Related Experiment Video
Updated: Aug 12, 2025

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
Developing an Actionable Taxonomy of Persistent Hypertension Using Electronic Health Records
Yuan Lu1,2, Cindy Xinxin Du2, Hazar Khidir3
1Center for Outcomes Research and Evaluation, Yale New Haven Hospital, CT (Y.L., C.C., S.M., E.S.S., H.M.K.).
Researchers developed a new way to classify patients with persistent hypertension using electronic health records. This taxonomy identifies reasons for uncontrolled blood pressure, enabling targeted interventions.
Area of Science:
- Cardiology
- Health Informatics
- Clinical Research
Background:
- Persistent hypertension management is evolving with digital health data.
- Electronic health records (EHRs) offer opportunities for novel patient stratification.
- Defining persistent hypertension requires consistent, high blood pressure readings over time.
Purpose of the Study:
- To create an actionable taxonomy for classifying patients with persistent hypertension.
- To leverage EHR data for stratifying patients based on hypertension persistence.
- To identify contributing factors to uncontrolled blood pressure in a patient cohort.
Main Methods:
- Qualitative content analysis of clinician notes within EHRs.
- Systematic, inductive approach to data abstraction and analysis.
- Analysis of 200 randomly selected patient records from 1664 eligible cases.
Main Results:
- Identified 3 domains contributing to hypertension persistence: non-intensification of treatment, non-implementation of prescribed treatment, and non-response to treatment.
- Saturation reached with 115 patients (mean age 66.0 years, 54.8% female).
- Patient demographics included White (52.2%), Black (30.4%), and Hispanic (13.9%) individuals.
Conclusions:
- A novel, actionable taxonomy for persistent hypertension classification was developed using EHR data.
- This taxonomy categorizes patients by the root causes of their uncontrolled blood pressure.
- The identified categories can be automated for targeted clinical interventions.
More Related Videos
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
05:03Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
Published on: December 11, 2019
Related Concept Videos
Hypertension III: Clinical Manifestations and Diagnostic Studies
Hypertension I: Introduction
Hypertension and Regulation of Blood Pressure
Hypertension V: Nursing Management
Errors occurring during blood pressure monitoring
Several factors...
Hypertension II: Pathophysiology