1
|
Li B, Li G, Liu J, Sun H, Wen C, Yang Y, Qiao A, Liu J, Liu Y. Deep-learning-based real-time individualization for reduce-order haemodynamic model. Comput Biol Med 2024; 174:108476. [PMID: 38636328 DOI: 10.1016/j.compbiomed.2024.108476] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2023] [Revised: 03/18/2024] [Accepted: 04/11/2024] [Indexed: 04/20/2024]
Abstract
The reduced-order lumped parameter model (LPM) has great computational efficiency in real-time numerical simulations of haemodynamics but is limited by the accuracy of patient-specific computation. This study proposed a method to achieve the individual LPM modeling with high accuracy to improve the practical clinical applicability of LPM. Clinical data was collected from two medical centres comprising haemodynamic indicators from 323 individuals, including brachial artery pressure waveforms, cardiac output data, and internal carotid artery flow waveforms. The data were expanded to 5000 synthesised cases that all fell within the physiological range of each indicator. LPM of the human blood circulation system was established. A double-path neural network (DPNN) was designed to input the waveforms of each haemodynamic indicator and their key features and then output the individual parameters of the LPM, which was labelled using a conventional optimization algorithm. Clinically collected data from the other 100 cases were used as the test set to verify the accuracy of the individual LPM parameters predicted by DPNN. The results show that DPNN provided good convergence in the training process. In the test set, compared with clinical measurements, the mean differences between each haemodynamic indicator and the estimate calculated by the individual LPM based on the DPNN were about 10 %. Furthermore, DPNN prediction only takes 4 s for 100 cases. The DPNN proposed in this study permits real-time and accurate individualization of LPM's. When facing medical issues involving haemodynamics, it lays the foundation for patient-specific numerical simulation, which may be beneficial for potential clinical application.
Collapse
Affiliation(s)
- Bao Li
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| | - Guangfei Li
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China.
| | - Jincheng Liu
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| | - Hao Sun
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| | - Chuanqi Wen
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| | - Yang Yang
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| | - Aike Qiao
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| | - Jian Liu
- Department of Cardiology, Peking University People's Hospital, Beijing, China
| | - Youjun Liu
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing, China
| |
Collapse
|
2
|
Shen G, Liu Z, Wang L, Li J. Inter-leg systolic blood pressure difference has been associated with all-cause and cardiovascular mortality: analysis of NHANES 1999-2004. BMC Public Health 2024; 24:1071. [PMID: 38632605 PMCID: PMC11025152 DOI: 10.1186/s12889-024-18508-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2024] [Accepted: 04/02/2024] [Indexed: 04/19/2024] Open
Abstract
BACKGROUND Inter-leg systolic blood pressure difference (ILSBPD) has emerged as a novel cardiovascular risk factor. This study aims to investigate the predictive value of ILSBPD on all-cause and cardiovascular mortality in general population. METHODS We combined three cycles (1999-2004) of the National Health and Nutrition Examination Survey (NHANES) data. Levels of ILSBPD were calculated and divided into four groups based on three cut-off values of 5, 10 and 15mmHg. Time-to-event curves were estimated with the use of the Kaplan-Meier method, and two multivariable Cox proportional hazards regression models were conducted to assess the hazard ratios (HRs) and 95% confidence intervals (CIs) of all-cause and cardiovascular mortality associated with ILSBPD. RESULTS A total of 6 842 subjects were included, with the mean (SD) age of 59.5 (12.8) years. By December 31, 2019, 2 544 and 648 participants were identified all-cause and cardiovascular mortality respectively during a median follow-up of 16.6 years. Time-to-event analyses suggested that higher ILSBPD was associated with increased all-cause and cardiovascular mortality (logrank, p < 0.001). Every 5mmHg increment of ILSBPD brings about 5% and 7% increased risk of all-cause and cardiovascular mortality, and individuals with an ILSBPD ≥ 15mmHg were significantly associated with higher incidence of all-cause mortality (HR 1.43, 95%CI 1.18-1.52, p < 0.001) and cardiovascular mortality (HR 1.73, 95%CI 1.36-2.20, p < 0.001) when multiple confounding factors were adjusted. Subgroup and sensitivity analysis confirmed the relationship. CONCLUSIONS Our findings suggest that the increment of ILSBPD was significantly associated with higher risk of all-cause and cardiovascular mortality in general population.
