Pub Date : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835370
Rashid Al Mukaddim, J. Shan, Irteza Enan Kabir, Abdullah Salmon Ashik, Rasheed Abid, Zhennan Yan, Dimitris N. Metaxas, B. Garra, Kazi Khairul Islam, S. Alam
Accurate segmentation of breast lesions is among the several challenges in the development of a fully automatic Computer-Aided Diagnosis system for solid breast mass classification. Many high level segmentation methods rely heavily on proper initialization and the seed point selection is usually the necessary first step. In this paper, a fully automatic and robust seed point selection method is proposed. The method involves a number of processing steps in both space and frequency domain and endeavors to incorporate the breast anatomical knowledge. Using a database of 498 images, we compared the proposed method with two other state-of-the-art methods; the proposed method outperforms both methods significantly with a success rate of 62.85% vs. 44.97% and 13.05% on seed point select.
{"title":"A novel and robust automatic seed point selection method for breast ultrasound images","authors":"Rashid Al Mukaddim, J. Shan, Irteza Enan Kabir, Abdullah Salmon Ashik, Rasheed Abid, Zhennan Yan, Dimitris N. Metaxas, B. Garra, Kazi Khairul Islam, S. Alam","doi":"10.1109/MEDITEC.2016.7835370","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835370","url":null,"abstract":"Accurate segmentation of breast lesions is among the several challenges in the development of a fully automatic Computer-Aided Diagnosis system for solid breast mass classification. Many high level segmentation methods rely heavily on proper initialization and the seed point selection is usually the necessary first step. In this paper, a fully automatic and robust seed point selection method is proposed. The method involves a number of processing steps in both space and frequency domain and endeavors to incorporate the breast anatomical knowledge. Using a database of 498 images, we compared the proposed method with two other state-of-the-art methods; the proposed method outperforms both methods significantly with a success rate of 62.85% vs. 44.97% and 13.05% on seed point select.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124445485","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835377
Md. Abu Saleh Tajin, Mohsin Ahmed, P. K. Saha
This paper proposes an Ultra Wideband Microstrip Patch Antenna for Wireless Capsule Endoscopy. An approximate model of the human gastrointestinal environment is designed with CST Microwave Studio, and the antenna is placed in the center. The antenna is small and bent in a fashion so that it can easily be accommodated inside a capsule. Ultra Wideband technology facilitates higher data rate, resulting in faster communication and high-quality images. Reflection Coefficient (S11), SAR, radiation pattern and power consumption are studied
{"title":"Performance analysis of an Ultra Wideband Antenna for Wireless Capsule Endoscopy","authors":"Md. Abu Saleh Tajin, Mohsin Ahmed, P. K. Saha","doi":"10.1109/MEDITEC.2016.7835377","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835377","url":null,"abstract":"This paper proposes an Ultra Wideband Microstrip Patch Antenna for Wireless Capsule Endoscopy. An approximate model of the human gastrointestinal environment is designed with CST Microwave Studio, and the antenna is placed in the center. The antenna is small and bent in a fashion so that it can easily be accommodated inside a capsule. Ultra Wideband technology facilitates higher data rate, resulting in faster communication and high-quality images. Reflection Coefficient (S11), SAR, radiation pattern and power consumption are studied","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123417620","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835390
S. I. Khan, A. S. M. L. Hoque
Misspelling of names is a major problem of real world datasets and a single person is identified differently as its consequence. In Bangladesh, it is common that many people, in real, do not know their full name and many of Bangladeshi citizens are unable to pronounce their name correctly, even in the mother tongue. The Same person provides a different version of their name during taking a public service e.g., treatment in hospital. In almost all healthcare centers, a patient is asked and he reports his demographic data i.e. name, age, etc. orally. This creates ambiguity with misspelled names. In this paper, we have provided an algorithm to identify the same person correctly from the variation of names. Experimental results show that our proposed technique can successfully link records with high accuracy for noisy data like misspelled patient names etc.
