High importance
Nov 7, 2026
This research could improve how patients with HHT are screened for brain issues, potentially leading to better monitoring and care. Patients and families may want to discuss these findings with their healthcare providers to understand what new screening options could be relevant for them.
The study aims to create a machine learning model that predicts the presence of brain arteriovenous malformations (bAVMs) in patients with hereditary hemorrhagic telangiectasia (HHT). This could help identify those who need closer monitoring for cerebrovascular issues.
A total of 142 HHT patients were studied. The models used for predicting bAVMs performed well, with one model (Logistic Regression) achieving a score indicating good predictive ability. However, when predicting overall cerebrovascular conditions, the models were less effective.
The researchers included patients diagnosed with HHT who had complete genetic testing and MRI screening from 2018 to 2026. Two main outcomes were looked at: the likelihood of finding bAVMs and the likelihood of detecting any cerebrovascular issues. Python and R programming languages were used for analysis.
This study is based on a specific patient group and the models' effectiveness needs further study to ensure they work well in larger, diverse populations. It's also important to note that the results need external validation before widespread use.
For your doctor:
PMID: 42998172
DOI: 10.1007/s00234-026-04253-9
BACKGROUND: Hereditary hemorrhagic telangiectasia (HHT) is an inherited vascular disorder characterized by telangiectasias and arteriovenous malformations (AVMs) in multiple organs. Although brain MRI screening is recommended in all patients with HHT, in many centers, this may be difficult to implement due to organizational constraints. The aim of this study was to develop a machine learning model to predict the presence of bAVMs and other cerebrovascular malformations in patients with HHT, with the goal of supporting risk stratification in centers where genotype information is already available and identifying patients who may benefit from closer and more conservative surveillance. METHODS: All patients with confirmed diagnosis of HHT, complete genetic work-up, and radiological screening (2018-2026) were included for the analysis. Two end points were defined: probability of detecting bAVMs, and probability of detecting any cerebrovascular findings. Analysis was performed using Python and R. RESULTS: A total of 142 patients with confirmed HHT (meeting ≥ 3 Curaçao criteria) were included. For bAVM prediction, both models showed good discrimination, with an AUC of 0.84 (95% CI: 0.73-0.94) for Logistic Regression (LR) and 0.85 (95% CI: 0.74-0.96) for Random Forest (RF). Despite the slightly higher AUC, RF showed lower specificity, PPV, and F1 score, higher sensitivity (0.73 vs. 0.69) and same NPV. LR also showed better calibration, with an intercept of -0.30 (95% CI: -1.38-0.78) and slope of 0.87 (95% CI: 0.34-1.40), compared with 1.39 (95% CI: -0.46-3.23) and 2.39 (95% CI: 0.64-4.15), respectively, for RF. In contrast, models predicting overall cerebrovascular malformations showed limited discrimination and poor calibration with both LR and RF. For bAVM prediction, LR identified deletion mutations, ENG, family history, ACVRL1, and truncated variants as the most influential features, while RF SHAP analysis highlighted ACVRL1, ENG, age, pulmonary AVMs, and family history. CONCLUSION: Effective risk stratification was achieved by the phenotype-specific bAVM model, supporting its potential applicability. Upon external validation this tool may enable an efficient allocation of screening strategies.