Mining Time-Stamped Electronic Health Records Using Referenced Sequences

TL;DR

This paper introduces a sequence-based method for creating time-interdependent variables from electronic health records, simplifying analysis of temporal relationships in medical data.

Contribution

It presents a novel technique using referenced sequences to generate clinically informed variables, streamlining the analysis process and enabling automation.

Findings

Sequences effectively capture patient medical history aspects.

Method applied to identify data anomalies and trends.

Created variables reveal temporal dependencies in treatment data.

Abstract

Electronic Health Records (EHRs) are typically stored as time-stamped encounter records. Observing temporal relationship between medical records is an integral part of interpreting the information. Hence, statistical analysis of EHRs requires that clinically informed time-interdependent analysis variables (TIAV) be created. Often, formulation and creation of these variables are iterative and requiring custom codes. We describe a technique of using sequences of time-referenced entities as the building blocks for TIAVs. These sequences represent different aspects of patient's medical history in a contiguous fashion. To illustrate the principles and applications of the method, we provide examples using Veterans Health Administration's research databases. In the first example, sequences representing medication exposure were used to assess patient selection criteria for a treatment comparative effectiveness study. In the second example, sequences of Charlson Comorbidity conditions and clinical settings of inpatient or outpatient were used to create variables with which data anomalies and trends were revealed. The third example demonstrated the creation of an analysis variable derived from the temporal dependency of medication exposure and comorbidity. Complex time-interdependent analysis variables can be created from the sequences with simple, reusable codes, hence enable unscripted or automation of TIAV creation.