BioMedical Engineering OnLine最新文献

{"title":"Pulse wave signal-driven machine learning for identifying left ventricular enlargement in heart failure patients.","authors":"Dandan Wu, Ryohei Ono, Sirui Wang, Yoshio Kobayashi, Koichi Sughimoto, Hao Liu","doi":"10.1186/s12938-024-01257-5","DOIUrl":"10.1186/s12938-024-01257-5","url":null,"abstract":"<p><strong>Background: </strong>Left ventricular enlargement (LVE) is a common manifestation of cardiac remodeling that is closely associated with cardiac dysfunction, heart failure (HF), and arrhythmias. This study aimed to propose a machine learning (ML)-based strategy to identify LVE in HF patients by means of pulse wave signals.</p><p><strong>Method: </strong>We constructed two high-quality pulse wave datasets comprising a non-LVE group and an LVE group based on the 264 HF patients. Fourier series calculations were employed to determine if significant frequency differences existed between the two datasets, thereby ensuring their validity. Then, the ML-based identification was undertaken by means of classification and regression models: a weighted random forest model was employed for binary classification of the datasets, and a densely connected convolutional network was utilized to directly estimate the left ventricular diastolic diameter index (LVDdI) through regression. Finally, the accuracy of the two models was validated by comparing their results with clinical measurements, using accuracy and the area under the receiver operating characteristic curve (AUC-ROC) to assess their capability for identifying LVE patients.</p><p><strong>Results: </strong>The classification model exhibited superior performance with an accuracy of 0.91 and an AUC-ROC of 0.93. The regression model achieved an accuracy of 0.88 and an AUC-ROC of 0.89, indicating that both models can quickly and accurately identify LVE in HF patients.</p><p><strong>Conclusion: </strong>The proposed ML methods are verified to achieve effective classification and regression with good performance for identifying LVE in HF patients based on pulse wave signals. This study thus demonstrates the feasibility and potential of the ML-based strategy for clinical practice while offering an effective and robust tool for diagnosing and intervening ventricular remodeling.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"60"},"PeriodicalIF":2.9,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11193305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141440106","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":"Changes in temporal lobe activation during a sound stimulation task in patients with sensorineural tinnitus: a multi-channel near-infrared spectroscopy study.","authors":"Xiaoli Fan, Bin Gong, Hao Yang, Juanjuan Yang, Gaowei Qi, Zheng Wang, Jie Sun, Yu Fang","doi":"10.1186/s12938-024-01255-7","DOIUrl":"10.1186/s12938-024-01255-7","url":null,"abstract":"<p><strong>Background: </strong>The subjective sign of a serious pandemic in human work and life is mathematical neural tinnitus. fNIRS (functional near-infrared spectroscopy) is a new non-invasive brain imaging technology for studying the neurological activity of the human cerebral cortex. It is based on neural coupling effects. This research uses the fNIRS approach to detect differences in the neurological activity of the cerebral skin in the sound stimulation mission in order to better discriminate between the sensational neurological tinnitus.</p><p><strong>Methods: </strong>In the fNIRS brain imaging method, 14 sensorineural tinnitus sufferers and 14 healthy controls listened to varied noise and quiet for fNIRS data collection. Linear fitting was employed in MATLAB to eliminate slow drifts during preprocessing and event-related design analysis. The false discovery rate (FDR) procedure was applied in IBM SPSS Statistics 26.0 to control the false positive rate in multiple comparison analyses.</p><p><strong>Results: </strong>When the ill group and the healthy control group were stimulated by pink noise, there was a significant difference in blood oxygen concentration (P < 0.05), and the healthy control group exhibited a high activation, according to the fNIRS measurement data. The blood oxygen concentration level in the patient group was dramatically enhanced after one month of acupuncture therapy under the identical stimulation task settings, and it was favorably connected with the levels of THI and TEQ scales.</p><p><strong>Conclusions: </strong>Using sensorineural tinnitus illness as an example, fNIRS technology has the potential to disclose future pathological study on subjective diseases throughout time. Other clinical disorders involving the temporal lobe and adjacent brain areas may also be examined, in addition to tinnitus-related brain alterations.