Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299304
B. Kanat, H. S. Portakal, O. Doluca
In recent years, the hybridization chain reaction (HCR) has been proposed as an alternative to polymerase chain reaction (PCR) for diagnosis. Unfortunately, the sensitivity of the HCR methods are still far below PCR and researchers focus on ways to improve it by investigating different HCR designs. While earlier designs exploit fluorescently labelled probes for detection, here we propose an HCR system that combines G-quadruplex formation and fluorescence for detection of single stranded DNA sequences with concentrations as low as 20 pM. We show that Gquadruplex-mediated oxidation of Amplex Red results in fluorescence increase and lowers the detection limit by about 10fold, in comparison to HCR using only fluorescently labelled HCR probes.
{"title":"Demonstration of G-quadruplex-assisted hybridization chain reaction for nucleic acid detection","authors":"B. Kanat, H. S. Portakal, O. Doluca","doi":"10.1109/TIPTEKNO50054.2020.9299304","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299304","url":null,"abstract":"In recent years, the hybridization chain reaction (HCR) has been proposed as an alternative to polymerase chain reaction (PCR) for diagnosis. Unfortunately, the sensitivity of the HCR methods are still far below PCR and researchers focus on ways to improve it by investigating different HCR designs. While earlier designs exploit fluorescently labelled probes for detection, here we propose an HCR system that combines G-quadruplex formation and fluorescence for detection of single stranded DNA sequences with concentrations as low as 20 pM. We show that Gquadruplex-mediated oxidation of Amplex Red results in fluorescence increase and lowers the detection limit by about 10fold, in comparison to HCR using only fluorescently labelled HCR probes.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125869483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299285
Beyza Bağiröz, E. Doruk, O. Yıldız
Machine learning methods used in the field of bioinformatics are a frequently used solution method in diagnosing, treating and investigating the underlying causes of diseases. In addition, it is an important field of study that allows for the ease of processing, the provision of computational power and the diversity of computational tools specific to the subject, especially in processes that require processing on gene expression and microarray data sets. In this study, an introduction has been made on the use of machine learning methods in the field of bioinformatics gene expression, and the use of machine learning methods has been exemplified by recent studies.
{"title":"Machine Learning In Bioinformatics: Gene Expression And Microarray Studies","authors":"Beyza Bağiröz, E. Doruk, O. Yıldız","doi":"10.1109/TIPTEKNO50054.2020.9299285","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299285","url":null,"abstract":"Machine learning methods used in the field of bioinformatics are a frequently used solution method in diagnosing, treating and investigating the underlying causes of diseases. In addition, it is an important field of study that allows for the ease of processing, the provision of computational power and the diversity of computational tools specific to the subject, especially in processes that require processing on gene expression and microarray data sets. In this study, an introduction has been made on the use of machine learning methods in the field of bioinformatics gene expression, and the use of machine learning methods has been exemplified by recent studies.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123715660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299222
Rahmetullah Varol, Sevde Omeroglu, Z. Karavelioglu, Ela Kumuk, Eda Nur Saruhan, Gizem Aydemir, M. E. Oruc, H. Uvet
This study reports a novel cell classification method based on the observation of trajectories that cells inside a fluidic chamber follow under an externally applied acoustic field. Proposed method is significant both as a cell classification method and as a method for characterizing the motion of various cell lines under different surface acoustic wave patterns. The difference is mainly due to the characteristic differences of cells such as mass, surface adhesiveness, cell stiffness and cellular volume. We discuss the mechanisms that affect the interaction between human colon carcinoma cell line (HCT116), human umbilical vein endothelial cells (HUVECs) and leukocyte cells and surface waves. Classification performance is tested using SVM, max-likelihood and MLP methods and accuracy, sensitivity and specificity values are reported for each. The results indicate that the method can be used as a powerful classifier particularly for cells that are hard to distinguish visually. It is observed that for a given frequency, the motion characteristics of different cell lines differ due to the difference between their mechanical properties for that particular line. This observation can be utilized for the development of a frequency based predictive cell manipulation method that is able to target specific cells using their characteristic frequencies. We discuss the potential of the proposed acoustic stimulation method as a cell manipulation technique.