Collapse
Affiliation(s)
- Geng Shen
- Division of Cardiology, Peking University First Hospital, No. 8 Xishiku St, Xicheng District, 100034, Beijing, China
| | - Zhihao Liu
- Division of Cardiology, Peking University First Hospital, No. 8 Xishiku St, Xicheng District, 100034, Beijing, China
| | - Leyi Wang
- Division of Cardiology, Peking University First Hospital, No. 8 Xishiku St, Xicheng District, 100034, Beijing, China
| | - Jianping Li
- Division of Cardiology, Peking University First Hospital, No. 8 Xishiku St, Xicheng District, 100034, Beijing, China.
| |
Collapse
|
3
|
Sun H, Li B, Zhang L, Zhang Y, Liu J, Huang S, Xi X, Liu Y. Numerical study of hemodynamic changes in the Circle of Willis after stenosis of the internal carotid artery. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 243:107881. [PMID: 37950924 DOI: 10.1016/j.cmpb.2023.107881] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 10/11/2023] [Accepted: 10/22/2023] [Indexed: 11/13/2023]
Abstract
BACKGROUND AND OBJECTIVES In clinical practice a large number of patients with ischemic stroke have internal carotid artery (ICA) stenosis accompanied by Circle of Willis (CoW) stenosis. In the presence of carotid artery stenosis, CoW atherosclerosis may cause cerebral blood flow decompensation and may promote the development of ischemic stroke. The reason for the concomitant stenosis at both sites is unknown. This study investigated the hemodynamic effects of ICA stenosis on the CoW. METHODS We developed a three-dimensional/zero-dimensional (3D/0D) closed-loop geometric multiscale model of the cerebral artery to quantify the hemodynamic indicators, including time-averaged wall shear stress (TAWSS) and oscillatory shear index (OSI). Mild (<50 %), moderate (50-69 %) and severe (>69 %) ICA stenoses were established based on 3D models of cerebral arteries in two volunteers. Geometric multiscale computing models were numerically evaluated to obtain local hemodynamic changes in the CoW in order to assess the risk of stenosis in the CoW. RESULTS Model calculations showed that for all 3D models the A1 segment of the anterior cerebral artery (ACA) or the posterior communicating artery (PCA) within the CoW exhibited a hemodynamic environment with high OSI (>0.2) and low TAWSS (<1 Pa) when the ICA had a moderate stenosis. While in the case of mild and severe stenosis in ICA, there is no such phenomenon. The proportion of the surface area possessing high OSI and low TAWSS in the A1 segment of the ACA or in the PCA was mostly greater than 60 %, which might potentially cause the formation and development of atherosclerosis in CoW and finally lead to CoW stenosis. CONCLUSIONS Therefore, although moderate carotid artery stenosis may not cause ischemic stroke, it may cause hemodynamic changes in the CoW, which in turn may promote CoW stenosis and cause CoW decompensation. In clinical treatment attention should be paid not only to stenosis of the carotid arteries but also to changes in the hemodynamic environment within the CoW, in order to prevent the adverse effects of CoW stenosis.
Collapse
Affiliation(s)
- Hao Sun
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China
| | - Bao Li
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China.
