Machine Learning Approximations to Predict Epigenetic Age Acceleration in Stroke Patients.

Age acceleration (Age-A) is a useful tool that is able to predict a broad range of health outcomes. It is necessary to determine DNA methylation levels to estimate it, and it is known that Age-A is influenced by environmental, lifestyle, and vascular risk factors (VRF). The aim of this study is to estimate the contribution of these easily measurable factors to Age-A in patients with cerebrovascular disease (CVD), using different machine learning (ML) approximations, and try to find a more accessible model able to predict Age-A. We studied a CVD cohort of 952 patients with information about VRF, lifestyle habits, and target organ damage. We estimated Age-A using Hannum's epigenetic clock, and trained six different models to predict Age-A: a conventional linear regression model, four ML models (elastic net regression (EN), K-Nearest neighbors, random forest, and support vector machine models), and one deep learning approximation (multilayer perceptron (MLP) model). The best-performing models were EN and MLP; although, the predictive capability was modest (R2 0.358 and 0.378, respectively). In conclusion, our results support the influence of these factors on Age-A; although, they were not enough to explain most of its variability.

Long-term vascular events after subarachnoid hemorrhage.

BACKGROUND: Spontaneous subarachnoid hemorrhage (SAH) long-term risk is not well known. Our aims are: describing long-term vascular event (VE) incidence rates in SAH survivors; describing VE: ischemic and/or hemorrhagic; identifying independent association of factors related to VE; and analyzing the usefulness of factors to increase predictive ability. METHODS: A prospective cohort study of consecutive patients admitted to Hospital del Mar with a diagnosis of SAH (n = 566) between January 2007 and January 2020 was carried out. They were followed up until January 2021. The study endpoint was a new VE in the follow-up. We calculated both incidence rates and cumulative rates at 5 years. Cox regression survival models including vascular risk factors with and without specific data of SAH disease were developed. We analyzed ROC curves of all multivariate models. RESULTS: The analyzed cohort included 423 non-fatal SAH cases. Total patient-years were 2468.16 years. The average follow-up was 70.03 ± 43.14; range: 1-180 months. There were 49 VE detected in 47 patients, as 2 of them had more than 1 VE. Incidence rate was 0.020 events_per_patient/year, cumulative incidence at 5 years was 11.11%. The more frequent VE that we found were cerebrovascular (28/49), mainly ischemic (21/28). Disability after SAH and the presence of multiple aneurysms were independently associated with a VE risk and improved the predictive capacity of multivariate models (AUC 0.679 vs 0.764; p = 0.0062). CONCLUSIONS: We reported a low vascular risk after SAH. We have shown the usefulness of SAH factors to identify patients with a higher risk of VE.