BioMedical Engineering OnLine最新文献

{"title":"Advancing ADMET prediction for major CYP450 isoforms: graph-based models, limitations, and future directions.","authors":"Asmaa A Abdelwahab, Mustafa A Elattar, Sahar Ali Fawzi","doi":"10.1186/s12938-025-01412-6","DOIUrl":"https://doi.org/10.1186/s12938-025-01412-6","url":null,"abstract":"<p><p>Understanding Cytochrome P450 (CYP) enzyme-mediated metabolism is critical for accurate Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) predictions, which play a pivotal role in drug discovery. Traditional approaches, while foundational, often face challenges related to cost, scalability, and translatability. This review provides a comprehensive exploration of how graph-based computational techniques, including Graph Neural Networks (GNNs), Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), have emerged as powerful tools for modeling complex CYP enzyme interactions and predicting ADMET properties with improved precision. Focusing on key CYP isoforms-CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4-we synthesize current research advancements and methodologies, emphasizing the integration of multi-task learning, attention mechanisms, and explainable AI (XAI) in enhancing the accuracy and interpretability of ADMET predictions. Furthermore, we address ongoing challenges, such as dataset variability and the generalization of models to novel chemical spaces. The review concludes by identifying future research opportunities, particularly in improving scalability, incorporating real-time experimental validation, and expanding focus on enzyme-specific interactions. These insights underscore the transformative potential of graph-based approaches in advancing drug development and optimizing safety evaluations.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"93"},"PeriodicalIF":2.9,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144697474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid model for detecting motion artifacts in ballistocardiogram signals.","authors":"Yuelong Jiang, Han Zhang, Qizheng Zeng","doi":"10.1186/s12938-025-01426-0","DOIUrl":"https://doi.org/10.1186/s12938-025-01426-0","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The field of contactless health monitoring has witnessed significant advancements with the advent of piezoelectric sensing technology, which enables the monitoring of vital signs such as heart rate and respiration without requiring direct contact with the subject. This is especially advantageous for home sleep monitoring, where traditional wearable devices may be intrusive. However, the acquisition of piezoelectric signals is often impeded by motion artifacts, which are distortions caused by the subject of movements and can obscure the underlying physiological signals. These artifacts can significantly impair the reliability of signal analysis, necessitating effective identification and mitigation strategies. Various methods, including filtering techniques and machine learning approaches, have been employed to address this issue, but the challenge persists due to the complexity and variability of motion artifacts.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This study introduces a hybrid model for detecting motion artifacts in ballistocardiogram (BCG) signals, utilizing a dual-channel approach. The first channel uses a deep learning model, specifically a temporal Bidirectional Gated Recurrent Unit combined with a Fully Convolutional Network (BiGRU-FCN), to identify motion artifacts. The second channel employs multi-scale standard deviation empirical thresholds to detect motion. The model was designed to address the randomness and complexity of motion artifacts by integrating deep learning capabilities with manual feature judgment. The data used for this study were collected from patients with sleep apnea using piezoelectric sensors, and the model's performance was evaluated using a set of predefined metrics.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;This paper proposes and confirms through analysis that the proposed hybrid model exhibits exceptional accuracy in detecting motion artifacts in ballistocardiogram (BCG) signals. Employing a dual-channel approach, the model integrates multi-scale feature judgment with a BiGRU-FCN deep learning model. It achieved a classification accuracy of 98.61% and incurred only a 4.61% loss of valid signals in non-motion intervals. When tested on data from ten patients with sleep apnea, the model demonstrated robust performance, highlighting its potential for practical use in home sleep monitoring.