely to be informative or noninformative based on visit type may aid in the assessment of the magnitude of potential bias.

Developing and evaluating a pediatric asthma severity computable phenotype derived from electronic health records

BACKGROUND

Extensive data available in electronic health records (EHRs) have the potential to improve asthma care and understanding of factors influencing asthma outcomes. However, this work can be accomplished only when the EHR data allow for accurate measures of severity, which at present are complex and inconsistent.

OBJECTIVE

Our aims were to create and evaluate a standardized pediatric asthma severity phenotype based in clinical asthma guidelines for use in EHR-based health initiatives and studies and also to examine the presence and absence of these data in relation to patient characteristics.

METHODS

We developed an asthma severity computable phenotype and compared the concordance of different severity components contributing to the phenotype to trends in the literature. We used multivariable logistic regression to assess the presence of EHR data relevant to asthma severity.

RESULTS

The asthma severity computable phenotype performs as expected in comparison with national statistics and the literature. Severity classification for a child is maximized when based on the long-term medication regimen component and minimized when based only on the symptom data component. Use of the severity phenotype results in better, clinically grounded classification. Children for whom severity could be ascertained from these EHR data were more likely to be seen for asthma in the outpatient setting and less likely to be older or Hispanic. Black children were less likely to have lung function testing data present.

CONCLUSION

We developed a pragmatic computable phenotype for pediatric asthma severity that is transportable to other EHRs.

Concussion and Risk of Chronic Medical and Behavioral Health Comorbidities

While chronic neurological effects from concussion have been studied widely, little is known about possible links between concussion and long-term medical and behavioral comorbidities. We performed a retrospective cohort study of 9205 adult patients with concussion, matched to non-concussion controls from a hospital-based electronic medical registry. Patients with comorbidities before the index visit were excluded. Behavioral and medical comorbidities were defined by International Classification of Diseases, Ninth and Tenth Revision codes. Groups were followed for up to 10 years to identify comorbidity incidence after a concussion. Cox proportional hazards models were used to calculate associations between concussion and comorbidities after multi-variable adjustment. Patients with concussion were 57% male (median age: 31; interquartile range [IQR] = 23-48 years) at enrollment with a median follow-up time of 6.1 years (IQR = 4.2-9.1) and well-matched to healthy controls. Most (83%) concussions were evaluated in outpatient settings (5% inpatient). During follow-up, we found significantly higher risks of cardiovascular risks developing including hypertension (hazard ratio [HR] = 1.7, 95% confidence interval [CI]: 1.5-1.9), obesity (HR = 1.7, 95% CI: 1.3-2.0), and diabetes mellitus (HR = 1.8, 95% CI: 1.4-2.3) in the concussion group compared with controls. Similarly, psychiatric and neurological disorders such as depression (HR = 3.0, 95% CI: 2.6-3.5), psychosis (HR = 6.0, 95% CI: 4.2-8.6), stroke (HR = 2.1 95% CI: 1.5-2.9), and epilepsy (HR = 4.4, 95% CI: 3.2-5.9) were higher in the concussion group. Most comorbidities developed less than five years post-concussion. The risks for post-concussion comorbidities were also higher in patients under 40 years old compared with controls. Patients with concussion demonstrated an increased risk of development of medical and behavioral health comorbidities. Prospective studies are warranted to better describe the burden of long-term comorbidities in patients with concussion.

Informative presence and observation in routine health data: A review of methodology for clinical risk prediction

Objective

Informative presence (IP) is the phenomenon whereby the presence or absence of patient data is potentially informative with respect to their health condition, with informative observation (IO) being the longitudinal equivalent. These phenomena predominantly exist within routinely collected healthcare data, in which data collection is driven by the clinical requirements of patients and clinicians. The extent to which IP and IO are considered when using such data to develop clinical prediction models (CPMs) is unknown, as is the existing methodology aiming at handling these issues. This review aims to synthesize such existing methodology, thereby helping identify an agenda for future methodological work.

Materials and Methods

A systematic literature search was conducted by 2 independent reviewers using prespecified keywords.

Results

Thirty-six articles were included. We categorized the methods presented within as derived predictors (including some representation of the measurement process as a predictor in the model), modeling under IP, and latent structures. Including missing indicators or summary measures as predictors is the most commonly presented approach amongst the included studies (24 of 36 articles).

Discussion

This is the first review to collate the literature in this area under a prediction framework. A considerable body relevant of literature exists, and we present ways in which the described methods could be developed further. Guidance is required for specifying the conditions under which each method should be used to enable applied prediction modelers to use these methods.

Conclusions

A growing recognition of IP and IO exists within the literature, and methodology is increasingly becoming available to leverage these phenomena for prediction purposes. IP and IO should be approached differently in a prediction context than when the primary goal is explanation. The work included in this review has demonstrated theoretical and empirical benefits of incorporating IP and IO, and therefore we recommend that applied health researchers consider incorporating these methods in their work.

Can Electronic Health Records Validly Estimate the Effects of Health System Interventions Aimed at Controlling Body Weight?

OBJECTIVE

This study aimed to compare weight collected at clinics and recorded in the electronic health record (EHR) with primary study-collected trial weights to assess the validity of using EHR data in future pragmatic weight loss or weight gain prevention trials.

METHODS

For both the Track and Shape obesity intervention randomized trials, clinic EHR weight data were compared with primary trial weight data over the same time period. In analyzing the EHR weights, intervention effects were estimated on the primary outcome of weight (in kilograms) with EHR data, using linear mixed effects models.

RESULTS

EHR weight measurements were higher on average and more variable than trial weight measurements. The mean difference and 95% CI were similar at all time points between the estimates using EHR and study-collected weights.

CONCLUSIONS

The results of this study can be used to help guide the planning of future pragmatic weight-related trials. This study provides evidence that body weight measurements abstracted from the EHR can provide valid, efficient, and cost-effective data to estimate treatment effects from randomized clinical weight loss and weight management trials. However, care should be taken to properly understand the data-generating process and any mechanisms that may affect the validity of these estimates.

Five analytic challenges in working with electronic health records data to support clinical trials with some solutions

Electronic health records data are becoming a key data resource in clinical research. Owing to issues of data efficiency, electronic health records data are being used for clinical trials. This includes both large-scale pragmatic trails and smaller—more focused—point-of-care trials. While electronic health records data open up a number of scientific opportunities, they also present a number of analytic challenges. This article discusses five particular challenges related to organizing electronic health records data for analytic purposes. These are as follows: (1) data are not organized for research purposes, (2) data are both densely and irregularly observed, (3) we don’t have all data elements we may want or need, (4) data are both cross-sectional and longitudinal, and (5) data may be informatively observed. While laying out these challenges, the article notes how many of these challenges can be addressed by careful and thoughtful study design as well as by integration of clinicians and informaticians into the analytic team.