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"59"},"PeriodicalIF":2.9,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11191237/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141431298","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":"EfficientNet-based machine learning architecture for sleep apnea identification in clinical single-lead ECG signal data sets.","authors":"Meng-Hsuan Liu, Shang-Yu Chien, Ya-Lun Wu, Ting-Hsuan Sun, Chun-Sen Huang, Kai-Cheng Hsu, Liang-Wen Hang","doi":"10.1186/s12938-024-01252-w","DOIUrl":"10.1186/s12938-024-01252-w","url":null,"abstract":"<p><strong>Objective: </strong>Our objective was to create a machine learning architecture capable of identifying obstructive sleep apnea (OSA) patterns in single-lead electrocardiography (ECG) signals, exhibiting exceptional performance when utilized in clinical data sets.</p><p><strong>Methods: </strong>We conducted our research using a data set consisting of 1656 patients, representing a diverse demographic, from the sleep center of China Medical University Hospital. To detect apnea ECG segments and extract apnea features, we utilized the EfficientNet and some of its layers, respectively. Furthermore, we compared various training and data preprocessing techniques to enhance the model's prediction, such as setting class and sample weights or employing overlapping and regular slicing. Finally, we tested our approach against other literature on the Apnea-ECG database.</p><p><strong>Results: </strong>Our research found that the EfficientNet model achieved the best apnea segment detection using overlapping slicing and sample-weight settings, with an AUC of 0.917 and an accuracy of 0.855. For patient screening with AHI > 30, we combined the trained model with XGBoost, leading to an AUC of 0.975 and an accuracy of 0.928. Additional tests using PhysioNet data showed that our model is comparable in performance to existing models regarding its ability to screen OSA levels.</p><p><strong>Conclusions: </strong>Our suggested architecture, coupled with training and preprocessing techniques, showed admirable performance with a diverse demographic dataset, bringing us closer to practical implementation in OSA diagnosis. Trial registration The data for this study were collected retrospectively from the China Medical University Hospital in Taiwan with approval from the institutional review board CMUH109-REC3-018.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"57"},"PeriodicalIF":2.9,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11188209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141431300","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":"Diurnal variation of heart rate variability in individuals with spinal cord injury.","authors":"Jittima Saengsuwan, Arphatsorn Ruangsuphaphichat, Lars Brockmann, Patpiya Sirasaporn, Nuttaset Manimmanakorn, Kenneth J Hunt","doi":"10.1186/s12938-024-01256-6","DOIUrl":"10.1186/s12938-024-01256-6","url":null,"abstract":"<p><strong>Background: </strong>Heart rate variability (HRV) may provide objective information about cardiogenic autonomic balance in individuals with spinal cord injury (SCI). The aim of this study was to characterize the diurnal variation of HRV in individuals with SCI at lesion level T6 and above and lesion level below T6.</p><p><strong>Methods: </strong>This was a retrospective analysis of a prior cross-sectional study. Individuals with chronic SCI underwent 24 h recording of the time between consecutive R waves (RR interval) to derive parameters of HRV as follows: standard deviation of all normal-to-normal R-R intervals (SDNN) and square root of the mean of the squared differences between successive R-R intervals (RMSSD) (time domain); and high frequency power (HF), low-frequency power (LF), very low frequency power (VLF), ultra-low frequency power (ULF) and total power (TP) (frequency domain). Changes in the magnitude of HRV outcomes over the 24 h period were investigated using a novel multi-component cosinor model constrained to the form of a three-harmonic Fourier series.</p><p><strong>Results: </strong>Participants were grouped as lesion level T6 and above (n = 22) or below T6 (n = 36). Most of them were male (n = 40, 69%) and the median age (interquartile range) was 50.5 (28) years. Both groups exhibited similar diurnal patterns in most HRV metrics. The lowest values occurred in the late afternoon (4-6 pm) and gradually increased, peaking around midnight to early morning (1-6 am). Exceptions included RMSSD, which peaked before midnight, and ULF, which showed a double peak pattern that peaked from 11 am to 1 pm and 4-6 am in participants with lesion level at T6 and above. The HRV values in participants with lesion level T6 and above were generally lower than participants with lesion level below T6, except for peak values of RMSSD, HF and LF.