| | - Liyuan Zhang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China
| | - Yanping Zhang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China
| | - Jincheng Liu
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China
| | - Suqin Huang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China
| | - Xiaolu Xi
- Wuhan United Imaging Healthcare Surgical Technology Co., Ltd. Hubei 100124, China
| | - Youjun Liu
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, No. 100 Pingleyuan, Chaoyang District, Beijing, China
| |
Collapse
|
4
|
Lin X, Liu Z, Weng H, Liu X, Liu S, Li J. Association between interleg systolic blood pressure difference and apparent peripheral neuropathy in US adults with diabetes: a cross-sectional study. JOURNAL OF HEALTH, POPULATION, AND NUTRITION 2023; 42:131. [PMID: 38001545 PMCID: PMC10675956 DOI: 10.1186/s41043-023-00475-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Accepted: 11/14/2023] [Indexed: 11/26/2023]
Abstract
BACKGROUND Interleg systolic blood pressure difference (ILSBPD) is associated with peripheral artery disease, but the relationship between ILSBPD and apparent peripheral neuropathy in diabetic patients remains unclear. We explored the relationship between ILSBPD and apparent peripheral neuropathy and examined the possible effect modifiers in US adults with diabetes. METHODS One thousand and fifty-one diabetic participants were included in the study with complete data on systolic blood pressure of the lower extremities and Semmes-Weinstein 10-g monofilament testing from the 1999-2004 National Health and Nutritional Examination Surveys. Systolic blood pressure in the lower extremities was measured using an oscillometric blood pressure device with the patient in the supine position. Apparent peripheral neuropathy was defined as the presence of monofilament insensitivity. RESULTS Every 5-mmHg increment in ILSBPD is associated with an about 14% increased risk of apparent peripheral neuropathy in crude model, but after adjustment for covariates, the correlation became nonsignificant (P = 0.160). When participants were divided into groups based on ILSBPD cutoffs of 5, 10 and 15 mmHg in different analyses, there was a significantly increased risk of apparent peripheral neuropathy in the ILSBPD ≥ 15 mmHg group (OR 1.79, 95% CI 1.11-2.91, P = 0.018), even after adjusting for confounders. In subgroup analysis, no interaction effect was found (all P for interaction > 0.05). CONCLUSIONS In US adults with diabetes, an increase in the ILSBPD (≥ 15 mmHg) was associated with a higher risk of apparent peripheral neuropathy.
Collapse
Affiliation(s)
- Xipeng Lin
- Department of Cardiology, Peking University First Hospital, Beijing, 100083, People's Republic of China
| | - Zhihao Liu
- Department of Cardiology, Peking University First Hospital, Beijing, 100083, People's Republic of China
| | - Haoyu Weng
- Department of Cardiology, Peking University First Hospital, Beijing, 100083, People's Republic of China
| | - Xu Liu
- Department of Cardiology, Peking University First Hospital, Beijing, 100083, People's Republic of China
| | - Shengcong Liu
- Department of Cardiology, Peking University First Hospital, Beijing, 100083, People's Republic of China
| | - Jianping Li
- Department of Cardiology, Peking University First Hospital, Beijing, 100083, People's Republic of China.
- Key Laboratory of Molecular Cardiovascular Sciences of Ministry of Education, Health Science Center, Peking University, Beijing, People's Republic of China.
| |
Collapse
|
5
|
Song X, Liu Y, Wang S, Zhang H, Qiao A, Wang X. Non-invasive hemodynamic diagnosis based on non-linear pulse wave theory applied to four limbs. Front Bioeng Biotechnol 2023; 11:1081447. [PMID: 36970627 PMCID: PMC10033961 DOI: 10.3389/fbioe.2023.1081447] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Accepted: 02/28/2023] [Indexed: 03/29/2023] Open
Abstract
Introduction: Hemodynamic diagnosis indexes (HDIs) can comprehensively evaluate the health status of the cardiovascular system (CVS), particularly for people older than 50 years and prone to cardiovascular disease (CVDs). However, the accuracy of non-invasive detection remains unsatisfactory. We propose a non-invasive HDIs model based on the non-linear pulse wave theory (NonPWT) applied to four limbs. Methods: This algorithm establishes mathematical models, including pulse wave velocity and pressure information of the brachial and ankle arteries, pressure gradient, and blood flow. Blood flow is key to calculating HDIs. Herein, we derive blood flow equation for different times of the cardiac cycle considering the four different distributions of blood pressure and pulse wave of four limbs, then obtain the average blood flow in a cardiac cycle, and finally calculate the HDIs. Results: The results of the blood flow calculations reveal that the average blood flow in the upper extremity arteries is 10.78 ml/s (clinically: 2.5-12.67 ml/s), and the blood flow in the lower extremity arteries is higher than that in the upper extremity. To verify model accuracy, the consistency between the clinical and calculated values is verified with no statistically significant differences (p < 0.05). Model IV or higher-order fitting is the closest. To verify the model generalizability, considering the risk factors of cardiovascular diseases, the HDIs are recalculated using model IV, and thus, consistency is verified (p < 0.05 and Bland-Altman plot). Conclusion: We conclude our proposed algorithmic model based on NonPWT can facilitate the non-invasive hemodynamic diagnosis with simpler operational procedures and reduced medical costs.
