دورية أكاديمية
Non-contact assessment of cardiac physiology using FO-MVSS-based ballistocardiography: a promising approach for heart failure evaluation
| العنوان: | Non-contact assessment of cardiac physiology using FO-MVSS-based ballistocardiography: a promising approach for heart failure evaluation |
|---|---|
| المؤلفون: | Zhan, Jing, Wu, Xiaoyan, Fu, Xuelei, Li, Chenze, Deng, Ke-Qiong, Wei, Qin, Zhang, Chao, Zhao, Tao, Li, Congcong, Huang, Longting, Chen, Kewei, Wang, Qiongxin, Li, Zhengying, Lu, Zhibing |
| المساهمون: | National Natural Science Foundation of China |
| المصدر: | Scientific Reports ; volume 14, issue 1 ; ISSN 2045-2322 |
| بيانات النشر: | Springer Science and Business Media LLC |
| سنة النشر: | 2024 |
| مصطلحات موضوعية: | Multidisciplinary |
| الوصف: | Continuous monitoring of cardiac motions has been expected to provide essential cardiac physiology information on cardiovascular functioning. A fiber-optic micro-vibration sensing system (FO-MVSS) makes it promising. This study aimed to explore the correlation between Ballistocardiography (BCG) waveforms, measured using an FO-MVSS, and myocardial valve activity during the systolic and diastolic phases of the cardiac cycle in participants with normal cardiac function and patients with congestive heart failure (CHF). A high-sensitivity FO-MVSS acquired continuous BCG recordings. The simultaneous recordings of BCG and electrocardiogram (ECG) signals were obtained from 101 participants to examine their correlation. BCG, ECG, and intracavitary pressure signals were collected from 6 patients undergoing cardiac catheter intervention to investigate BCG waveforms and cardiac cycle phases. Tissue Doppler imaging (TDI) measured cardiac time intervals in 51 participants correlated with BCG intervals. The BCG recordings were further validated in 61 CHF patients to assess cardiac parameters by BCG. For heart failure evaluation machine learning was used to analyze BCG-derived cardiac parameters. Significant correlations were observed between cardiac physiology parameters and BCG's parameters. Furthermore, a linear relationship was found betwen IJ amplitude and cardiac output (r = 0.923, R 2 = 0.926, p < 0.001). Machine learning techniques, including K-Nearest Neighbors (KNN), Decision Tree Classifier (DTC), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and XGBoost, respectively, demonstrated remarkable performance. They all achieved average accuracy and AUC values exceeding 95% in a five-fold cross-validation approach. We establish an electromagnetic-interference-free and non-contact method for continuous monitoring of the cardiac cycle and myocardial contractility and measure the different phases of the cardiac cycle. It presents a sensitive method for evaluating changes in both ... |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1038/s41598-024-53464-8 |
| الإتاحة: | https://doi.org/10.1038/s41598-024-53464-8Test https://www.nature.com/articles/s41598-024-53464-8.pdfTest https://www.nature.com/articles/s41598-024-53464-8Test |
| حقوق: | https://creativecommons.org/licenses/by/4.0Test ; https://creativecommons.org/licenses/by/4.0Test |
| رقم الانضمام: | edsbas.2F6731C8 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1038/s41598-024-53464-8 |
|---|