Prediction of major outcomes in patients with malignant hypertension using machine learning : a report from the West Birmingham malignant hypertension registry
Argyris, Antonios A Ishiguchi, Hironori Chen, Yang Zheng, Yalin Shantsila, Alena Shantsila, Eduard Beevers, D Gareth Lip, Gregory Y H
Argyris, Antonios A
Ishiguchi, Hironori
Chen, Yang
Zheng, Yalin
Shantsila, Alena
Shantsila, Eduard
Beevers, D Gareth
Lip, Gregory Y H
Citations
Altmetric:
Affiliation
University of Liverpool; Sandwell and West Birmingham NHS Trust; Aalborg University; Medical University of Bialystok
Other Contributors
Publication date
2025-04-18
Subject
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Background: Malignant hypertension (MHT) is a rare, yet severe condition with high morbidity and mortality. We aimed to assess the potential of machine learning (ML) algorithms in forecasting prognostic outcomes in MHT patients. Methods: Data from the West Birmingham MHT Registry were used. We evaluated the efficacy of 9 ML algorithms, CatBoost, Decision Tree (DT), Light-Gradient Boosting Machine (LightGBM), K-Nearest Neighbours (KNN), Logistic Regression (LR), Multi-Layer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM) and XGBoost in predicting a composite outcome of all-cause mortality/dialysis. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) and F1 score. SHapley Additive exPlanations values were employed to quantify the importance of each feature. Results: The cohort comprised 385 individuals with MHT (mean age 48 ± 13 years, 66% male). During a median follow-up of 11 (interquartile range: 3-18) years, 282 patients (73%) experienced the composite outcome. Among 24 demographic and clinical variables, 16 were selected into the ML models. The SVM, LR, and MLP models exhibited robust predictive performance, achieving AUCs of .81 (95% CI: .70-.90), .82 (95% CI: .71-.92) and .81 (95% CI: .71-.90), respectively. Furthermore, these models demonstrated high F1 scores (SVM: .75, LR: .80. MLP: .75). Age, smoking, follow-up systolic blood pressure, and baseline creatinine were commonly identified as primary prognostic features in both SVM and LR models. Conclusions: The application of ML algorithms facilitates effective prediction of prognostic outcomes in MHT patients, illustrating their potential utility in clinical decision-making through more targeted risk stratification and individualised patient care.
Citation
Argyris AA, Ishiguchi H, Chen Y, Zheng Y, Shantsila A, Shantsila E, Beevers DG, Lip GYH. Prediction of major outcomes in patients with malignant hypertension using machine learning: A report from the West Birmingham malignant hypertension registry. Eur J Clin Invest. 2025 Apr 18:e70052. doi: 10.1111/eci.70052. Epub ahead of print
Type
Article