{"title":"Optimizing alginate tubes for cell culture","authors":"Jack Rauch , Emily Francis , Hendrik Viljoen","doi":"10.1016/j.bea.2024.100113","DOIUrl":"10.1016/j.bea.2024.100113","url":null,"abstract":"<div><p>Cells can be cultured to very high densities in hollow alginate tubes (<span><math><mrow><mn>5</mn><mo>−</mo><mn>10</mn><mspace></mspace><mo>×</mo><mspace></mspace><msup><mrow><mn>10</mn></mrow><mn>8</mn></msup><mrow><mspace></mspace><mi>c</mi><mi>e</mi><mi>l</mi><mi>l</mi><mi>s</mi><mo>/</mo><mi>m</mi><mi>L</mi><mo>)</mo><mo>,</mo></mrow></mrow></math></span> with the provisothat their nutrient and oxygen needs are met. After the tubes have been extruded, they are suspended in growth medium. Nutrients and metabolic products pass readily through the alginate tube walls and the cells grow from small aggregates until they fill the hollow space in the tube. A mathematical model is presented of nutrient and oxygen transport between the bulk phase and the tubes. Our main result is a necessary condition for growing cells to confluency. It sets an upper limit on the inner tube diameter. This limit depends on the alginate wall thickness, transport properties and consumption rates. Experimental results are reported for <span>l</span>-Wnt-3a cells, which have been expanded in tubes with inner diameters of <span><math><mrow><mn>400</mn><mo>,</mo><mspace></mspace><mn>500</mn><mo>,</mo><mspace></mspace><mn>600</mn><mspace></mspace></mrow></math></span>and <span><math><mrow><mn>700</mn><mspace></mspace><mi>μ</mi><mi>m</mi></mrow></math></span>. For our experimental set-up, glucose was the limiting nutrient. Cells reached confluency in <span><math><mrow><mn>400</mn><mspace></mspace><mi>a</mi><mi>n</mi><mi>d</mi><mspace></mspace><mn>500</mn><mspace></mspace><mi>μ</mi><mi>m</mi></mrow></math></span> tubes at bulk glucose concentrations of <span><math><mrow><mn>20</mn><mspace></mspace><mi>m</mi><mi>M</mi></mrow></math></span>. When the bulk glucose concentration was increased to 25, 30 and 35 mM, confluency was reached in <span><math><mrow><mn>600</mn><mspace></mspace><mi>μ</mi><mi>m</mi></mrow></math></span> tubes for all three cases. Confluency was not achieved in tubes with inner diameters of 700 um, even at the elevated glucose concentrations, suggesting that the dissolved oxygen concentration has become the limiting factor. These results match the model predictions well and confirms that the model can be used to select tube dimensions.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100113"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000021/pdfft?md5=050937ef7b2cb9ac0459ebbdcd8443ef&pid=1-s2.0-S2667099224000021-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139631365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Understanding fibrosis: Mechanisms, clinical implications, current therapies, and prospects for future interventions","authors":"Jennifer C. Ku , Jacob Raiten , Yong Li","doi":"10.1016/j.bea.2024.100118","DOIUrl":"https://doi.org/10.1016/j.bea.2024.100118","url":null,"abstract":"<div><p>Fibrosis is a prevalent and detrimental condition associated with various diseases with a high impact on global morbidity and mortality rates. Despite its diverse causes and affected organs, common underlying mechanisms drive the development and progression of the disease. These mechanisms include an exaggerated inflammatory response, excessive activation of fibroblasts, and abnormal tissue remodeling following severe or repetitive tissue injury. Although significant advancements have been achieved to enhance our understanding of fibrosis, there is still a gap between identifying potential antifibrotic targets and successfully translating them into effective clinical interventions. Novel approaches that target specific cellular and molecular processes involved in fibrosis hold promise for reducing the pathological consequences of the disease. Understanding the pathogenesis and clinical implications of fibrotic diseases is crucial for developing effective therapeutic strategies and improving patient outcomes. In this review, we introduce the concept of fibrosis, discuss the mechanisms by which it arises, and explore existing and emerging therapeutic approaches in development.