Conectar
by Sona M. Al Younis, Leontios J. Hadjileontiadis, Aamna M. Al Shehhi, Cesare Stefanini, Mohanad Alkhodari, Stergios Soulaidopoulos, Petros Arsenos, Ioannis Doundoulakis, Konstantinos A. Gatzoulis, Konstantinos Tsioufis, Ahsan H. Khandoker
Heart Failure (HF) significantly impacts approximately 26 million people worldwide, causing disruptions in the normal functioning of their hearts. The estimation of left ventricular ejection fraction (LVEF) plays a crucial role in the diagnosis, risk stratification, treatment selection, and monitoring of heart failure. However, achieving a definitive assessment is challenging, necessitating the use of echocardiography. Electrocardiogram (ECG) is a relatively simple, quick to obtain, provides continuous monitoring of patient’s cardiac rhythm, and cost-effective procedure compared to echocardiography. In this study, we compare several regression models (support vector machine (SVM), extreme gradient boosting (XGBOOST), gaussian process regression (GPR) and decision tree) for the estimation of LVEF for three groups of HF patients at hourly intervals using 24-hour ECG recordings. Data from 303 HF patients with preserved, mid-range, or reduced LVEF were obtained from a multicentre cohort (American and Greek). ECG extracted features were used to train the different regression models in one-hour intervals. To enhance the best possible LVEF level estimations, hyperparameters tuning in nested loop approach was implemented (the outer loop divides the data into training and testing sets, while the inner loop further divides the training set into smaller sets for cross-validation). LVEF levels were best estimated using rational quadratic GPR and fine decision tree regression models with an average root mean square error (RMSE) of 3.83% and 3.42%, and correlation coefficients of 0.92 (pby Se Eun Kim, So Hee Park, Woo-Jung Park, Gayeong Kim, Seo Yeon Kim, Hyeran Won, Yun-Ho Hwang, Heeji Lim, Hyeon Guk Kim, You-Jin Kim, Dokeun Kim, Jung-Ah Lee
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) emerged in 2019 and caused the coronavirus disease 2019 (COVID-19) pandemic worldwide. As of September 2023, the number of confirmed coronavirus cases has reached over 770 million and caused nearly 7 million deaths. The World Health Organization assigned and informed the characterization of variants of concern (VOCs) to help control the COVID-19 pandemic through global monitoring of circulating viruses. Although many vaccines have been proposed, developing an effective vaccine against variants is still essential to reach the endemic stage of COVID-19. We designed five DNA vaccine candidates composed of the first isolated genotype and major SARS-CoV-2 strains from isolated Korean patients classified as VOCs, such as Alpha, Beta, Gamma, and Delta. To evaluate the immunogenicity of each genotype via homologous and heterologous vaccination, mice were immunized twice within a 3-week interval, and the blood and spleen were collected 1 week after the final vaccination to analyze the immune responses. The group vaccinated with DNA vaccine candidates based on the S genotype and the Alpha and Beta variants elicited both humoral and cellular immune responses, with higher total IgG levels and neutralizing antibody responses than the other groups. In particular, the vaccine candidate based on the Alpha variant induced a highly diverse cytokine response. Additionally, we found that the group subjected to homologous vaccination with the S genotype and heterologous vaccination with S/Alpha induced high total IgG levels and a neutralization antibody response. Homologous vaccination with the S genotype and heterologous vaccination with S/Alpha and S/Beta significantly induced IFN-γ immune responses. The immunogenicity after homologous vaccination with S and Alpha and heterologous vaccination with the S/Alpha candidate was better than that of the other groups, indicating the potential for developing novel DNA vaccines against different SARS-CoV-2 variants.
FreshRSS