Collapse
Affiliation(s)
- Xiaorui Song
- School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai’an, China
| | - Yi Liu
- Department of Ultrasound, Taian Maternity and Child Health Care Hospital, Tai’an, China
| | - Sirui Wang
- Graduate School of Engineering, Chiba University, Chiba, Japan
| | - Honghui Zhang
- College of Engineering, Inner Mongolia Minzu University, Tongliao, China
| | - Aike Qiao
- Faculty of Environment and Life, Beijing University of Technology, Beijing, China
| | - Xuezheng Wang
- School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai’an, China
- Department of Medical Image, The Second Affiliated Hospital of Shandong First Medical University, Tai’an, China
- *Correspondence: Xuezheng Wang,
| |
Collapse
|
6
|
Charry D, Gouskova N, Meyer ML, Ring K, Nambi V, Heiss G, Tanaka H. Arterial stiffness and contralateral differences in blood pressure: The Atherosclerosis Risk in Communities (ARIC) study. J Clin Hypertens (Greenwich) 2022; 24:878-884. [PMID: 35698928 PMCID: PMC9278590 DOI: 10.1111/jch.14493] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Revised: 04/21/2022] [Accepted: 04/23/2022] [Indexed: 11/30/2022]
Abstract
A large interarm difference in brachial systolic blood pressure (SBP) (≥10 or ≥15 mmHg) is strongly associated with elevated cardiovascular events and mortality. Evidence demonstrating whether such contralateral differences in SBP occur in ankle blood pressure and its association with arterial stiffness is scarce. The aims of this study were to characterize arm and ankle contralateral SBP differences in a sample of community‐dwelling older adults (5077), and to determine whether this difference is associated with arterial stiffness assessed by pulse wave velocity (PWV) between the heart and ankle (haPWV), femoral artery and ankle (faPWV), and brachial artery and ankle (baPWV) in the right and left sides. Prevalence of interarm SBP differences ≥10 and ≥15 mmHg was 5.1% and .7%, respectively; the corresponding prevalence for interankle SBP was 24.9% and 12.0%. Higher BMI and lower ankle‐brachial index (ABI) were significantly correlated with greater interarm SBP differences. Increased age, higher BMI, lower ABI, and greater contralateral differences in haPWV, faPWV, and baPWV were significantly correlated to greater interankle SBP differences. Interankle SBP difference ≥15 mmHg was significantly associated with contralateral differences of >80 cm/s in haPWV (OR = 1.94 [95% CI = 1.52–2.49]), >165 cm/s in faPWV (OR = 1.64 [95% CI = 1.27–2.12]), and >240 cm/s in baPWV (OR = 2.43 [95% CI = 1.94–3.05]). The associations remained significant after adjustment for age, sex, race, BMI, smoking status, and ABI. Compared with interarm differences, interankle differences in SBP are common in older adults. The magnitude of interankle, but not interarm, differences in SBP is associated with various measures of arterial stiffness.
Collapse
Affiliation(s)
- Daniela Charry
- Department of Kinesiology and Health Education, The University of Texas at Austin, Austin, Texas, USA
| | - Natalia Gouskova
- Hinda and Arthur Marcus Institute for Aging Research, Hebrew SeniorLife, Harvard Medical School, Boston, Massachusetts, USA
| | - Michelle L Meyer
- Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina, Chapel Hill, North Carolina, USA
| | - Kimberley Ring
- Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina, Chapel Hill, North Carolina, USA
| | - Vijay Nambi
- Department of Cardiology, Baylor College of Medicine, Houston, Texas, USA
| | - Gerardo Heiss
- Department of Cardiology, Baylor College of Medicine, Houston, Texas, USA
| | - Hirofumi Tanaka
- Department of Kinesiology and Health Education, The University of Texas at Austin, Austin, Texas, USA
| |
Collapse
|
7
|
Li B, Xu K, Liu J, Mao B, Li N, Sun H, Zhang Z, Zhao X, Yang H, Zhang L, Du T, Du J, Liu Y. A Numerical Model for Simulating the Hemodynamic Effects of Enhanced External Counterpulsation on Coronary Arteries. Front Physiol 2021; 12:656224. [PMID: 33912072 PMCID: PMC8072480 DOI: 10.3389/fphys.2021.656224] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2021] [Accepted: 03/17/2021] [Indexed: 11/30/2022] Open
Abstract
Traditional enhanced external counterpulsation (EECP) used for the clinical treatment of patients with coronary heart disease only assesses diastolic/systolic blood pressure (Q = D/S > 1.2). However, improvement of the hemodynamic environment surrounding vascular endothelial cells of coronary arteries after long-term application of EECP is the basis of the treatment. Currently, the quantitative hemodynamic mechanism is not well understood. In this study, a standard 0D/3D geometric multi-scale model of the coronary artery was established to simulate the hemodynamic effects of different counterpulsation modes on the vascular endothelium. In this model, the neural regulation caused by counterpulsation was thoroughly considered. Two clinical trials were carried out to verify the numerical calculation model. The results demonstrated that the increase in counterpulsation pressure amplitude and pressurization duration increased coronary blood perfusion and wall shear stress (WSS) and reduced the oscillatory shear index (OSI) of the vascular wall. However, the impact of pressurization duration was the predominant factor. The results of the standard model and the two real individual models indicated that a long pressurization duration would cause more hemodynamic risk areas by resulting in excessive WSS, which could not be reflected by the change in the Q value. Therefore, long-term pressurization during each cardiac cycle therapy is not recommended for patients with coronary heart disease and clinical treatment should not just pay attention to the change in the Q value. Additional physiological indicators can be used to evaluate the effects of counterpulsation treatment.
