Search

With aging being a major non-reversible risk factor for cardiovascular disease, the concept of Vascular Age (VA) emerges as a promising alternate measure to assess an individual’s cardiovascular risk and overall health. This study investigated the use of frequency features and Supervised Learning (SL) models for estimating a VA Age-Group (VAAG), as a surrogate of Chronological Age (CHA). Frequency features offer an accessible alternative to temporal and amplitude features, reducing reliance on high sampling frequencies and complex algorithms. Simulated subjects from One-dimensional models were employed to train SL algorithms, complemented with healthy in vivo subjects. Validation with real-world subject data was emphasized to ensure model applicability, using well-known risk factors as a form of cardiovascular health analysis and verification. Random Forest (RF) proved to be the best-performing model, achieving an accuracy/AUC score of 66.5%/0.59 for the in vivo test dataset, and 97.5%/0.99 for the in silico one. This research contributed to preventive medicine strategies, supporting early detection and personalized risk assessment for improved cardiovascular health outcomes across diverse populations.

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.

The shudders of the COVID-19 pandemic have projected newer challenges in the healthcare domain across the world. In South American scenario, severe issues and difficulties have been noticed in areas like patient consultations, remote monitoring, medical resources, healthcare personnel etc. This work is aimed at providing a holistic view to the digital healthcare during the times of COVID-19 pandemic in South America. It includes different initiatives like mobile apps, web-platforms and intelligent analyses toward early detection and overall healthcare management. In addition to discussing briefly the key issues toward extensive implementation of eHealth paradigms, this work also sheds light on some key aspects of Artificial Intelligence and the Internet of Things along their potential applications like clinical decision support systems and predictive risk modeling, especially in the direction of combating the emergent challenges due to the COVID-19 pandemic.

En estos últimos años se han implementado nuevas formas de pedagogía en el área de ingeniería, habida cuenta que los desafíos reales que enfrentará el futuro ingeniero deberán ser abordados de manera interdisciplinaria. Es por ello que desde los primeros años de su carrera y ya desde las ciencias básicas, es conveniente que el estudiante pueda enfrentar problemas procedentes de otros escenarios y así poder establecer puentes entre las distintas ciencias y potenciar los aportes de cada una de ellas. El objetivo principal del presente trabajo es describir el resultado de una experiencia interdisciplinar en la que se involucra al estudiante en la aplicación de conceptos matemáticos a una disciplina biológica. La experiencia se llevó a cabo con estudiantes cursantes de la asignatura Análisis Matemático I, correspondiente al primer año de las distintas carreras de Ingeniería de la Facultad Buenos Aires en la Universidad Tecnológica Nacional, a quienes se les presentó una actividad relacionada con el concepto de “ingeniería aplicada al modelado del sistema cardiovascular”. Para abordarla, 58 estudiantes debieron aplicar conceptos estudiados en la asignatura e incorporar aquellos ligados a la fisiología humana. Asimismo, participaron tanto en la recolección general de datos como en la asistencia para la adquisición de los mismos, que luego se analizaron en trabajos grupales. Se consideró una metodología descriptiva a partir de un cuestionario individual, con el objeto de completar la evaluación de la experiencia. Los resultados obtenidos evidenciaron un elevado interés por parte de los estudiantes en el abordaje de situaciones problemáticas, con un 89% de aprobación en relación a la importancia de establecer relaciones entre las distintas áreas de conocimiento. La actividad fue diseñada en el marco del proyecto de investigación y desarrollo: "Empleo de problemas interdisciplinarios en asignaturas de matemática en carreras de ingeniería" conjuntamente con el Grupo de Investigación y Desarrollo en Bioingeniería, perteneciente a la misma institución y en virtud de la experticia de sus integrantes en tópicos relacionados con la salud cardiovascular. Efectivamente, los resultados obtenidos demuestran que la implementación de estrategias interdisciplinares de enseñanza basadas en situaciones problemáticas propicia un incremento en la atención por parte del estudiante, una mayor participación y proporciona una aplicación directa de las herramientas matemáticas estudiadas.

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 (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 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.

Background. Adequate fluid management could be essential to minimize high arterial stiffness observed in chronically hemodialyzed patients (CHP). Aim. To determine the association between body fluid status and central and peripheral arterial stiffness levels. Methods. Arterial stiffness was assessed in 65 CHP by measuring the pulse wave velocity (PWV) in a central arterial pathway (carotid-femoral) and in a peripheral pathway (carotid-brachial). A blood pressure-independent regional arterial stiffness index was calculated using PWV. Volume status was assessed by whole-body multiple-frequency bioimpedance. Patients were first observed as an entire group and then divided into three different fluid status-related groups: normal, overhydration, and dehydration groups. Results. Only carotid-femoral stiffness was positively associated (P

Carotid-to-radial pulse wave velocity (PWVcr) has been proposed to evaluate endothelial function. However, the measurement of PWVcr is not without limitations. A new simple approach could have wide application. Stiffness index (SI) is obtained by analysis of the peripheral pulse wave and gives reproducible information about stiffness of large arteries. This study assessed the effects of hyperemia on SI and compared it with PWVcr in 14 healthy subjects. Both were measured at rest and during 8 minutes after ischemia. SI temporal course was determined. At 1 minute, SI and PWVcr decreased (5.58±0.24 to 5.34±0.23 m/s, P

Purpose. To evaluate in chronically haemodialysed patients (CHPs), if: (1) the vascular access (VA) position (upper arm or forearm) is associated with differential changes in upper limb arterial stiffness; (2) differences in arterial stiffness exist between genders associated with the VA; (3) the vascular substitute (VS) of choice, in biomechanical terms, depends on the previous VA location and CHP gender. Methods. 38 CHPs (18 males; VA in upper arm: 18) were studied. Left and right carotid-brachial pulse wave velocity (PWVc-b) was measured. In in vitro studies, PWV was obtained in ePTFE prostheses and in several arterial and venous homografts obtained from donors. The biomechanical mismatch (BM) between CHP native vessel (NV) and VS was calculated. Results/Conclusions. PWVc-b in upper limbs with VA was lower than in the intact contralateral limbs (P

Carotid-femoral pulse wave velocity (PWV) has emerged as the gold standard for non-invasive evaluation of aortic stiffness; absence of standardized methodologies of study and lack of normal and reference values have limited a wider clinical implementation. This work was carried out in a Uruguayan (South American) population in order to characterize normal, reference, and threshold levels of PWV considering normal age-related changes in PWV and the prevailing blood pressure level during the study. A conservative approach was used, and we excluded symptomatic subjects; subjects with history of cardiovascular (CV) disease, diabetes mellitus or renal failure; subjects with traditional CV risk factors (other than age and gender); asymptomatic subjects with atherosclerotic plaques in carotid arteries; patients taking anti-hypertensives or lipid-lowering medications. The included subjects (n=429) were categorized according to the age decade and the blood pressure levels (at study time). All subjects represented the “reference population”; the group of subjects with optimal/normal blood pressures levels at study time represented the “normal population.” Results. Normal and reference PWV levels were obtained. Differences in PWV levels and aging-associated changes were obtained. The obtained data could be used to define vascular aging and abnormal or disease-related arterial changes.

This work was carried out in a Uruguayan (South American) population to characterize aging-associated physiological arterial changes. Parameters markers of subclinical atherosclerosis and that associate age-related changes were evaluated in healthy people. A conservative approach was used and people with nonphysiological and pathological conditions were excluded. Then, we excluded subjects with (a) cardiovascular (CV) symptoms, (b) CV disease, (c) diabetes mellitus or renal failure, and (d) traditional CV risk factors (other than age and gender). Subjects (n=388) were submitted to non-invasive vascular studies (gold-standard techniques), to evaluate (1) common (CCA), internal, and external carotid plaque prevalence, (2) CCA intima-media thickness and diameter, (3) CCA stiffness (percentual pulsatility, compliance, distensibility, and stiffness index), (4) aortic stiffness (carotid-femoral pulse wave velocity), and (5) peripheral and central pressure wave-derived parameters. Age groups: ≤20, 21–30, 31–40, 41–50, 51–60, 61–70, and 71–80 years old. Age-related structural and functional vascular parameters profiles were obtained and analyzed considering data from other populations. The work has the strength of being the first, in Latin America, that uses an integrative approach to characterize vascular aging-related changes. Data could be used to define vascular aging and abnormal or disease-related changes.

Assessing the geometry of the coronary arteries in a patient can help to better explain coronary artery disease (CAD) development. Allometric scaling functions were successfully applied to describe how essential materials are transported through recursive networks, also observed in the coronary tree. In this work we used skeletonization methods on multislice computed tomography (MSCT) images to render the coronary tree in 3D. Fifty subjects were recruited in two groups: 1) free from plaques and 2) with focal lesions. The left coronary tree was segmented using a custom algorithm with minimum user intervention. Vessels were separated using a stem-crown architecture. Cumulative arterial length (L) with volume (V) and vessel stem diameter (DSTEM) with distal L functions were analysed. In the allometric functions L = kv Vβ and DSTEM = kL Lγ, no significant differences were found between groups. The scaling exponent range for β was 0.6–0.9 and for γ was 0.1–0.4. Values were not different from other studies in pigs. In a Log–Log scatter plot in all patients, lines were parallel, confirmed with an ANCOVA. In other words, the allometric function stood for all patients. The idea that parameters from diseased hearts are expected to deviate from normal was not revealed in this study. We believe that CAD did not disturb the allometric relations due to the focal nature of the lesions and the absence of diffuse CAD. Further combination of MSCT with 3D morphological extraction algorithms can help to overcome the qualitative analysis of a patient vasculature and advance into new clinical quantitative perspectives.