{"title":"Use of Velocity Vectors for Cell Classification Under Acoustic Drifting Forces","authors":"Rahmetullah Varol, Sevde Omeroglu, Z. Karavelioglu, Ela Kumuk, Eda Nur Saruhan, Gizem Aydemir, M. E. Oruc, H. Uvet","doi":"10.1109/TIPTEKNO50054.2020.9299222","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299222","url":null,"abstract":"This study reports a novel cell classification method based on the observation of trajectories that cells inside a fluidic chamber follow under an externally applied acoustic field. Proposed method is significant both as a cell classification method and as a method for characterizing the motion of various cell lines under different surface acoustic wave patterns. The difference is mainly due to the characteristic differences of cells such as mass, surface adhesiveness, cell stiffness and cellular volume. We discuss the mechanisms that affect the interaction between human colon carcinoma cell line (HCT116), human umbilical vein endothelial cells (HUVECs) and leukocyte cells and surface waves. Classification performance is tested using SVM, max-likelihood and MLP methods and accuracy, sensitivity and specificity values are reported for each. The results indicate that the method can be used as a powerful classifier particularly for cells that are hard to distinguish visually. It is observed that for a given frequency, the motion characteristics of different cell lines differ due to the difference between their mechanical properties for that particular line. This observation can be utilized for the development of a frequency based predictive cell manipulation method that is able to target specific cells using their characteristic frequencies. We discuss the potential of the proposed acoustic stimulation method as a cell manipulation technique.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114382023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299259
A. Kavsaoğlu, V. Demir, Havva Sungur
The aim of this study is to design and develop a system for polymerase chain reaction devices. Temperature is an important criterion for the realization of polymerase chain reactions, which is a simple and precise technique. Equal temperature stability must be achieved on the hopper aluminum block used for the placement of PCR tubes in equal time. By using the Peltier effect of the thermoelectric module, electric energy is converted to heat energy due to the temperature difference between the surfaces. In the study, the Peltier effect is to ensure that the samples placed in the aluminum block are kept at the desired temperature during the desired time. The thermoelectric modules used for this system were operated in heating/cooling modes and the values obtained with the temperature sensor used were drawn as temperature-time graph on the interface screen designed momentarily. PCR devices are commonly used in the areas of DNA amplifications, activation of incubation and cultures, serum coagulation, melting/boiling points, nucleic acid hydridizations, and PCR testing.
{"title":"Heating/Cooling Block System Design with Thermoelectric Module","authors":"A. Kavsaoğlu, V. Demir, Havva Sungur","doi":"10.1109/TIPTEKNO50054.2020.9299259","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299259","url":null,"abstract":"The aim of this study is to design and develop a system for polymerase chain reaction devices. Temperature is an important criterion for the realization of polymerase chain reactions, which is a simple and precise technique. Equal temperature stability must be achieved on the hopper aluminum block used for the placement of PCR tubes in equal time. By using the Peltier effect of the thermoelectric module, electric energy is converted to heat energy due to the temperature difference between the surfaces. In the study, the Peltier effect is to ensure that the samples placed in the aluminum block are kept at the desired temperature during the desired time. The thermoelectric modules used for this system were operated in heating/cooling modes and the values obtained with the temperature sensor used were drawn as temperature-time graph on the interface screen designed momentarily. PCR devices are commonly used in the areas of DNA amplifications, activation of incubation and cultures, serum coagulation, melting/boiling points, nucleic acid hydridizations, and PCR testing.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117042749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299224
Ufuk Tan Baler, A. F. Okyar
Analysis of the mechanical response of the lumbar vertebral body (VB) under certain loading conditions requires a numerical model, which is the building block directly used by finite element method (FEM). Yet, such model comes with drawbacks to deal with in the generation process. The difficulties are related to lacking data integrity provided by subject-specific computed tomography (CT) scan. In order to get through the obstacles, deterministic nature of the parametric computer-aided design (CAD) modeling is adopted. Six parameters, which create a parametric curve on a cross-sectional slice image of a VB; are optimized such that best fits are obtained on fifteen slices grouped as three for each Ll, L2, L3, L4, and L5 VBs. Then, total of 72 construction points necessary to create fifteen contours, in an open-source CAD software called FreeCAD, are transformed from fifteen slice images to a global Cartesian coordinate system (CSYS) by the transformation matrices. After transforming construction points, groups of three contours are lofted to create the lumbar CAD model including only VB section. Finally, this model is compared with another parametric model in terms of Hausdorff distance (HD).