Collapse
Affiliation(s)
- Bao Li
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Ke Xu
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Jincheng Liu
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Boyan Mao
- The School of Life Sciences, Beijing University of Chinese Medicine, Beijing, China
| | - Na Li
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Hao Sun
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Zhe Zhang
- Department of Cardiac Surgery, Peking University Third Hospital, Beijing, China
| | - Xi Zhao
- Philips (China) Investment Company, Shanghai, China
| | - Haisheng Yang
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Liyuan Zhang
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Tianming Du
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| | - Jianhang Du
- The Eighth Affiliated Hospital, Sun Yat-sen University, Shenzhen, China
| | - Youjun Liu
- Department of Biomedical Engineering, Beijing University of Technology, Beijing, China
| |
Collapse
|
8
|
Li B, Wang H, Li G, Liu J, Zhang Z, Gu K, Yang H, Qiao A, Du J, Liu Y. A patient-specific modelling method of blood circulatory system for the numerical simulation of enhanced external counterpulsation. J Biomech 2020; 111:110002. [PMID: 32898825 DOI: 10.1016/j.jbiomech.2020.110002] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2020] [Revised: 07/09/2020] [Accepted: 08/14/2020] [Indexed: 11/17/2022]
Abstract
Lumped parameter model (LPM) is a common numerical model for hemodynamic simulation of human's blood circulatory system. The numerical simulation of enhanced external counterpulsation (EECP) is a typical biomechanical simulation process based on the LPM of blood circulatory system. In order to simulate patient-specific hemodynamic effects of EECP and develop best treatment strategy for each individual, this study developed an optimization algorithm to individualize LPM elements. Physiological data from 30 volunteers including approximate aortic pressure, cardiac output, ankle pressure and carotid artery flow were clinically collected as optimization objectives. A closed-loop LPM was established for the simulation of blood circulatory system. Aiming at clinical data, a sensitivity analysis for each element was conducted to identify the significant ones. We improved the traditional simulated annealing algorithm to iteratively optimize the sensitive elements. To verify the accuracy of the patient-specific model, 30 samples of simulated data were compared with clinical measurements. In addition, an EECP experiment was conducted on a volunteer to verify the applicability of the optimized model for the simulation of EECP. For these 30 samples, the optimization results show a slight difference between clinical data and simulated data. The average relative root mean square error is lower than 5%. For the subject of EECP experiment, the relative error of hemodynamic responses during EECP is lower than 10%. This slight error demonstrated a good state of optimization. The optimized modeling algorithm can effectively individualize the LPM for blood circulatory system, which is significant to the numerical simulation of patient-specific hemodynamics.