</p><p><strong>Conclusion: </strong>This study demonstrated substantial diurnal variation of HRV in participants with SCI in both groups of participants. In clinical and research settings, diurnal variations in HRV must be taken into consideration.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"58"},"PeriodicalIF":2.9,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11188279/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141431299","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":"Noninvasive prediction of lymph node metastasis in pancreatic cancer using an ultrasound-based clinicoradiomics machine learning model.","authors":"Dong-Yue Wen, Jia-Min Chen, Zhi-Ping Tang, Jin-Shu Pang, Qiong Qin, Lu Zhang, Yun He, Hong Yang","doi":"10.1186/s12938-024-01259-3","DOIUrl":"10.1186/s12938-024-01259-3","url":null,"abstract":"<p><strong>Objectives: </strong>This study was designed to explore and validate the value of different machine learning models based on ultrasound image-omics features in the preoperative diagnosis of lymph node metastasis in pancreatic cancer (PC).</p><p><strong>Methods: </strong>This research involved 189 individuals diagnosed with PC confirmed by surgical pathology (training cohort: n = 151; test cohort: n = 38), including 50 cases of lymph node metastasis. Image-omics features were extracted from ultrasound images. After dimensionality reduction and screening, eight machine learning algorithms, including logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), extra trees (ET), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP), were used to establish image-omics models to predict lymph node metastasis in PC. The best omics prediction model was selected through ROC curve analysis. Machine learning models were used to analyze clinical features and determine variables to establish a clinical model. A combined model was constructed by combining ultrasound image-omics and clinical features. Decision curve analysis (DCA) and a nomogram were used to evaluate the clinical application value of the model.</p><p><strong>Results: </strong>A total of 1561 image-omics features were extracted from ultrasound images. 15 valuable image-omics features were determined by regularization, dimension reduction, and algorithm selection. In the image-omics model, the LR model showed higher prediction efficiency and robustness, with an area under the ROC curve (AUC) of 0.773 in the training set and an AUC of 0.850 in the test set. The clinical model constructed by the boundary of lesions in ultrasound images and the clinical feature CA199 (AUC = 0.875). The combined model had the best prediction performance, with an AUC of 0.872 in the training set and 0.918 in the test set. The combined model showed better clinical benefit according to DCA, and the nomogram score provided clinical prediction solutions.</p><p><strong>Conclusion: </strong>The combined model established with clinical features has good diagnostic ability and can be used to predict lymph node metastasis in patients with PC. It is expected to provide an effective noninvasive method for clinical decision-making, thereby improving the diagnosis and treatment of PC.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"56"},"PeriodicalIF":2.9,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11184715/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141417568","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":"<ArticleTitle xmlns:ns0=\"http://www.w3.org/1998/Math/MathML\">Folic acid-mediated hollow <ns0:math> <ns0:mrow><ns0:msub><ns0:mtext>Mn</ns0:mtext> <ns0:mn>3</ns0:mn></ns0:msub> <ns0:msub><ns0:mtext>O</ns0:mtext> <ns0:mn>4</ns0:mn></ns0:msub> </ns0:mrow> </ns0:math> nanocomposites for in vivo MRI/FLI monitoring the metastasis of gastric cancer.","authors":"Zhihua Yang, Chenying Wang, Shangting Du, Qin Ma, Wei Wang, Changhu Liu, Yonghua Zhan, Wenhua Zhan","doi":"10.1186/s12938-024-01248-6","DOIUrl":"10.1186/s12938-024-01248-6","url":null,"abstract":"<p><strong>Background: </strong>Metastasis is one of the main factors leading to the high mortality rate of gastric cancer. The current monitoring methods are not able to accurately monitor gastric cancer metastasis.</p><p><strong>Methods: </strong>In this paper, we constructed a new type of hollow <math> <mrow><msub><mtext>Mn</mtext> <mn>3</mn></msub> <msub><mtext>O</mtext> <mn>4</mn></msub> </mrow> </math> nanocomposites, <math> <mrow><msub><mtext>Mn</mtext> <mn>3</mn></msub> <msub><mtext>O</mtext> <mn>4</mn></msub> </mrow> </math> @HMSN-Cy7.5-FA, which had a size distribution of approximately 100 nm and showed good stability in different liquid environments. The in vitro magnetic resonance imaging (MRI) results show that the nanocomposite has good response effects to the acidic microenvironment of tumors. The acidic environment can significantly enhance the contrast of <math><msub><mtext>T</mtext> <mn>1</mn></msub> </math> -weighted MRI. The cellular uptake and endocytosis results show that the nanocomposite has good targeting capabilities and exhibits good biosafety, both in vivo and in vitro. In a gastric cancer nude mouse orthotopic metastatic tumor model, with bioluminescence imaging's tumor location information, we realized in vivo MRI/fluorescence imaging (FLI) guided precise monitoring of the gastric cancer orthotopic and metastatic tumors with this nanocomposite.</p><p><strong>Results: </strong>This report demonstrates that <math> <mrow><msub><mtext>Mn</mtext> <mn>3</mn></msub> <msub><mtext>O</mtext> <mn>4</mn></msub> </mrow> </math> @HMSN-Cy7.5-FA nanocomposites is a promising nano-diagnostic platform for the precision diagnosis and therapy of gastric cancer metastasis in the future.</p><p><strong>Conclusions: </strong>In vivo MRI/FLI imaging results show that the nanocomposites can achieve accurate monitoring of gastric cancer tumors in situ and metastases. BLI's tumor location information further supports the good accuracy of MRI/FLI dual-modality imaging. The above results show that the MHCF NPs can serve as a good nano-diagnostic platform for precise in vivo monitoring of tumor metastasis. This nanocomposite provides more possibilities for the diagnosis and therapy of gastric cancer metastases.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"53"},"PeriodicalIF":2.9,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141299953","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":"Towards more precise automatic analysis: a systematic review of deep learning-based multi-organ segmentation.","authors":"Xiaoyu Liu, Linhao Qu, Ziyue Xie, Jiayue Zhao, Yonghong Shi, Zhijian Song","doi":"10.1186/s12938-024-01238-8","DOIUrl":"10.1186/s12938-024-01238-8","url":null,"abstract":"<p><p>Accurate segmentation of multiple organs in the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy. In the past few years, with a data-driven feature extraction approach and end-to-end training, automatic deep learning-based multi-organ segmentation methods have far outperformed traditional methods and become a new research topic. This review systematically summarizes the latest research in this field. We searched Google Scholar for papers published from January 1, 2016 to December 31, 2023, using keywords \"multi-organ segmentation\" and \"deep learning\", resulting in 327 papers. We followed the PRISMA guidelines for paper selection, and 195 studies were deemed to be within the scope of this review. We summarized the two main aspects involved in multi-organ segmentation: datasets and methods. Regarding datasets, we provided an overview of existing public datasets and conducted an in-depth analysis. Concerning methods, we categorized existing approaches into three major classes: fully supervised, weakly supervised and semi-supervised, based on whether they require complete label information. We summarized the achievements of these methods in terms of segmentation accuracy. In the discussion and conclusion section, we outlined and summarized the current trends in multi-organ segmentation.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"52"},"PeriodicalIF":2.9,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11162022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141293105","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":"A novel functional electrical stimulation sleeve based on textile-embedded dry electrodes.","authors":"Baptiste Garnier, Melissa Marquez-Chin, Stephanie DiNunzio, Stephanie N Iwasa, Zia Saadatnia, Hani E Naguib, Milos R Popovic","doi":"10.1186/s12938-024-01246-8","DOIUrl":"10.1186/s12938-024-01246-8","url":null,"abstract":"<p><strong>Background: </strong>Functional electrical stimulation (FES) is a rehabilitation technique that enables functional improvements in patients with motor control impairments. This study presents an original design and prototyping method for a smart sleeve for FES applications. The article explains how to integrate a carbon-based dry electrode into a textile structure and ensure an electrical connection between the electrodes and the stimulator for effective delivery of the FES. It also describes the materials and the step-by-step manufacturing processes.