{"title":"A Novel Parametric Approach for Generating Subject Specific Lumbar Vertebral Bodies","authors":"Ufuk Tan Baler, A. F. Okyar","doi":"10.1109/TIPTEKNO50054.2020.9299224","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299224","url":null,"abstract":"Analysis of the mechanical response of the lumbar vertebral body (VB) under certain loading conditions requires a numerical model, which is the building block directly used by finite element method (FEM). Yet, such model comes with drawbacks to deal with in the generation process. The difficulties are related to lacking data integrity provided by subject-specific computed tomography (CT) scan. In order to get through the obstacles, deterministic nature of the parametric computer-aided design (CAD) modeling is adopted. Six parameters, which create a parametric curve on a cross-sectional slice image of a VB; are optimized such that best fits are obtained on fifteen slices grouped as three for each Ll, L2, L3, L4, and L5 VBs. Then, total of 72 construction points necessary to create fifteen contours, in an open-source CAD software called FreeCAD, are transformed from fifteen slice images to a global Cartesian coordinate system (CSYS) by the transformation matrices. After transforming construction points, groups of three contours are lofted to create the lumbar CAD model including only VB section. Finally, this model is compared with another parametric model in terms of Hausdorff distance (HD).","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123837394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299284
Aslan Berk Tüzüner, ve Osman Eroğul, G. Atac, V. Er
Thyroid tumors frequently observed disease by using medical imaging methods. Ultrasonography is the most frequently performed method for diagnosis. To determine, tumor is benign or malign, experienced doctors use various techniques. Fine needle aspiration biopsy and follow-up checking are used for determining type of tumor. However, these methods are time consuming and increasing work load of doctors. So, they created a risk stratification system which has called as ACR-TIRADS. Downside of this system is being subjective and for multiple tumors, it will be time consuming due to analyzing multiple features. To ease, doctors work load and help them to obtain more objective classification, on this study we worked thyroid tumors with texture analysis methods and tried to classify them, to their TIRADS classes. As the result of this study, sensitivity found up %82.8, precision %85 and accuracy found up %73.0.
{"title":"Classification of Ultrasonographic Thyroid Tumor Images to TIRADS Categories via Texture Analysis Methods","authors":"Aslan Berk Tüzüner, ve Osman Eroğul, G. Atac, V. Er","doi":"10.1109/TIPTEKNO50054.2020.9299284","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299284","url":null,"abstract":"Thyroid tumors frequently observed disease by using medical imaging methods. Ultrasonography is the most frequently performed method for diagnosis. To determine, tumor is benign or malign, experienced doctors use various techniques. Fine needle aspiration biopsy and follow-up checking are used for determining type of tumor. However, these methods are time consuming and increasing work load of doctors. So, they created a risk stratification system which has called as ACR-TIRADS. Downside of this system is being subjective and for multiple tumors, it will be time consuming due to analyzing multiple features. To ease, doctors work load and help them to obtain more objective classification, on this study we worked thyroid tumors with texture analysis methods and tried to classify them, to their TIRADS classes. As the result of this study, sensitivity found up %82.8, precision %85 and accuracy found up %73.0.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121749093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299240
C. Kalkandelen, Sena Su, Elif Saatçioğlu, O. Gündüz
Hyaluronic acid (HA) is a linear natural polymer, polysaccharide, with a high water affinity, biocompatible, called glucosaminoglycan. It is the preferred material in bioengineering research with its biodegradability, biodegradability and biofunctionality. In this study, hyaluronic acid was produced by chemical extraction from the rooster needle, which has not been evaluated much in our country. In addition, Fourier Transform Infrared Spectroscopy and Proton Nuclear Magnetic Resonance Spectroscopy analysis of the produced hyaluronic acid was performed. As a result, it has been shown that hyaluronic acid, a product with high added value, can be produced from cock crests by chemical methods.
{"title":"Hyaluronic Acid Production and Analysis from Rooster Comb","authors":"C. Kalkandelen, Sena Su, Elif Saatçioğlu, O. Gündüz","doi":"10.1109/TIPTEKNO50054.2020.9299240","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299240","url":null,"abstract":"Hyaluronic acid (HA) is a linear natural polymer, polysaccharide, with a high water affinity, biocompatible, called glucosaminoglycan. It is the preferred material in bioengineering research with its biodegradability, biodegradability and biofunctionality. In this study, hyaluronic acid was produced by chemical extraction from the rooster needle, which has not been evaluated much in our country. In addition, Fourier Transform Infrared Spectroscopy and Proton Nuclear Magnetic Resonance Spectroscopy analysis of the produced hyaluronic acid was performed. As a result, it has been shown that hyaluronic acid, a product with high added value, can be produced from cock crests by chemical methods.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124471811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299251
M. E. Kütük, M. T. Das, L. Dülger
An exoskeleton for human wrist and forearm rehabilitation has been designed and manufactured. Considering the torque values required for daily life activities, a structural analysis study has been presented. It has three degrees of freedom (DOF) which must be fitted to real human wrist and forearm. Anatomical motion ranges of human limbs have been taken into account during design. IMU has been used in order to get the kinematic values of the limbs and to evaluate the performance level of the therapy. Adapting a six DOF Denso robot to rehabilitation has been completed and experiments have been performed.
{"title":"Robotic Assisted Passive Wrist and Forearm Rehabilitation: Design of an Exoskeleton and Implementation","authors":"M. E. Kütük, M. T. Das, L. Dülger","doi":"10.1109/TIPTEKNO50054.2020.9299251","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299251","url":null,"abstract":"An exoskeleton for human wrist and forearm rehabilitation has been designed and manufactured. Considering the torque values required for daily life activities, a structural analysis study has been presented. It has three degrees of freedom (DOF) which must be fitted to real human wrist and forearm. Anatomical motion ranges of human limbs have been taken into account during design. IMU has been used in order to get the kinematic values of the limbs and to evaluate the performance level of the therapy. Adapting a six DOF Denso robot to rehabilitation has been completed and experiments have been performed.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125431052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299270
Şeyma Yol, G. Tohumoglu
The seizure is a chain of abnormal neurological functions caused by the abnormal electrical discharge of neurons in the brain. The most common is epileptic seizures (ES) which are caused by sudden and uncontrolled electrical discharges in brain cells. A routine 20-minute electroencephalogram (EEG) determines whether the brain’s electrical activity is normal, or the presence of an electrical focus leading to epilepsy. However, the only EEG test by itself is not enough to establish a diagnosis of epileptic seizures. Another seizure known as Psychogenic Nonepileptic Seizures (PNES) is not involuntary electrical abnormal discharges results from psychological conditions rather than brain function. PNES can mimic the many manifestations of epilepsy. The similarity of these two types of seizures poses diagnostic challenges that often lead to delayed diagnosis of PNES. The diagnosis of PNES also involves high-cost hospital admission and monitoring using video-electroencephalogram machines (VEM). Due to economic feasibility and the tediousness of VEM, alternative methods are being researched to differentiate PNES and ES. In this study, we present a summary of the methods and obtained results for epileptic and non-epileptic (pseudo) seizure detection in the literature.
{"title":"EEG Sinyallerinde Epilepsi ve Psödo (sahte) Nöbetlerinin Belirlenmesi: Kısa Derleme Detection Methods of Pseudo and Epileptic Seizures from EEG signals: A Short Review","authors":"Şeyma Yol, G. Tohumoglu","doi":"10.1109/TIPTEKNO50054.2020.9299270","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299270","url":null,"abstract":"The seizure is a chain of abnormal neurological functions caused by the abnormal electrical discharge of neurons in the brain. The most common is epileptic seizures (ES) which are caused by sudden and uncontrolled electrical discharges in brain cells. A routine 20-minute electroencephalogram (EEG) determines whether the brain’s electrical activity is normal, or the presence of an electrical focus leading to epilepsy. However, the only EEG test by itself is not enough to establish a diagnosis of epileptic seizures. Another seizure known as Psychogenic Nonepileptic Seizures (PNES) is not involuntary electrical abnormal discharges results from psychological conditions rather than brain function. PNES can mimic the many manifestations of epilepsy. The similarity of these two types of seizures poses diagnostic challenges that often lead to delayed diagnosis of PNES. The diagnosis of PNES also involves high-cost hospital admission and monitoring using video-electroencephalogram machines (VEM). Due to economic feasibility and the tediousness of VEM, alternative methods are being researched to differentiate PNES and ES. In this study, we present a summary of the methods and obtained results for epileptic and non-epileptic (pseudo) seizure detection in the literature.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130196288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299275
M. B. Terzi, V. Arikan
In this study, a new technique which detects anomalies in skin sympathetic nerve activity (SKNA) and ECG by using state-of- the-art signal processing and machine learning methods is developed to perform the robust detection of myocardial infarction (MI). For this purpose, a signal processing technique that simultaneously obtains SKNA and ECG from wideband recordings on PTB-EKG database is developed. By using preprocessed data, a novel feature extraction technique which obtains SKNA features that are critical for the reliable detection of MI is developed. By using extracted features, a supervised learning technique based on artificial neural network (ANN) and an unsupervised learning technique based on Gaussian mixture model (GMM) are developed to perform the robust detection of SKNA anomalies. A Neyman-Pearson type of approach is developed to perform the robust detection of outliers that correspond to MI. The performance results of the proposed technique over PTB-EKG database showed that the technique provides highly reliable detection of MI by performing the robust detection of SKNA anomalies. Therefore, in cases where the diagnostic information of ECG is not sufficient for the reliable diagnosis of MI, the proposed technique can provide early diagnosis of the disease, which can lead to a significant reduction in the mortality rates of cardiovascular diseases.
{"title":"Detection of Myocardial Infarction using Autonomic Nervous System, Gaussian Mixture Model and Artificial Neural Network","authors":"M. B. Terzi, V. Arikan","doi":"10.1109/TIPTEKNO50054.2020.9299275","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299275","url":null,"abstract":"In this study, a new technique which detects anomalies in skin sympathetic nerve activity (SKNA) and ECG by using state-of- the-art signal processing and machine learning methods is developed to perform the robust detection of myocardial infarction (MI). For this purpose, a signal processing technique that simultaneously obtains SKNA and ECG from wideband recordings on PTB-EKG database is developed. By using preprocessed data, a novel feature extraction technique which obtains SKNA features that are critical for the reliable detection of MI is developed. By using extracted features, a supervised learning technique based on artificial neural network (ANN) and an unsupervised learning technique based on Gaussian mixture model (GMM) are developed to perform the robust detection of SKNA anomalies. A Neyman-Pearson type of approach is developed to perform the robust detection of outliers that correspond to MI. The performance results of the proposed technique over PTB-EKG database showed that the technique provides highly reliable detection of MI by performing the robust detection of SKNA anomalies. Therefore, in cases where the diagnostic information of ECG is not sufficient for the reliable diagnosis of MI, the proposed technique can provide early diagnosis of the disease, which can lead to a significant reduction in the mortality rates of cardiovascular diseases.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133302241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：