{"title":"Similarity analysis of patients' data: Bangladesh perspective","authors":"S. I. Khan, A. S. M. L. Hoque","doi":"10.1109/MEDITEC.2016.7835390","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835390","url":null,"abstract":"Misspelling of names is a major problem of real world datasets and a single person is identified differently as its consequence. In Bangladesh, it is common that many people, in real, do not know their full name and many of Bangladeshi citizens are unable to pronounce their name correctly, even in the mother tongue. The Same person provides a different version of their name during taking a public service e.g., treatment in hospital. In almost all healthcare centers, a patient is asked and he reports his demographic data i.e. name, age, etc. orally. This creates ambiguity with misspelled names. In this paper, we have provided an algorithm to identify the same person correctly from the variation of names. Experimental results show that our proposed technique can successfully link records with high accuracy for noisy data like misspelled patient names etc.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131937432","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835395
Shuvashis Das Gupta, K. S. Rabbani, Z. Mahbub
This work is focused on the quantitative study of Magnetic Resonance Imaging (MRI) for the purpose of identification of brain tumor by apparent diffusion coefficient (ADC) calculations of Diffusion-weighted images (DWI). Such diffusion-based measurements of cellular response can provide additional quantitative information for tissue characterization that strengthens the diagnosis carried out by conventional T1 and T2 weighted MRI. Initially, the DWI protocol were implemented on different test subjects with 6 sets of diffusion weighting factor by using a 3T MR scanner at National Institute of Neuroscience, Dhaka, Bangladesh. Afterward, based on the discussion with radiologists and specialists, two subjects (subject number 2 and 5) with suspected brain tumor were selected from the previous pool; ADC calculations were performed on the tumor region and the normal tissues on the symmetric region of the tumor on the other hemisphere. The comparison revealed a significant difference in ADC values of both regions, thus indicating a successful detection of the brain tumor. Such quantitative analysis provides a broader diagnostic scope as an addition with routine anatomical MRI and could play a crucial role in the treatment planning for pre and post-operative condition.
{"title":"Brain tumor identification through microstructure study using MRI","authors":"Shuvashis Das Gupta, K. S. Rabbani, Z. Mahbub","doi":"10.1109/MEDITEC.2016.7835395","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835395","url":null,"abstract":"This work is focused on the quantitative study of Magnetic Resonance Imaging (MRI) for the purpose of identification of brain tumor by apparent diffusion coefficient (ADC) calculations of Diffusion-weighted images (DWI). Such diffusion-based measurements of cellular response can provide additional quantitative information for tissue characterization that strengthens the diagnosis carried out by conventional T1 and T2 weighted MRI. Initially, the DWI protocol were implemented on different test subjects with 6 sets of diffusion weighting factor by using a 3T MR scanner at National Institute of Neuroscience, Dhaka, Bangladesh. Afterward, based on the discussion with radiologists and specialists, two subjects (subject number 2 and 5) with suspected brain tumor were selected from the previous pool; ADC calculations were performed on the tumor region and the normal tissues on the symmetric region of the tumor on the other hemisphere. The comparison revealed a significant difference in ADC values of both regions, thus indicating a successful detection of the brain tumor. Such quantitative analysis provides a broader diagnostic scope as an addition with routine anatomical MRI and could play a crucial role in the treatment planning for pre and post-operative condition.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128004937","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}
Human being faces numerous types of neurological disorders. Among them epilepsy is the most frequent after stroke. Several techniques have been developed to identify seizure using EEG signals. The basic contribution of those works can be broadly categorized in three different areas: pre-processing, feature extraction and classification. In this work, we systematically compare different features and their fusions. We have explored how different features and fusions are performing for different cases of seizure classification. We have also investigated how specific combination of features and classifier can outperform others. In addition, we have also observed how information is distributed across different frequency bands for different cases of seizure classifications. Our detailed experimental results illustrate how we can obtain maximum performance by integrating both time and frequency (wavelet) domain features together with specific classifier.
