Estimating summary statistics for electronic health record laboratory data for use in high-throughput phenotyping algorithms

Abstract

We study the question of how to represent or summarize raw laboratory data taken from an electronic health record (EHR) using parametric model selection to reduce or cope with biases induced through clinical care. It has been previously demonstrated that the health care process (Hripcsak and Albers, 2012, 2013), as defined by measurement context (Hripcsak and Albers, 2013; Albers et al., 2012) and measurement patterns (Albers and Hripcsak, 2010, 2012), can influence how EHR data are distributed statistically (Kohane and Weber, 2013; Pivovarov et al., 2014). We construct an algorithm, PopKLD, which is based on information criterion model selection (Burnham and Anderson, 2002; Claeskens and Hjort, 2008), is intended to reduce and cope with health care process biases and to produce an intuitively understandable continuous summary. The PopKLD algorithm can be automated and is designed to be applicable in high-throughput settings; for example, the output of the PopKLD algorithm can be used as input for phenotyping algorithms. Moreover, we develop the PopKLD-CAT algorithm that transforms the continuous PopKLD summary into a categorical summary useful for applications that require categorical data such as topic modeling. We evaluate our methodology in two ways. First, we apply the method to laboratory data collected in two different health care contexts, primary versus intensive care. We show that the PopKLD preserves known physiologic features in the data that are lost when summarizing the data using more common laboratory data summaries such as mean and standard deviation. Second, for three disease-laboratory measurement pairs, we perform a phenotyping task: we use the PopKLD and PopKLD-CAT algorithms to define high and low values of the laboratory variable that are used for defining a disease state. We then compare the relationship between the PopKLD-CAT summary disease predictions and the same predictions using empirically estimated mean and standard deviation to a gold standard generated by clinical review of patient records. We find that the PopKLD laboratory data summary is substantially better at predicting disease state. The PopKLD or PopKLD-CAT algorithms are not meant to be used as phenotyping algorithms, but we use the phenotyping task to show what information can be gained when using a more informative laboratory data summary. In the process of evaluation our method we show that the different clinical contexts and laboratory measurements necessitate different statistical summaries. Similarly, leveraging the principle of maximum entropy we argue that while some laboratory data only have sufficient information to estimate a mean and standard deviation, other laboratory data captured in an EHR contain substantially more information than can be captured in higher-parameter models.

The emerging landscape of health research based on biobanks linked to electronic health records: Existing resources, statistical challenges, and potential opportunities

“…[61][62][63] Recent works propose phenotyping strategies to overcome hurdles using multiple data sources to more accurately ascertain disease status. [64][65][66][67][68][69][70][71][72] However, future work is needed to provide statistical methods for incorporating data of different types for phenome generation. For a detailed review of phenotyping procedures, see Bush et al 7 Figure S8 provides some examples of the types of structured and unstructured EHR information that can be used to construct phenotypes.…”

“…Recent works propose phenotyping strategies to overcome hurdles using multiple data sources to more accurately ascertain disease status . However, future work is needed to provide statistical methods for incorporating data of different types for phenome generation.…”

Healthcare Process Modeling to Phenotype Clinician Behaviors for Exploiting the Signal Gain of Clinical Expertise (HPM-ExpertSignals): Development and evaluation of a conceptual framework

“…Traditional predictive modeling can detect some environmental and system modifiers through latent factors, but HPM-ExpertSignals encourage explicit modeling of difficult-to-detect modifiers using a top-down modeling approach. 6 , 47 , 48 For example, our team has demonstrated the implicit identification of contextual factors and data-driven covariates for modeling laboratory data 47 and survival models of chronic kidney disease 48 for healthcare process biases and effects.…”

Automated Phenotyping Tool for Identifying Developmental Language Disorder Cases in Health Systems Data (APT-DLD): A New Research Algorithm for Deployment in Large-Scale Electronic Health Record Systems

“…The variability in the presence of SLP referrals and definitive diagnoses describes our diverse set of cases that met our definition for inclusion (DLD classification) and highlights the need for efficient identification of LDs (see Supplemental Material S3 ). Other recently developed EHR data mining algorithms employ natural language processing to automatically classify phenotypes using text recognition from medical notes and other clinical information ( Albers et al, 2018 ; Deferio et al, 2018 ; Wei et al, 2016 ). APT-DLD, however, is automated, is rule based, and does not depend on natural language processing or access to medical notes.…”