Arterial blood pressure (ABP) is an important vital sign from which it can be extracted valuable information about the subject’s health. After studying its morphology it is possible to diagnose cardiovascular diseases such as hypertension, so ABP routine control is recommended. The most common method of controlling ABP is the cuff-based method, from which it is obtained only the systolic and diastolic blood pressure (SBP and DBP, respectively). This paper proposes a cuff-free method to estimate the morphology of the average ABP pulse ($\overline{ABPM}$) through a deep learning model based on a seq2seq architecture with attention mechanism. It only needs raw photoplethysmogram signals (PPG) from the finger and includes the capacity to integrate both categorical and continuous demographic information (DI). The experiments were performed on more than 1100 subjects from the MIMIC database for which their corresponding age and gender were consulted. Without allowing the use of data from the same subjects to train and test, the mean absolute errors (MAE) were 6.57 ± 0.20 and 14.39 ± 0.42 mmHg for DBP and SBP, respectively. For $\overline{ABPM}$, R correlation coefficient and the MAE were 0.98 ± 0.001 and 8.89 ± 0.10 mmHg. In summary, this methodology is capable of transforming PPG into an ABP pulse, which obtains better results when DI of the subjects is used, potentially useful in times when wireless devices are becoming more popular.

Arterial stiffness is a major condition related to many cardiovascular diseases. Traditional approaches in the assessment of arterial stiffness supported by machine learning techniques are limited to the pulse wave velocity (PWV) estimation based on pressure signals from the peripheral arteries. Nevertheless, arterial stiffness can be assessed based on the pressure–strain relationship by analyzing its hysteresis loop. In this work, the capacity of deep learning models based on generative adversarial networks (GANs) to transfer pressure signals from the peripheral arterial region to pressure and area signals located in the central arterial region is explored. The studied signals are from a public and validated virtual database. Compared to other works in which the assessment of arterial stiffness was performed via PWV, in the present work the pressure–strain hysteresis loop is reconstructed and evaluated in terms of classical machine learning metrics and clinical parameters. Least-square GAN (LSGAN) and Wasserstein GAN with gradient penalty (WGAN-GP) adversarial losses are compared, yielding better results with LSGAN. LSGAN mean ± standard deviation of error for pressure and area pulse waveforms are 0.8 ± 0.4 mmHg and 0.1 ± 0.1 cm², respectively. Regarding the pressure–strain elastic modulus, it is achieved a mean absolute percentage error of 6.5 ± 5.1%. GAN-based deep learning models can recover the pressure–strain loop of central arteries while observing pressure signals from peripheral arteries.

Évaluation non invasive de la dynamique cardiovasculaire à l'aide d'outils d'apprentissage statistique: Dans ce manuscrit, des outils d'apprentissage statistique ont été appliqués afin d'apporter une contribution à l'amélioration de l'évaluation de la dynamique vasculaire à partir d'une approche non invasive. Différents modèles ont été proposés en suivant des étapes progressives : de l'acquisition du signal brut, en passant par le traitement du signal, jusqu'à l'estimation des paramètres cardiovasculaires en tant que tels.Tout d'abord, une technique d'identification des points de repère à partir de la forme d'onde de la pression artérielle (PA) a été introduite. Ensuite, des modèles d'apprentissage automatique basés sur des caractéristiques ont été comparés en termes d'estimation de la tension artérielle systolique centrale. Ensuite, une méthode d'estimation du pouls artériel moyen par apprentissage profond a été proposée sur la base de la photopléthysmographie et d'informations démographiques. Ensuite, une technique basée sur le GAN a été introduite pour estimer la boucle pression-déformation centrale, un paramètre clé dans l'évaluation de la rigidité artérielle, sur la base de séries temporelles de tension artérielle périphérique. Enfin, l'approche d'apprentissage non supervisé a été appliquée pour identifier les groupes présentant des conditions ischémiques sur la base des informations de base de l'échocardiographie d'effort, suggérant que le couplage ventriculaire-artériel est une caractéristique utile pour les identifier.