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;The proposed hybrid model presents a significant advancement in the detection of motion artifacts in BCG signals. Compared to existing methods such as the Alivar method [29], Enayati method [22], and Wiard method [20], our hybrid model achieves higher classification accuracy (98.61%) and lower valid signal loss ratio (4.61%). This demonstrates the effectiveness of integrating multi-scale standard deviation empirical thresholds with a deep learning model in enhancing the accuracy and robustness of motion artifact detection. This approach is particularly effective for home sleep","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"92"},"PeriodicalIF":2.9,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144697473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Odontogenic/osteogenic differentiation of dental pulp stem cells on a Biodentine-coated polymer nanofibers.","authors":"Zahra Sarvarian, Parisa Sanaei-Rad, Farzad Moradikhah, Ehsan Seyedjafari, Mohammad Javanbakht","doi":"10.1186/s12938-025-01421-5","DOIUrl":"10.1186/s12938-025-01421-5","url":null,"abstract":"<p><strong>Background: </strong>Tissue engineering has become increasingly applied for tissue repair purposes. Scaffolds, one of the main components of tissue engineering, provide a supportive framework for cell culture and growth. The objective of the present study was to investigate the odontogenic/osteogenic differentiation of dental pulp stem cells, cultured on a polycaprolactone (PCL)-based nanofibrous scaffold, coated with Biodentine. This study evaluated the use of Biodentine as a coating on nanofiber scaffolds and investigated the biological effects of this material on the differentiation of dental pulp stem cells, which hold promising applications in dental and bone tissue engineering.</p><p><strong>Methods: </strong>This study is a basic research investigation. Initially, PCL nanofibrous scaffolds were produced through electrospinning, followed by a post-fabrication surface modification step. The morphology and properties of the scaffolds were examined using scanning electron microscopy (SEM). In the surface treatment step, two different concentrations of Biodentine (0.05% and 0.01%) were applied on the mats. The biocompatibility of the scaffolds was assessed using an MTT assay on days 1, 3, and 5. Additionally, the odontogenic/osteogenic differentiation potency of fabricated scaffolds was evaluated by alkaline phosphatase (ALP) activity and deposited calcium of the cells on days 7, 14, and 21.</p><p><strong>Results: </strong>SEM analysis revealed that Biodentine coating increased surface roughness, particularly at the 0.05% concentration, where excessive particle aggregation was observed. In contrast, the control PCL scaffold exhibited a well-organized fibrous structure with a smooth surface, whereas the 0.01% Biodentine-coated scaffold displayed a moderately roughened surface with uniformly distributed mineralized deposits. Cell viability was higher in the 0.01% Biodentine group, while the 0.05% concentration showed reduced proliferation. ALP activity peaked on day 14, and the highest level of calcium deposition was observed in the 0.01% Biodentine group on day 21, indicating enhanced biomineralization.</p><p><strong>Conclusion: </strong>Biodentine/PCL scaffolds demonstrated notable and suitable physical and chemical properties. Furthermore, they enhanced odontogenic/osteogenic differentiation and mineralization compared to the control group. These findings support the potential of fabricated scaffolds for odontogenic/osteogenic differentiation applications.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"91"},"PeriodicalIF":2.9,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12273335/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144658271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In vitro study on the osteoimmunological potential of magnesium implants (WE43MEO).","authors":"Sabrin Aydin, Ana Prates Soares, Heilwig Fischer, Raphael Silvan Knecht, Alexander Kopp, Katharina Schmidt-Bleek, Max Heiland, Carsten Rendenbach","doi":"10.1186/s12938-025-01413-5","DOIUrl":"10.1186/s12938-025-01413-5","url":null,"abstract":"<p><strong>Introduction: </strong>Bioresorbable implants significantly advance orthopedics and regenerative medicine, offering advantages over permanent implants for bone regeneration. They eliminate the need for secondary surgery and reduce long-term risks associated with permanent implants. Magnesium-based alloys are particularly promising, as their biocompatibility and mechanical properties are similar to bone. However, the degradation of magnesium is associated with physiological challenges that need to be better understood.</p><p><strong>Objective: </strong>The primary focus of this in vitro study was to investigate the osteogenic and immunomodulatory potential of WE43, a promising magnesium alloy tailored for clinical applications, and to test its osteogenic effect when a plasma electrolytic oxidation (PEO) surface modification is added.