</p><p><strong>Results: </strong>The carbon-based dry electrode is integrated into the textile substrate by a thermal compression molding process on an embroidered conductive matrix. This matrix is composed of textile silver-plated conductive yarns and is linked to the stimulator. Besides ensuring the electrical connection, the matrix improves the fixation between the textile substrate and the electrode. The stimulation intensity, the perceived comfort and the muscle torque generated by the smart FES sleeve were compared to hydrogel electrodes. The results show a better average comfort and a higher average stimulation intensity with the smart FES sleeve, while there were no significant differences for the muscle torque generated.</p><p><strong>Conclusions: </strong>The integration of the proposed dry electrodes into a textile is a viable solution. The wearable FES system does not negatively impact the electrodes' performance, and tends to improve it. Additionally, the proposed prototyping method is applicable to an entire garment in order to target all muscles. Moreover, the process is feasible for industrial production and commercialization since all materials and processes used are already available on the market.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"51"},"PeriodicalIF":3.9,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11149225/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141247323","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":"Automatic detection of epilepsy from EEGs using a temporal convolutional network with a self-attention layer.","authors":"Leen Huang, Keying Zhou, Siyang Chen, Yanzhao Chen, Jinxin Zhang","doi":"10.1186/s12938-024-01244-w","DOIUrl":"10.1186/s12938-024-01244-w","url":null,"abstract":"<p><strong>Background: </strong>Over 60% of epilepsy patients globally are children, whose early diagnosis and treatment are critical for their development and can substantially reduce the disease's burden on both families and society. Numerous algorithms for automated epilepsy detection from EEGs have been proposed. Yet, the occurrence of epileptic seizures during an EEG exam cannot always be guaranteed in clinical practice. Models that exclusively use seizure EEGs for detection risk artificially enhanced performance metrics. Therefore, there is a pressing need for a universally applicable model that can perform automatic epilepsy detection in a variety of complex real-world scenarios.</p><p><strong>Method: </strong>To address this problem, we have devised a novel technique employing a temporal convolutional neural network with self-attention (TCN-SA). Our model comprises two primary components: a TCN for extracting time-variant features from EEG signals, followed by a self-attention (SA) layer that assigns importance to these features. By focusing on key features, our model achieves heightened classification accuracy for epilepsy detection.</p><p><strong>Results: </strong>The efficacy of our model was validated on a pediatric epilepsy dataset we collected and on the Bonn dataset, attaining accuracies of 95.50% on our dataset, and 97.37% (A v. E), and 93.50% (B vs E), respectively. When compared with other deep learning architectures (temporal convolutional neural network, self-attention network, and standardized convolutional neural network) using the same datasets, our TCN-SA model demonstrated superior performance in the automated detection of epilepsy.</p><p><strong>Conclusion: </strong>The proven effectiveness of the TCN-SA approach substantiates its potential as a valuable tool for the automated detection of epilepsy, offering significant benefits in diverse and complex real-world clinical settings.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"50"},"PeriodicalIF":3.9,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11143608/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141186169","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 2023 International Conference on aging, innovation and rehabilitation.","authors":"Babak Taati, Milos R Popovic","doi":"10.1186/s12938-024-01243-x","DOIUrl":"10.1186/s12938-024-01243-x","url":null,"abstract":"","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"23 1","pages":"49"},"PeriodicalIF":3.9,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11106936/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141074613","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}