Related Experiment Video
Updated: Jan 16, 2026
A Pipeline to Characterize Structural Heart Defects in the Fetal Mouse
Published on: December 16, 2022
Automated phenotyping of congenital heart disease for dynamic patient aggregation and outcome reporting
Shuhei Toba1,2,3, Taylor M Smith1,2, Francesca Sperotto1,2
1Department of Cardiology, Boston Children's Hospital, Boston, MA 02115, United States.
Insights
This study developed an accurate and efficient method to determine congenital heart defect phenotypes using diagnostic and surgical codes. This approach aids in research, quality improvement, and clinical decision-making for congenital heart patients.
Area of Science:
- Cardiology
- Medical Informatics
- Computational Biology
Background:
- Accurate patient characterization is crucial for congenital heart disease (CHD) research and clinical care.
- Existing methods for phenotyping CHD patients can be labor-intensive and may lack comprehensive data integration.
Purpose of the Study:
- To develop and validate an automated approach for computing detailed CHD phenotypes from existing diagnostic and surgical codes.
- To assess the accuracy and efficiency of this computational method in a large patient cohort.
Main Methods:
- Extracted diagnostic and procedural codes for over 161,000 patients from 1981-2020.
- Developed a computational pipeline to map codes, compute parent anatomy, and identify subcategories and co-variate findings.
- Validated the algorithm's accuracy against clinical documentation for 500 patients.
Main Results:
- Successfully assigned phenotypes for 52% of patients with CHD.
- Achieved high agreement (96.4%) between algorithmic assignments and clinical expert adjudication.
- Identified definitional differences as the primary source of disagreement.
Conclusions:
- Automated computation of detailed CHD phenotypes from codes is feasible with high accuracy and efficiency.
- This framework can support the development of tools for interactive outcomes reporting and clinical decision support in CHD care.
Objectives:
Accurate characterization of patients with congenital heart disease is fundamental to research, outcomes reporting, quality improvement, and clinical decision-making. Here we present an approach to computing the anatomy of patients with congenital heart disease based on the whole of their diagnostic and surgical codes.
Materials And Methods:
All diagnostic and procedure codes for patients cared for between 1981 and 2020 at Boston Children's Hospital were extracted from a database containing diagnostic codes from echocardiograms, and procedural codes from surgical and catheterization procedures. The pipeline sequentially (1) mapped each of the 7500 native codes to algorithm codes; (2) computed the parent anatomy for each study using a pre-defined hierarchy; (3) computed the parent anatomy for the patient, based on highest ranking parent anatomy; and (4) computed the subcategories and mandatory co-variate findings for each patient. Thereafter, diagnostic accuracy of 500 unseen patients was adjudicated against clinical documentation by clinical experts.
Results:
A total of 514 541 echocardiograms on 161 735 patients were available for this study. Phenotypes of congenital cardiac diseases were assigned in 84 285 patients (52%), and the remainder were computed to have normal anatomy. Clinicians agreed with algorithm assignments in 96.4% (482 of 500 patients), with disagreements most often representing definitional differences. An interactive dashboard enabled by the output of this algorithm is presented.
Conclusions:
The computation of detailed congenital heart defect phenotypes from raw diagnostic and procedure codes is possible with a high degree of accuracy and efficiency. This framework may enable tools to support interactive outcomes reporting and clinical decision support.
Related Concept Videos
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy