ODVICE: An Ontology-Driven Visual Analytic Tool for Interactive Cohort Extraction

TL;DR

ODVICE is an ontology-guided visual tool that enhances cohort extraction from EHRs through systematic data augmentation, significantly improving predictive performance for medical research, especially in rare disease studies.

Contribution

The paper introduces ODVICE, a novel ontology-driven data augmentation framework with an interactive visual interface for improved cohort analysis in EHR data.

Findings

~30% improvement in AUC with ODVICE augmentation

Effective augmentation for rare disease cohorts

Outperforms existing data augmentation methods

Abstract

Increased availability of electronic health records (EHR) has enabled researchers to study various medical questions. Cohort selection for the hypothesis under investigation is one of the main consideration for EHR analysis. For uncommon diseases, cohorts extracted from EHRs contain very limited number of records - hampering the robustness of any analysis. Data augmentation methods have been successfully applied in other domains to address this issue mainly using simulated records. In this paper, we present ODVICE, a data augmentation framework that leverages the medical concept ontology to systematically augment records using a novel ontologically guided Monte-Carlo graph spanning algorithm. The tool allows end users to specify a small set of interactive controls to control the augmentation process. We analyze the importance of ODVICE by conducting studies on MIMIC-III dataset for two learning tasks. Our results demonstrate the predictive performance of ODVICE augmented cohorts, showing ~30% improvement in area under the curve (AUC) over the non-augmented dataset and other data augmentation strategies.