COVID-19 is known to be a cause of microvascular disease imputable to, for instance, the cytokine storm inflammatory response and the consequent blood coagulation. In this study, we propose a methodological approach for assessing the COVID-19 presence and severity based on Random Forest (RF) and Support Vector Machine (SVM) classifiers. Classifiers were applied to Heart Rate Variability (HRV) parameters extracted from photoplethysmographic (PPG) signals collected from healthy and COVID-19 affected subjects. The supervised classifiers were trained and tested on HRV parameters obtained from the PPG signals in a cohort of 50 healthy subjects and 93 COVID-19 affected subjects, divided into two groups, mild and moderate, based on the support of oxygen therapy and/or ventilation. The most informative feature set for every group’s comparison was determined with the Least Absolute Shrinkage and Selection Operator (LASSO) technique. Both RF and SVM classifiers showed a high accuracy percentage during groups’ comparisons. In particular, the RF classifier reached 94% of accuracy during the comparison between the healthy and minor severity COVID-19 group. Obtained results showed a strong capability of RF and SVM to discriminate between healthy subjects and COVID-19 patients and to differentiate the two different COVID-19 severity. The proposed method might be helpful for detecting, in a low-cost and fast fashion, the presence and severity of COVID-19 disease; moreover, these reasons make this method interesting as a starting point for future studies that aim to investigate its effectiveness as a possible screening method.
Objective:Vascular ageing is associated with several alterations, including arterial stiffness and endothelial dysfunction. Such alterations represent an independent factor in the development of cardiovascular disease. In our previous works we demonstrated the alterations occurring in the vascular system are themselves reflected in the shape of the peripheral waveform; thus, a model that describes the waveform as a sum of Gaussian curves provides a set of parameters that successfully discriminate between under(<= 35 years old) and over subjects (> 35 years old). In the present work, we explored the feasibility of a new decomposition model, based on a sum of exponential pulses, applied to the same problem. Approach: The first processing step extracts each pulsation from the input signal and removes the long-term trend using a cubic spline with nodes between consecutive pulsations. After that, a Least Squares fitting algorithm determines the set of optimal model parameters that best approximates each single pulse. The vector of model parameters gives a compact representation of the pulse waveform that constitutes the basis for the classification step. Each subject is associated to his/her "representative" pulse waveform, obtained by averaging the vector parameters corresponding to all pulses. Finally, a Bayesan classifier has been designed to discriminate the waveforms of under and over subjects, using the leave-one-subject-out validation method. Main results: Results indicate that the fitting procedure reaches a rate of 96% in under subjects and 95% in over subjects and that the Bayesan classifier is able to correctly classify 91\% of the subjects with a specificity of 94% and a sensibility of 84%. Significance: This study shows a sensible vascular age estimation accuracy with a multi-exponential model, which may help to predict cardiovascular diseases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.