</p><p><strong>Results: </strong>The present data revealed that WE43 implants show excellent biocompatibility and bioactivity, promoting the viability of osteoblasts and enhancing the expression of osteogenic genes, specially Alpl and Tnfrsf11b. PEO surface modification did not further enhance osteogenic differentiation. Notably, WE43 implants elicited a minimal inflammatory response in RAW264.7 murine macrophages, indicating good biocompatibility. Furthermore, supernatant collected from RAW264.7 murine macrophages cultured with WE43 implants stimulated the Alpl expression in MC3T3-E1 murine osteoblasts, demonstrating their potential osteoimmune effect.</p><p><strong>Conclusion: </strong>The present findings highlight the promising potential of WE43 alloy as a biocompatible and osteoinductive biomaterial for bone regeneration applications. Their osteoimmune modulation further demonstrates the advantages of using this alloy system. Specifically, a minimal, well-controlled inflammatory response can promote a faster transition to the bone remodeling phase, leading to quicker and more effective bone regeneration.</p><p><strong>Methodology: </strong>A comprehensive in vitro investigation was conducted to assess the impact of both WE43 and WE43 PEO on the viability, Alkaline Phosphatase (ALP) expression, osteogenic gene expression (Alpl, Tnfrsf11b, and Bglap), and mineralization of MC3T3-E1 murine osteoblasts. The osteoimmunomodulatory response to WE43 was evaluated using RAW264.7 murine macrophages by assessing their response to direct contact with the alloy.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"90"},"PeriodicalIF":2.9,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12265262/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Special collection in association with the 2024 International Conference on Aging, Innovation and Rehabilitation.","authors":"Babak Taati, Milos Popovic","doi":"10.1186/s12938-025-01427-z","DOIUrl":"10.1186/s12938-025-01427-z","url":null,"abstract":"","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"89"},"PeriodicalIF":2.9,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12257741/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144636050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a clinical prediction model for concurrent pulmonary infection in convalescent patients with intracerebral hemorrhage.","authors":"Jixiang Xu, Xiaoxiao Han, Yinliang Qi, Xiaomei Zhou","doi":"10.1186/s12938-025-01425-1","DOIUrl":"10.1186/s12938-025-01425-1","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to develop and validate a clinical prediction model for assessing the risk of concurrent pulmonary infection (PI) in patients recovering from intracerebral hemorrhage (ICH).</p><p><strong>Methods: </strong>In this retrospective study, we analyzed clinical data from 761 patients in the subacute recovery phase of ICH, of whom 504 developed PI and 257 did not. Univariate logistic regression was initially used to identify potential risk factors, followed by variable selection through the Least Absolute Shrinkage and Selection Operator (LASSO) regression. Predictors selected by LASSO were entered into a multivariate logistic regression to establish a final model. A nomogram was constructed based on the significant variables. The model's discrimination was evaluated using the area under the receiver operating characteristic curve (AUC), and its calibration was assessed using calibration plots and the Hosmer-Lemeshow goodness-of-fit test. Clinical utility was evaluated via decision curve analysis (DCA). Positive predictive value (PPV) and negative predictive value (NPV) were also calculated at the optimal threshold.</p><p><strong>Results: </strong>Eight independent predictors were identified: age, prophylactic antibiotic use, disturbance of consciousness, tracheotomy, dysphagia, duration of bed rest, nasal feeding, and procalcitonin level. The model demonstrated excellent discriminative ability with an AUC of 0.901(95%CI 0.878-0.924) and good calibration (Hosmer-Lemeshow test, P = 0.982). At the optimal cut-off point, the PPV was 92.6% and the NPV was 68.0%. DCA indicated favorable clinical benefit across a wide range of threshold probabilities.</p><p><strong>Conclusion: </strong>We developed a nomogram-based prediction model that accurately identifies the risk of pulmonary infection in patients recovering from ICH. This model offers valuable support for early clinical decision-making and targeted preventive strategies.