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100118"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000070/pdfft?md5=19c16f4e8297ced0f648e3f808d2b978&pid=1-s2.0-S2667099224000070-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140134131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Covalent surface immobilization on metal implants: Key aspects on post-synthesis characterization","authors":"Luna Sánchez-López","doi":"10.1016/j.bea.2023.100111","DOIUrl":"https://doi.org/10.1016/j.bea.2023.100111","url":null,"abstract":"<div><p>A variety of methodologies have been applied for characterizing covalent immobilizations of biomolecules and other compounds on metal implant surfaces, due to the positive impact of functionalization and the enhancement of biomimetic signaling at covalently immobilized biomaterial surfaces. However, current challenges should be addressed, as both physically adsorbed and covalently immobilized molecules usually coexist on functionalized surfaces and covalent immobilization efficiencies greatly vary among works, in which the immobilized biomolecule size seems a determinant parameter of the efficiency.</p><p>Discrimination of the irreversible-bound covalent fraction should be assessed and advanced techniques for surface characterization must be conducted, such as quartz crystal microbalance or photon induced spectroscopy, as evaluation criteria. Verification of biomolecule activity once it is covalently immobilized on metal substrates is also required. Long-term stability and degradation resistances studies are also highly recommended for obtention of long-lasting, biomimetic-active surfaces upon covalent functionalization of metal biomaterials for medical applications.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100111"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099223000403/pdfft?md5=3dc2be95953b8dae1217be65efdaa826&pid=1-s2.0-S2667099223000403-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139100253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yijun Zhou , Benedikt Helgason , Stephen J. Ferguson , Cecilia Persson
{"title":"Validated, high-resolution, non-linear, explicit finite element models for simulating screw - bone interaction","authors":"Yijun Zhou , Benedikt Helgason , Stephen J. Ferguson , Cecilia Persson","doi":"10.1016/j.bea.2024.100115","DOIUrl":"https://doi.org/10.1016/j.bea.2024.100115","url":null,"abstract":"<div><h3>Background and Objective</h3><p>Primary stability evaluation of screw implants through pull-out or push-in experiments is commonly used to investigate the mechanism of screw loosening. Numerical models simulating these testing methods could provide an enhanced understanding of the underlying attachment mechanisms as well as save time and cost in the development of new screws. However, previous numerical models have been limited by compromises between modelling the trabecular structure at high resolution versus incorporating sophisticated mechanical properties and boundary conditions, leading to overestimated mechanical performance. The aim of this study was to overcome these limitations.</p></div><div><h3>Methods</h3><p>We developed explicit models incorporating the microstructure of trabecular bone, with frictional contact, and a non-linear material model incorporating damage. One model digitally inserted the screw into the trabecular bone structure using Boolean operations, while another model simulated the screw's rotational insertion.</p></div><div><h3>Results</h3><p>The results showed a strong correlation between numerical and experimental results (<em>R</em><sup>2</sup>: 0.54–0.93) for force-displacement response in terms of stiffness and strength. We found that the damage induced by the screw insertion process is an important factor to be considered, as the absence of modelling it led to an overestimated stiffness in previous studies.</p></div><div><h3>Conclusions</h3><p>The study highlights the importance of including frictional contact and also identified screw insertion damage as an important part of the simulating screw-bone interaction. Our findings demonstrate the potential of explicit finite element models for accurately replicating experimental push-in results and optimizing orthopaedic screws. The code is available at <span>https://github.com/zhou436/Bone-Screw-Constructs-eFEM</span><svg><path></path></svg>.