Relational machine learning for electronic health record-driven phenotyping

Highlights

• We compared ILP to propositional machine learning approaches for EHR phenotyping.

• Training subject selection for machine learning was automated using ICD-9 codes.

• ILP out-performed propositional machine learning approaches in AUROC.

• Relational learning using ILP offers a viable approach to EHR-driven phenotyping.

Abstract

Objective

Electronic health records (EHR) offer medical and pharmacogenomics research unprecedented opportunities to identify and classify patients at risk. EHRs are collections of highly inter-dependent records that include biological, anatomical, physiological, and behavioral observations. They comprise a patient’s clinical phenome, where each patient has thousands of date-stamped records distributed across many relational tables. Development of EHR computer-based phenotyping algorithms require time and medical insight from clinical experts, who most often can only review a small patient subset representative of the total EHR records, to identify phenotype features. In this research we evaluate whether relational machine learning (ML) using inductive logic programming (ILP) can contribute to addressing these issues as a viable approach for EHR-based phenotyping.

Methods

Two relational learning ILP approaches and three well-known WEKA (Waikato Environment for Knowledge Analysis) implementations of non-relational approaches (PART, J48, and JRIP) were used to develop models for nine phenotypes. International Classification of Diseases, Ninth Revision (ICD-9) coded EHR data were used to select training cohorts for the development of each phenotypic model. Accuracy, precision, recall, F-Measure, and Area Under the Receiver Operating Characteristic (AUROC) curve statistics were measured for each phenotypic model based on independent manually verified test cohorts. A two-sided binomial distribution test (sign test) compared the five ML approaches across phenotypes for statistical significance.

Results

We developed an approach to automatically label training examples using ICD-9 diagnosis codes for the ML approaches being evaluated. Nine phenotypic models for each ML approach were evaluated, resulting in better overall model performance in AUROC using ILP when compared to PART (p = 0.039), J48 (p = 0.003) and JRIP (p = 0.003).

Discussion

ILP has the potential to improve phenotyping by independently delivering clinically expert interpretable rules for phenotype definitions, or intuitive phenotypes to assist experts.

Conclusion

Relational learning using ILP offers a viable approach to EHR-driven phenotyping.