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"88"},"PeriodicalIF":2.9,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12255977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144616120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical value of serum uric acid and homocysteine levels in predicting the occurrence of atrial fibrillation in patients with type 2 diabetes mellitus.","authors":"Dong Li, Jinlong Deng, Lixian Ma","doi":"10.1186/s12938-025-01418-0","DOIUrl":"10.1186/s12938-025-01418-0","url":null,"abstract":"<p><strong>Background: </strong>The objective of this study was to evaluate the predictive value of serum uric acid (UA) and homocysteine (Hcy) levels for atrial fibrillation (AF) development in type 2 diabetes mellitus (T2DM) patients.</p><p><strong>Methods: </strong>Clinical data of 400 patients diagnosed with T2DM between January 2020 and August 2023 were retrospectively analyzed. They were categorized into AF group and non-AF group according to whether AF occurred or not. The predictive efficacy of serum UA and Hcy on the occurrence of AF in patients with T2DM was analyzed by using the receiver operating characteristic (ROC). The combined values were derived using regression coefficients, enabling joint prediction. Logistic regression analysis was employed to identify the influential factors. The nomogram prediction model was developed using R software based on the screened influencing factors, with internal validation performed via the Bootstrap method. ROC curves, calibration curves, and decision curves were plotted to evaluate the efficacy of the model.</p><p><strong>Results: </strong>Compared with the non-AF group, the total bilirubin (TBIL), DBIL/TBIL, total protein (TP), UA, Hcy, cystatin C (Cys C), and large platelet ratio (PLCR) levels were significantly higher in the AF group, whereas triglycerides (TG), high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), and platelet count (PLT) levels were significantly lower (p < 0.05). The area under the curve (AUC) predicted by the combination of serum UA and serum Hcy was 0.928, which was higher than that of UA (Z = 2.635, p = 0.008) and Hcy (Z = 4.629, p < 0.001). UA, Hcy, TP, PLCR, TG, and LDL-C were all influential factors for AF in patients with T2DM (p < 0.05). The nomogram model constructed on the basis of the above independent influences predicted an AUC of 0.946 (95% CI: 0.924-0.968) for the occurrence of AF, with p = 0.134 in the Hosmer-Lemeshow test. In addition, calibration curve and decision curve analyses showed good agreement and clinical benefit for this nomogram model.</p><p><strong>Conclusion: </strong>Serum UA and Hcy levels exhibited some predictive value for the occurrence of AF in patients with T2DM. The nomogram model incorporating demographic and serological parameters demonstrated good diagnostic performance and may serve as a valuable predictive tool for AF occurrence.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"86"},"PeriodicalIF":2.9,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12239247/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144599204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a deep learning-based MRI diagnostic model for human Brucella spondylitis.","authors":"Binyang Wang, Jinquan Wei, Zhijun Wang, Pengying Niu, Lvlin Yang, Yanmei Hu, Dan Shao, Wei Zhao","doi":"10.1186/s12938-025-01404-6","DOIUrl":"10.1186/s12938-025-01404-6","url":null,"abstract":"<p><strong>Introduction: </strong>Brucella spondylitis (BS) and tuberculous spondylitis (TS) are prevalent spinal infections with distinct treatment protocols. Rapid and accurate differentiation between these two conditions is crucial for effective clinical management; however, current imaging and pathogen-based diagnostic methods fall short of fully meeting clinical requirements. This study explores the feasibility of employing deep learning (DL) models based on conventional magnetic resonance imaging (MRI) to differentiate BS and TS.</p><p><strong>Methods: </strong>A total of 310 subjects were enrolled in our hospital, comprising 209 with BS, 101 with TS. The participants were randomly divided into a training set (n = 217) and a test set (n = 93). And 74 with other hospital was external validation set. Integrating Convolutional Block Attention Module (CBAM) into the ResNeXt-50 architecture and training the model using sagittal T2-weighted images (T2WI). Classification performance was evaluated using the area under the receiver operating characteristic (AUC) curve, and diagnostic accuracy was compared against general models such as ResNet50, GoogleNet, EfficientNetV2, and VGG16.</p><p><strong>Results: </strong>The CBAM-ResNeXt model revealed superior performance, with accuracy, precision, recall, F1-score, and AUC from 0.942, 0.940, 0.928, 0.934, 0.953, respectively. These metrics outperformed those of the general models.