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100115"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000045/pdfft?md5=30c2d7c3983b082c023234f6e80bba85&pid=1-s2.0-S2667099224000045-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139945129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reliable quality of R-phycoerythrin derived from Portieria hornemannii for effective antioxidant, antibacterial, and anticancer activity","authors":"Saranya Karuppannan , Mani Sivakumar , Balasubramani Govindasamy , Santhosh Chinnaraj , Viji Maluventhan , Maruthupandian Arumugam","doi":"10.1016/j.bea.2024.100116","DOIUrl":"https://doi.org/10.1016/j.bea.2024.100116","url":null,"abstract":"<div><p>The phycobiliprotein is a light-harvesting fluorescent probe; Phycoerythrin is a pigment used in many industrial, and pharmaceutical applications; including fluorescence resonance energy transfer and flow cytometry. The main objective of the current study was purifying the phycoerythrin in <em>Portieria hornemannii</em>. The phycoerythrin pigment was dialyzed commonly using Q sepharose, but it is high cost. However, the alternative method is DEAE-Sephadex is cost-effective, high- yield, pure compound, and has high activity performance. Then the R-Phycoerythrin (R-PE) compound was extracted in 0.02 M of phosphate buffer (pH–7.2). R-PE investigated the FT-IR, HPLC, SDS-PAGE and including physico-chemical properties. Then the purified R-PE compound was evaluated by an antibacterial, antioxidant, and anticancer activity. The R-Phycoerythrin was showing a maximum inhibition effect of high concentration (IC<sub>50</sub>value 77.98 µg/ml) against the colon cancer HT-29 cell line.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100116"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000057/pdfft?md5=002935a3085e505b6e3bda709475f7f0&pid=1-s2.0-S2667099224000057-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140162705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ejay Nsugbe , Oluwarotimi Williams Samuel , Mojisola Grace Asogbon , Jose Javier Reyes-Lagos
{"title":"A pilot on the use of stride cadence for the characterization of walking ability in lower limb amputees","authors":"Ejay Nsugbe , Oluwarotimi Williams Samuel , Mojisola Grace Asogbon , Jose Javier Reyes-Lagos","doi":"10.1016/j.bea.2024.100117","DOIUrl":"https://doi.org/10.1016/j.bea.2024.100117","url":null,"abstract":"<div><p>Amputations are a prominent affliction that occur worldwide, with causes ranging from congenital, disease-based, or external reasons such as trauma. Prosthesis provides the closest alternative functional replacement to the loss of a limb. Before any form of rehabilitation support can be offered to amputee patients, an assessment of their degree and level of mobility first needs to be evaluated using the K-level grading system. The typical means towards the assigning of a K-level grading is through qualitative methods, which have been criticized for being subjective and, at times, imprecise. As a means towards remedying this shortcoming, we investigated the prospect of utilizing data from wearable sensors for analyzing the stride pattern and cadence of various subjects towards the quantitative inference of a K-level. This was accomplished using data from accelerometers, alongside advanced signal processing and machine learning models, towards the quantitative identification and differentiation of the various K-levels of amputees of varied levels of mobility. The experimental results showed that this aim could be accomplished under the circumstance investigated and the models applied as part of this research. Additional analysis was also done on the use of data from accelerometers towards the differentiation between amputated and non-amputated subjects, which showed that the cohorts could be classified and differentiated using purely accelerometer data and the accompanying postprocessing methods.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100117"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000069/pdfft?md5=6108080486d7a798af1f8c86bd34967f&pid=1-s2.0-S2667099224000069-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139936197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Samit Hasan , Tanvir Pantha, Muhammad Abdullah Arafat
{"title":"Design and development of a cost-effective portable IoT enabled multi-channel physiological signal monitoring system","authors":"Samit Hasan , Tanvir Pantha, Muhammad Abdullah Arafat","doi":"10.1016/j.bea.2024.100124","DOIUrl":"10.1016/j.bea.2024.100124","url":null,"abstract":"<div><p>In health care, early detection of diseases is important in order to increase survival rates. Regular monitoring of vital signs is necessary for the early detection of health issues. Due to the high cost, inadequacy, and complexity of monitoring devices, it is challenging for individuals to check their vital signs at home. Consequently, a cost-effective, broadly accessible, and easy-to-use system is necessary for health monitoring. For this purpose, we developed a portable and wireless acquisition electronic device to help patients record physiologically relevant signals such as ECG, EMG, EEG, and EOG for continuous monitoring. The key components of the acquisition system are a portable device, a Wi-Fi router, a SQL server, and a graphical user interface (GUI). In this study, a cost-effective, fairly low-power Internet-of-Things (IoT)-based health monitoring system was built employing a portable device incorporating analog front ends (AFE) and the ESP 32 Wroom-32. Continuous remote monitoring and diagnostics are made possible by including IoT in the architecture. In the proposed monitoring system, the lightweight Message Queue Telemetry Transport (MQTT) protocol was used. A GUI is constructed that shows near-real-time data in a web browser and can be accessed from any operating system. The accuracy of the acquired signals was validated by comparing the individual’s ECG recorded in a remote device through the IoT cloud with a conventional biomedical certified ECG machine. The AFEs were built and evaluated based on the amplitude and bandwidth of ECG, EMG, EEG, and EOG signals. The cost and power analysis, as well as other key parameters are presented. Compared to similar existing boards, our developed system demonstrates high configurable sampling frequency, high Common Mode Rejection Ratio (CMRR) and high transmission throughput with no packet loss while costing significantly less and consuming moderate power. This makes the proposed system suited for the acquisition of multichannel physiological signals for home applications.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100124"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000136/pdfft?md5=e7c65edbbf308424060687ea71e1e269&pid=1-s2.0-S2667099224000136-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141035685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Validation of upper extremity kinematics using Markerless motion capture","authors":"Robyn M. Hansen, Sara L. Arena, Robin M. Queen","doi":"10.1016/j.bea.2024.100128","DOIUrl":"https://doi.org/10.1016/j.bea.2024.100128","url":null,"abstract":"<div><p>Movement research has typically been performed using three-dimensional (3D) marker-based motion capture, which is considered the “gold-standard” for biomechanical assessment. However, limitations exist due to the lack of portability, extensive preparation for data collection, marker placement training, error due to marker movement, and possible skin irritation due to marker adhesives. There is inherent error due to motion artifact stemming from skin movement and differences in marker placement between testers. Markerless motion capture systems are emerging as a new method of kinematic assessment. These methods require little preparation and there is no need to alter participant clothing. Markerless motion capture has also been validated for the lower extremity in healthy older adults during gait. However, it has not been validated for other populations or for the assessment of upper extremity (UE) motion. Therefore, the purpose of this study was to examine differences in calculated UE kinematics between marker-based and a markerless motion capture system. Participants attended two data collection sessions. Marker-based and markerless motion capture data was collected simultaneously while participants completed the Box and Blocks test (BBT). Kinematic and spatiotemporal data from both systems was exported using identical time series to ensure the same conditions for comparisons. Intraclass Correlation Coefficients (ICCs) were calculated to determine between session reliability for both systems on range of motion and peak joint angular data to ensure movement variability was not affecting measurement consistency. ICCs and Bland Altman statistics were also calculated between the systems. Root mean square deviation (RMSD) values were determined between demeaned UE joint angles for the two systems to examine movement pattern differences. The resulting between-session ICCs for each system showed that the markerless system shared similar reliability during this task as the marker-based system, further supporting the effect of variability on between-session reliability. Between-system ICCs resulted in good (0.7<ICC<0.9) to excellent (ICC>0.9) agreement. Bland Altman results confirmed the existence of measurement bias between the systems. RMSD values for all UE joint angles were found to be less than 6°. Overall, the results from this study support the use of markerless motion capture in clinical settings to examine upper extremity biomechanics in children.