Single center Automated, Multi-Source deeply Phenotyped Heart Transplant Registry as a template to build tailored data infrastructure
Patel, K.; Eager, T. N.; Ghobrial, M.; Moore, L. W.; Guha, A.; Martin, C.; Akay, M. H.; Loza, L.; Jones, S. L.; Gaber, A. O.; Bhimaraj, A.
Show abstract
BackgroundTraditional heart transplant registries often lack the granularity required for deep phenotyping and rely on labor-intensive manual abstraction. We describe the methodology and validation of a next-generation, automated, multi-source registry designed to address these limitations. MethodsUtilizing a High-Performance Computing environment, we integrated structured data from Epic data warehouses (Clarity and Caboodle), external molecular diagnostics, and verified UNOS survival records. A custom deterministic rule-based Natural Language Processing (NLP) engine was developed to extract echocardiographic measures, rejection grades, and vasculopathy scores from over 21,000 unstructured clinical reports. ResultsThe Houston Methodist J.C. Walter Jr. Transplant Center Precision Registry and Platform-Heart (TCPR-Heart) captures 1,687 heart transplants (1,636 patients) spanning the years 1984-2025. The TCPR-Heart comprises 1,054 transplants with active clinical follow-up: 555 transplants were extracted and abstracted from our modern electronic health record (EHR) in the decade since deployment, providing access to data throughout the patients course of heart transplant; 427 were legacy active transplants (transplanted pre-2016 with continued follow-up), and 72 were external transplants (transplanted elsewhere but followed at Methodist). Additionally, the registry houses a historic cohort of 633 transplants (last follow-up < June 2016) with limited variables. Automated deep phenotyping successfully generated longitudinal data trends across clinical domains, including immunosuppression strategies, rejection, immunologic HLA data, renal function, metabolic profiles, vasculopathy, graft function, hospitalization burden and survival information. ConclusionThis automated framework unifies clinical, administrative, and molecular data streams. By leveraging an automated, regularly updated registry, we established a scalable, high-fidelity data source as a foundation for further innovations and novel applications based on an expertly curated and validated data source.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Pilot Randomized Controlled Trial of de novo Belatacept-Based Immunosuppression in Lung Transplantation 94%
- Machine learning-supported interpretation of kidney graft elementary lesions in combination with clinical data 93%
- Predicting Post-Liver Transplant Outcomes in Patients with Acute-on-Chronic Liver Failure using Expert-Augmented Machine Learning 93%
Similar papers in this journal
- Prediction of donor heart acceptance for transplant and its clinical implications – results from the Donor Heart Study 96%
- Race, Sex and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart Failure 91%
- Diastolic Perfusion Pressure Predicts Response to Inotropes/Vasopressors and Benefit from Mechanical Circulatory Support in Cardiogenic Shock? 91%
Similar papers in this journal
- Spatial proteomics of human diabetic kidney disease, from health to class III 90%
- Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict rapid progression of diabetic kidney disease 89%
- Quantifying stem cell derived islet graft volume and composition with FDOPA positron emission tomography 88%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.