</p><p><strong>Conclusions: </strong>The proposed model offers promising potential for the diagnosis of BS and TS using conventional MRI. It could serve as an invaluable tool in clinical practice, providing a reliable reference for distinguishing between these two diseases.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"87"},"PeriodicalIF":2.9,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12239351/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144599164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning for predicting myopia severity classification method.","authors":"WangMeiYu Xing, XiaoNa Li, JingShu Ni, YuanZhi Zhang, ZhongSheng Li, Yong Liu, YiKun Wang, Yao Huang","doi":"10.1186/s12938-025-01416-2","DOIUrl":"10.1186/s12938-025-01416-2","url":null,"abstract":"<p><strong>Background: </strong>Myopia is a major cause of vision impairment. To improve the efficiency of myopia screening, this paper proposes a deep learning model, X-ENet, which combines the advantages of depthwise separable convolution and dynamic convolution to classify different severities of myopia. The proposed model not only enables precise extraction of detailed features from fundus images but also achieves lightweight processing, thereby improving both computational efficiency and classification accuracy.</p><p><strong>Approach: </strong>First, fundus images are enhanced and preprocessed to improve feature extraction effectiveness and enhance the model's generalization capability. Then, the model is trained using fivefold cross-validation, leveraging dynamic convolution and depthwise separable convolution to extract features from each fundus image and classify the severity of myopia. Next, Grad-CAM is employed to visualize the model's decision-making process, highlighting the regions contributing to classification. Finally, a user-friendly GUI interface is developed to intuitively present the classification results, thereby enhancing the system's usability and practical applicability.</p><p><strong>Results: </strong>The experimental results show that the proposed method achieves an accuracy of 0.9104, a precision of 0.8154, a recall of 0.8177, an F1-score of 0.8147, and a specificity of 0.9376 in the classification of myopia severity.</p><p><strong>Significance: </strong>The model significantly outperforms existing conventional deep learning models in terms of accuracy, demonstrating strong effectiveness and reliability.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"85"},"PeriodicalIF":2.9,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12239301/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144599205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Filter-type neural network-based counter-pulsation control in pulsatile ECMO: improving heartbeat-pulse discrimination and synchronization accuracy.","authors":"Hyun-Woo Jang, Chang-Young Yoo, Seong-Min Kang, Seong-Wook Choi","doi":"10.1186/s12938-025-01414-4","DOIUrl":"10.1186/s12938-025-01414-4","url":null,"abstract":"<p><p>Implementing counter-pulsation (CP) control in pulsatile extracorporeal membrane oxygenator (p-ECMO) systems offers a refined approach to mitigate risks commonly associated with conventional ECMOs. To attain CP between the p-ECMO and heart, accurate detection of heartbeats within blood pressure (BP) waveform data becomes imperative, especially in situations where measuring electrocardiograms (ECGs) are difficult or impractical. In this study, a cumulative algorithm incorporating filter-type neural networks was developed to distinguish heartbeats from other pulse signals generated by the p-ECMO, reflections, or motion artifacts in the BP data. A control system was implemented using the cumulative algorithm that detects the heart rate (HR) and maintains a proper interval between the p-ECMO's pulses and heart beats, thereby achieving CP. To ensure precise circulatory support control, the p-ECMO setup was connected to a mock circulation system, with the human BP waveforms being replicated using a heart model. The algorithm could maintain CP perfectly when the HR remained constant; however, owing to a 0.48-s delay from the HR detection to CP control, the success rate of the CP control decreases when a sudden increase in the HR occurred. In fact, when the HR varied by ± 5 bpm every minute, the CP success rate dropped to 78.62%; however, this was still higher as compared to the 25.75% success rate achieved when no control was applied.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"24 1","pages":"83"},"PeriodicalIF":2.9,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12232688/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144582969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}