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100128"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000173/pdfft?md5=84d5e0cc6b0b70cec79906a42f262a8e&pid=1-s2.0-S2667099224000173-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141240762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Aspects of conceptualization, development, and simulation of an extracellular vesicles' bulk isolation device for cosmetic and therapeutic applications","authors":"Franck M Senda, Gilles C Roy","doi":"10.1016/j.bea.2024.100125","DOIUrl":"https://doi.org/10.1016/j.bea.2024.100125","url":null,"abstract":"<div><p>This paper discusses the concept and model to develop a prototype extracellular vesicle bulk-isolation device (EBID). It proposes an engineering design and potential ways to mitigate limitations in the currently available extracellular vesicle (EV) isolation techniques. A more convenient isolation technique is developed and presented to ensure production-scale isolation and purification of the specific size of EV (approximately 0.1 to 0.34 µm) from a large quantity of cell-culture media or biological fluid sources. A more appropriate design concept was established based on the chitosan-assisted precipitation of EV techniques and the membrane filtration technology-based prototype. After that, a novel theoretical model for bulk isolation of EVs was developed and presented using pressure-driven circulation and particulate flow in the EBID loop, where the EV production results from the biofluid flowing through the EBID membrane filter module (MFM). Governing equations are coupled with Darcy's law to investigate the biofluid flow behavior in the EBID MFM, therefore simulating the isolation process of EVs from their biofluids. The flow characteristics of the EV isolation process within the EBID MFM are theoretically simulated and discussed for improved isolation yield with a high degree of quality and purity.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100125"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000148/pdfft?md5=84dd2e142c95fd087f8ef103ffa3c9e4&pid=1-s2.0-S2667099224000148-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140950735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Determining Diagnostic Utility of EEG for Assessing Stroke Severity using Deep Learning Models","authors":"Shatakshi Singh , Dimple Dawar , Esha Mehmood , Jeyaraj Durai Pandian , Rajeshwar Sahonta , Subhash Singla , Amit Batra , Cheruvu Siva Kumar , Manjunatha Mahadevappa","doi":"10.1016/j.bea.2024.100121","DOIUrl":"10.1016/j.bea.2024.100121","url":null,"abstract":"<div><p>Stroke has become a leading cause of disability worldwide. Early medication and rehabilitation is the key to help post-stroke survivors recover faster. Presently, doctors rely on imaging modalities like CT/MRI for diagnosing stroke patients. The diagnosis done using these modalities can be highly subjective. Apart from this, these imaging modalities are very costly, time taking and inconvenient for the patients. So there is a need of faster, portable and an automated diagnostic system for assessing post-stroke conditions so that right measures can be taken in the right time. To cater to this need EEG comes in handy because of its portable nature. So, in this work, utility of EEG has been studied to diagnose three aspects of stroke: 1) type of stoke, 2) affected artery and 3) severity of stroke. To achieve this, one-minute resting state EEG data was used to extract 57 features. The features were ranked and selected using ranking algorithm and deep learning (DL) models were trained with supervision from information extracted using MRI data. To find out type of stroke and affected artery DWI, SWI and MRA images were used, and severity of stroke was recorded in terms of NIHSS score. Three different DL models were trained for each task i.e. type of stroke, affected artery and severity of stroke. For classifying type of stroke an accuracy of 97.74% was obtained using 37 features. For stroke severity, the model gave RMSE of 2.1955 with a high correlation value (r = 0.91). The DL model for classifying affected artery used 33 features and gave accuracy of 95.7%. It was also found that less complex time domain features and QEEG features were frequently selected out of 57 features for all the DL models. Features in delta and theta sub-bands were frequently selected along with QEEG features. The work presented here established that EEG can act as a reliable modality for faster diagnosis of stroke specifics and hence can help medical professionals in speeding the decision making process.</p></div>","PeriodicalId":72384,"journal":{"name":"Biomedical engineering advances","volume":"7 ","pages":"Article 100121"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667099224000100/pdfft?md5=530698daff608a0818105c4a51e13276&pid=1-s2.0-S2667099224000100-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140398406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}