Prediction of hypertension and restenosis under guideline-directed management in aortic coarctation: development and validation of machine-learning models.

Authors

Abstract

Aortic coarctation (CoA) is a major cause of arterial hypertension in young individuals, with recurrence occurring in up to one-third of patients throughout life despite guideline-directed management. We conducted a development and validation study at a single centre in Berlin, Germany, utilising routinely collected electronic health records, cardiovascular magnetic resonance (CMR), and mid-/long-term follow-up data from 218 visits (160 individuals with CoA receiving standard of care, guideline-based management) collected between January 2014 and April 2022. Machine learning (ML) models (CatBoost, XGBoost, random forest, support vector classifiers, neural networks, logistic regression, and K-nearest neighbours) were developed to predict three endpoints: re-coarctation requiring intervention (CoA-I), aortic surgery (CoA-S) as a subset of CoA-I, and persistent arterial hypertension. The dataset was divided by random stratified split into a training set (n = 159; for model development with five-fold cross-validation), and a hold-out test set (n = 59; for out-of-sample validation). Stratification was based on sex, age, and CoA-I status. We included a final set of 38 clinically relevant features, encompassing baseline characteristics, medication intake, echocardiography, CMR, electrocardiography (ECG), and treatment decisions. ClinicalTrials.gov Identifier: NCT02591940. Tree-based and support vector classifier models performed best after Bayesian hyperparameter optimisation, yielding high performance in a stratified validation cohort: area under the receiver operating characteristic curve (ROC AUC) 0.90 ± 0.01 for CoA-I, 0.90 ± 0.01 for CoA-S, and 0.84 ± 0.01 for hypertension. Shapley Additive exPlanations (SHAP) highlighted peak Doppler gradient, time since index visit, and ventricular size indices as key predictors for CoA-I. In inverse-probability-weighted analyses, antihypertensive medication was associated with a lower CoA-I probability (-17.3%; 95% confidence interval [CI], -28.2 to -6.4; p = 0.002), with concordant propensity-score-matched findings. An open-access research interface (https://icm.dhzc.charite.de/calc_coa) incorporates treatment thresholds and personalised risk estimates from an updatable ML framework. These findings suggest that patient-specific multimodal ML-based risk estimates may complement guideline-based care by identifying patients at increased risk of CoA-I or persistent hypertension, with the potential to support more tailored follow-up and reduce lifetime exposure to brachiocephalic hypertension. In adjusted cohort-level analyses, antihypertensive medication was associated with a lower probability of CoA-I. This study was supported by the European Commission's Seventh Framework Programme (FP7, project ID 611232). M.K. acknowledges support within the Charité Digital Clinician Scientist Programme funded by DFG. M.K. and T.K. have received funding within the CHAIN project (Project ID: 101314833), supported by the European Union's EU4Health Programme. T.K. and M.K. acknowledge support within the Collaborative Research Centre SFB 1470, funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project ID 437531118. M.K. has received funding from the Bundesministerium für Forschung, Technologie und Raumfahrt (BMFTR, Federal Ministry of Research, Technology and Space), VADYS-ME, grant number 01EJ2406A.

Tags

Topics