Related Experiment Video
Updated: May 5, 2026

Implantation of Total Artificial Heart in Congenital Heart Disease
Published on: July 18, 2014
Algorithmic complexity stratification for congenital heart disease patients.
Jason Chami1, Geoff Strange2,3, David Baker4
1Sydney Medical School, The University of Sydney, Camperdown, Australia.
An algorithm can now automatically score the complexity of congenital heart disease (CHD) using diagnosis lists. This automates a process previously requiring manual input, enabling large-scale CHD research and improved health service planning.
Area of Science:
- Cardiology
- Medical Informatics
- Health Services Research
Background:
- Congenital Heart Disease (CHD) comprises diverse diagnoses requiring complexity stratification for clinical guidelines, health services planning, and research.
- Current methods for assigning CHD complexity scores necessitate manual specialist input, limiting scalability and data completeness in large databases.
- Existing scoring systems are prone to becoming outdated with revised clinical guidelines.
Purpose of the Study:
- To develop and validate an algorithm for automatically assigning complexity scores to Congenital Heart Disease patients based solely on their diagnosis lists.
- To enable efficient and consistent complexity scoring for large-scale Congenital Heart Disease datasets.
- To facilitate research into the management, outcomes, and burden of Congenital Heart Disease.
Main Methods:
- Utilized up-to-date European Society of Cardiology guidelines to construct an algorithm for CHD complexity scoring.
- Algorithmically assigned complexity scores using patient diagnosis lists.
- Validated algorithm performance against manual complexity scores assigned by two independent Congenital Heart Disease specialists.
Main Results:
- The algorithm achieved 96% accuracy when compared against specialist consensus on CHD complexity scores.
- Specialist agreement on complexity scores occurred in 68% of cases overall, and 79% for moderate or complex CHD.
- Algorithm limitations were identified in cases with non-specific diagnoses (e.g., unspecified septal defects) or procedure-dependent complexity.
Conclusions:
- An algorithm can successfully determine CHD complexity scores from diagnosis lists for a majority of patients.
- Automated complexity scoring can be implemented in large CHD databases, such as the Registry of the Congenital Heart Alliance of Australia and New Zealand.
- This approach will significantly enhance targeted research on CHD management, outcomes, and patient burden.
Related Concept Videos
Pulmonary Hypertension: Classification and Pathogenesis
There are various classifications for PH, each relating to different underlying causes and also...
Mitral Stenosis II: Clinical features and Diagnostic Tests
Heart Failure IV: Classification and Diagnostic Evaluation
Cardiomyopathy II: Dilated Cardiomyopathy
Cardiomyopathy III: Hypertrophic Cardiomyopathy
Cardiomyopathy V: Interprofessional Care

