Дослідження зрозуміло

Назад до стрічки
PubMed

Висока важливість

7 лист. 2026 р.

An approach using machine learning for MRI screening of brain arteriovenous malformations in hereditary haemorrhagic telangiectasia.

Відкрити першоджерело

Чому це важливо

This research has the potential to enhance how patients with HHT are screened for brain-related issues, which could lead to better monitoring and care. Patients and their families may wish to discuss these findings with their healthcare providers to explore new screening options that may be relevant.

Мета

The study aims to develop a machine learning model that predicts the likelihood of brain arteriovenous malformations (bAVMs) in patients with hereditary haemorrhagic telangiectasia (HHT). This could assist in identifying individuals who may require more careful monitoring for cerebrovascular problems.

Результати

A total of 142 patients with HHT were analysed. The predictive models for bAVMs performed well, with one model (Logistic Regression) achieving a score that indicated strong predictive ability. However, the models were less effective when it came to predicting overall cerebrovascular conditions.

Методи

The researchers included patients diagnosed with HHT who underwent complete genetic testing and MRI screening between 2018 and 2026. They focused on two main outcomes: the chances of discovering bAVMs and the likelihood of identifying any cerebrovascular issues. The data analysis was conducted using Python and R programming languages.

Обмеження

This study is limited to a specific group of patients, and further research is needed to determine the effectiveness of the models in larger, more diverse populations. Additionally, external validation of the results is necessary before they can be widely implemented in clinical settings.

Для вашого лікаря:

PMID: 42998172

DOI: 10.1007/s00234-026-04253-9

Анотація

Показано англійською

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.