Collapse
Affiliation(s)
- Bao Li
- Department of Biomedical Engineering, College of Life Science and Bioengineering, Beijing University of Technology, Beijing, China.
| | - Hui Wang
- The Eighth Affiliated Hospital, Sun Yat-sen University, ShenZhen, GuangDong, China
| | - Gaoyang Li
- Institute of Fluid Science, Tohoku University, Sendai, Miyagi, Japan
| | - Jian Liu
- Peking University People's Hospital, Beijing, China
| | - Zhe Zhang
- Peking University Third Hospital, Beijing, China
| | - Kaiyun Gu
- Peking University Third Hospital, Beijing, China
| | - Haisheng Yang
- Department of Biomedical Engineering, College of Life Science and Bioengineering, Beijing University of Technology, Beijing, China
| | - Aike Qiao
- Department of Biomedical Engineering, College of Life Science and Bioengineering, Beijing University of Technology, Beijing, China
| | - Jianhang Du
- The Eighth Affiliated Hospital, Sun Yat-sen University, ShenZhen, GuangDong, China
| | - Youjun Liu
- Department of Biomedical Engineering, College of Life Science and Bioengineering, Beijing University of Technology, Beijing, China.
| |
Collapse
|
9
|
Li G, Watanabe K, Anzai H, Song X, Qiao A, Ohta M. Pulse-Wave-Pattern Classification with a Convolutional Neural Network. Sci Rep 2019; 9:14930. [PMID: 31624300 PMCID: PMC6797811 DOI: 10.1038/s41598-019-51334-2] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2018] [Accepted: 09/24/2019] [Indexed: 11/29/2022] Open
Abstract
Owing to the diversity of pulse-wave morphology, pulse-based diagnosis is difficult, especially pulse-wave-pattern classification (PWPC). A powerful method for PWPC is a convolutional neural network (CNN). It outperforms conventional methods in pattern classification due to extracting informative abstraction and features. For previous PWPC criteria, the relationship between pulse and disease types is not clear. In order to improve the clinical practicability, there is a need for a CNN model to find the one-to-one correspondence between pulse pattern and disease categories. In this study, five cardiovascular diseases (CVD) and complications were extracted from medical records as classification criteria to build pulse data set 1. Four physiological parameters closely related to the selected diseases were also extracted as classification criteria to build data set 2. An optimized CNN model with stronger feature extraction capability for pulse signals was proposed, which achieved PWPC with 95% accuracy in data set 1 and 89% accuracy in data set 2. It demonstrated that pulse waves are the result of multiple physiological parameters. There are limitations when using a single physiological parameter to characterise the overall pulse pattern. The proposed CNN model can achieve high accuracy of PWPC while using CVD and complication categories as classification criteria.
Collapse
Affiliation(s)
- Gaoyang Li
- Institute of Fluid Science, Tohoku University, 2-1-1, Katahira, Aoba-ku, Sendai, Miyagi, 980-8577, Japan
- Graduate School of Biomedical Engineering, Tohoku University, 6-6 Aramaki-aza-aoba, Aoba-ku, Sendai, Miyagi, 980-8579, Japan
| | - Kazuhiro Watanabe
- Institute of Fluid Science, Tohoku University, 2-1-1, Katahira, Aoba-ku, Sendai, Miyagi, 980-8577, Japan
- Graduate School of Biomedical Engineering, Tohoku University, 6-6 Aramaki-aza-aoba, Aoba-ku, Sendai, Miyagi, 980-8579, Japan
| | - Hitomi Anzai
- Graduate School of Biomedical Engineering, Tohoku University, 6-6 Aramaki-aza-aoba, Aoba-ku, Sendai, Miyagi, 980-8579, Japan
| | - Xiaorui Song
- Department of Radiology, Taishan Medical University, No.619 Greatwall Road, Daiyue District, Taian, Shandong, 271000, China
| | - Aike Qiao
- College of Life Science and Bioengineering, Beijing University of Technology, No.100, Pingleyuan, Chaoyang District, Beijing, 100022, China
| | - Makoto Ohta
- Graduate School of Biomedical Engineering, Tohoku University, 6-6 Aramaki-aza-aoba, Aoba-ku, Sendai, Miyagi, 980-8579, Japan.
- ELyTMaX UMI 3757, CNRS-Université de Lyon-Tohoku University, Sendai, Japan.
| |
Collapse
|
10
|
Tang D, Li ZY. Preface: Computational and experimental methods for biological research: cardiovascular diseases and beyond. Biomed Eng Online 2016; 15:157. [PMID: 28155696 PMCID: PMC5259905 DOI: 10.1186/s12938-016-0269-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Affiliation(s)
- Dalin Tang
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, 210096 China
- Department of Mathematical Sciences, Worcester Polytechnic Institute, Worcester, MA 01609 USA
| | - Zhi-Yong Li
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, 210096 China
| |
Collapse
|