Dataset Information

Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

ABSTRACT:

Background

In electronic health records, patterns of missing laboratory test results could capture patients' course of disease as well as reflect clinician's concerns or worries for possible conditions. These patterns are often understudied and overlooked. This study aims to identify informative patterns of missingness among laboratory data collected across 15 healthcare system sites in three countries for COVID-19 inpatients.

Methods

We collected and analyzed demographic, diagnosis, and laboratory data for 69,939 patients with positive COVID-19 PCR tests across three countries from 1 January 2020 through 30 September 2021. We analyzed missing laboratory measurements across sites, missingness stratification by demographic variables, temporal trends of missingness, correlations between labs based on missingness indicators over time, and clustering of groups of labs based on their missingness/ordering pattern.

Results

With these analyses, we identified mapping issues faced in seven out of 15 sites. We also identified nuances in data collection and variable definition for the various sites. Temporal trend analyses may support the use of laboratory test result missingness patterns in identifying severe COVID-19 patients. Lastly, using missingness patterns, we determined relationships between various labs that reflect clinical behaviors.

Conclusion

In this work, we use computational approaches to relate missingness patterns to hospital treatment capacity and highlight the heterogeneity of looking at COVID-19 over time and at multiple sites, where there might be different phases, policies, etc. Changes in missingness could suggest a change in a patient's condition, and patterns of missingness among laboratory measurements could potentially identify clinical outcomes. This allows sites to consider missing data as informative to analyses and help researchers identify which sites are better poised to study particular questions.

SUBMITTER: Tan ALM

PROVIDER: S-EPMC10849195 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

Tan Amelia L M ALM Getzen Emily J EJ Hutch Meghan R MR Strasser Zachary H ZH Gutiérrez-Sacristán Alba A Le Trang T TT Dagliati Arianna A Morris Michele M Hanauer David A DA Moal Bertrand B Bonzel Clara-Lea CL Yuan William W Chiudinelli Lorenzo L Das Priam P Zhang Harrison G HG Aronow Bruce J BJ Avillach Paul P Brat Gabriel A GA Cai Tianxi T Hong Chuan C La Cava William G WG Hooi Will Loh He H Luo Yuan Y Murphy Shawn N SN Yuan Hgiam Kee K Omenn Gilbert S GS Patel Lav P LP Jebathilagam Samayamuthu Malarkodi M Shriver Emily R ER Shakeri Hossein Abad Zahra Z Tan Byorn W L BWL Visweswaran Shyam S Wang Xuan X Weber Griffin M GM Xia Zongqi Z Verdy Bertrand B Long Qi Q Mowery Danielle L DL Holmes John H JH

Journal of biomedical informatics 20230203

<h4>Background</h4>In electronic health records, patterns of missing laboratory test results could capture patients' course of disease as well as reflect clinician's concerns or worries for possible conditions. These patterns are often understudied and overlooked. This study aims to identify informative patterns of missingness among laboratory data collected across 15 healthcare system sites in three countries for COVID-19 inpatients.<h4>Methods</h4>We collected and analyzed demographic, diagn ...[more]

PMID: 36738870

Similar Datasets

Project description:BackgroundMissing data in electronic health records are highly prevalent and result in analytical concerns such as heterogeneous sources of bias and loss of statistical power. One simple analytic method for addressing missing or unknown covariate values is to treat missingness for a particular variable as a category onto itself, which we refer to as the missing indicator method. For cross-sectional analyses, recent work suggested that there was minimal benefit to the missing indicator method; however, it is unclear how this approach performs in the setting of longitudinal data, in which correlation among clustered repeated measures may be leveraged for potentially improved model performance.objectivesThis study aims to conduct a simulation study to evaluate whether the missing indicator method improved model performance and imputation accuracy for longitudinal data mimicking an application of developing a clinical prediction model for falls in older adults based on electronic health record data.MethodsWe simulated a longitudinal binary outcome using mixed effects logistic regression that emulated a falls assessment at annual follow-up visits. Using multivariate imputation by chained equations, we simulated time-invariant predictors such as sex and medical history, as well as dynamic predictors such as physical function, BMI, and medication use. We induced missing data in predictors under scenarios that had both random (missing at random) and dependent missingness (missing not at random). We evaluated aggregate performance using the area under the receiver operating characteristic curve (AUROC) for models with and with no missing indicators as predictors, as well as complete case analysis, across simulation replicates. We evaluated imputation quality using normalized root-mean-square error for continuous variables and percent falsely classified for categorical variables.ResultsIndependent of the mechanism used to simulate missing data (missing at random or missing not at random), overall model performance via AUROC was similar regardless of whether missing indicators were included in the model. The root-mean-square error and percent falsely classified measures were similar for models including missing indicators versus those with no missing indicators. Model performance and imputation quality were similar regardless of whether the outcome was related to missingness. Imputation with or with no missing indicators had similar mean values of AUROC compared with complete case analysis, although complete case analysis had the largest range of values.ConclusionsThe results of this study suggest that the inclusion of missing indicators in longitudinal data modeling neither improves nor worsens overall performance or imputation accuracy. Future research is needed to address whether the inclusion of missing indicators is useful in prediction modeling with longitudinal data in different settings, such as high dimensional data analysis.

Dataset Information

Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

Background

Methods

Results

Conclusion

Publications

Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets