Estimated pulse wave velocity (ePWV) as a potential gatekeeper for MRI-assessed PWV: a linear and deep neural network based approach in 2254 participants of the Netherlands Epidemiology of Obesity study

Hout, M.J. van; Dekkers, I.A.; Lin, L.; Westenberg, J.J.; Schalij, M.J.; Jukema, J.W.; ... ; Lamb, H.J. (2021)

Article / Letter to editor

Pulse wave velocity (PWV) assessed by magnetic resonance imaging (MRI) is a prognostic marker for cardiovascular events. Prediction modelling could enable indirect PWV assessment based on clinical and anthropometric data. The aim was to calculate estimated-PWV (ePWV) based on clinical and anthropometric measures using linear ridge regression as well as a Deep Neural Network (DNN) and to determine the cut-off which provides optimal discriminative performance between lower and higher PWV values. In total 2254 participants from the Netherlands Epidemiology of Obesity study were included (age 45-65 years, 51% male). Both a basic and expanded prediction model were developed. PWV was estimated using linear ridge regression and DNN. External validation was performed in 114 participants (age 30-70 years, 54% female). Performance was compared between models and estimation accuracy was evaluated by ROC-curves. A cut-off for optimal discriminative performance was determined using Youden's index. The basic ridge regression model provided an adjusted R-2 of 0.33 and bias of < 0.001, the expanded model did not add predictive performance. Basic and expanded DNN models showed similar model performance. Optimal discriminative performance was found for PWV < 6.7 m/s. In external validation expanded ridge regression provided the best performance of the four models (adjusted R-2: 0.29). All models showed good discriminative performance for PWV < 6.7 m/s (AUC range 0.81-0.89). ePWV showed good discriminative performance with regard to differentiating individuals with lower PWV values (< 6.7 m/s) from those with higher values, and could function as gatekeeper in selecting patients who benefit from further MRI-based PWV assessment.

• Magnetic resonance imaging
• Pulse wave velocity
• Prediction modelling

• All authors: Hout, M.J. van; Dekkers, I.A.; Lin, L.; Westenberg, J.J.; Schalij, M.J.; Jukema, J.W.; Widya, R.L.; Boone, S.C.; Mutsert, R. de; Rosendaal, F.R.; Scholte, A.J.; Lamb, H.J.
• Date: 2021-07-25
• Journal: International Journal of Cardiovascular Imaging
• Volume: 38
• Pages: 183 - 193
• DOI: doi:10.1007/s10554-021-02359-0
• Link: https://link.springer.com/content/pdf/10.1007/s10554-021-02359-0.pdf