{"title":"Seizure detection system: A comparative study on features and fusions","authors":"M.K.M. Rahman, Md.A.Mannan Joadder, Tanvir Ahammed Ashique","doi":"10.1109/MEDITEC.2016.7835389","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835389","url":null,"abstract":"Human being faces numerous types of neurological disorders. Among them epilepsy is the most frequent after stroke. Several techniques have been developed to identify seizure using EEG signals. The basic contribution of those works can be broadly categorized in three different areas: pre-processing, feature extraction and classification. In this work, we systematically compare different features and their fusions. We have explored how different features and fusions are performing for different cases of seizure classification. We have also investigated how specific combination of features and classifier can outperform others. In addition, we have also observed how information is distributed across different frequency bands for different cases of seizure classifications. Our detailed experimental results illustrate how we can obtain maximum performance by integrating both time and frequency (wavelet) domain features together with specific classifier.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"17 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132192673","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835392
Abu Shafin Mohammad Mahdee Jameel, M. Mace, Shouyan Wang, R. Vaidyanathan, K. Mamun
The use of Deep Brain Local Field Potentials (LFP) in the process of connecting the human brain with artificial devices is one of the most promising fields in neural engineering. Inner mechanisms of our the central nervous system (CNS) can be understood through the study of LFPs. Of special importance are the the LFPs that come from subthalamic nucleus (STN) as they are related to the preparation, execution and imaging of movements. While researchers have focused on decoding movements and its laterality, left or right sided visually cued movements from STN LFPs, there is scope for using the same information for prediction of movements and laterality. In this paper, an algorithm is proposed that can be used to predict movement and laterality using STN LFPs. For this, wavelet packet transform (WPT) is used to generate separated frequency components of the LFPs. Then a selection of time and frequency domain features are used, namely time window based power features, causality features computed using granger causality and cross correlation, and frequency domain features computed using discrete cosine transform (DCT). Utilizing a weighted sequential feature selection process (WSFS), promising results are obtained from a Bayesian classifier along with cross validation procedure.
{"title":"Predicting movement and laterality from Deep Brain Local Field Potentials","authors":"Abu Shafin Mohammad Mahdee Jameel, M. Mace, Shouyan Wang, R. Vaidyanathan, K. Mamun","doi":"10.1109/MEDITEC.2016.7835392","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835392","url":null,"abstract":"The use of Deep Brain Local Field Potentials (LFP) in the process of connecting the human brain with artificial devices is one of the most promising fields in neural engineering. Inner mechanisms of our the central nervous system (CNS) can be understood through the study of LFPs. Of special importance are the the LFPs that come from subthalamic nucleus (STN) as they are related to the preparation, execution and imaging of movements. While researchers have focused on decoding movements and its laterality, left or right sided visually cued movements from STN LFPs, there is scope for using the same information for prediction of movements and laterality. In this paper, an algorithm is proposed that can be used to predict movement and laterality using STN LFPs. For this, wavelet packet transform (WPT) is used to generate separated frequency components of the LFPs. Then a selection of time and frequency domain features are used, namely time window based power features, causality features computed using granger causality and cross correlation, and frequency domain features computed using discrete cosine transform (DCT). Utilizing a weighted sequential feature selection process (WSFS), promising results are obtained from a Bayesian classifier along with cross validation procedure.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132877542","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835358
Ahmed Imteaj, Muhammad Kamrul Hossain
Nowadays, smartphones have reached every hand and every home. As a result, people are making use of the beneficial mobile applications to make their everyday life easier. This paper focuses on development of a mobile application(app) to help providing an effective health care system. Using this app people can get numerous benefits like finding hospital information in the city, information about cabin, cabin booking with payment, intelligent suggestion on choosing suitable hospital, finding a doctor, emergency service calling, first aid information, alarm system for medication, Body Mass Index(BMI) calculator etc. This application will be a helping hand for people who find it difficult to select hospital, book cabin, contacting doctor for appointment or seeking help in emergency situation. Besides, it will help the masses in their everyday life by providing health care information, aid and medication information, medicine reminder system, etc.
{"title":"A smartphone based application to improve the health care system of Bangladesh","authors":"Ahmed Imteaj, Muhammad Kamrul Hossain","doi":"10.1109/MEDITEC.2016.7835358","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835358","url":null,"abstract":"Nowadays, smartphones have reached every hand and every home. As a result, people are making use of the beneficial mobile applications to make their everyday life easier. This paper focuses on development of a mobile application(app) to help providing an effective health care system. Using this app people can get numerous benefits like finding hospital information in the city, information about cabin, cabin booking with payment, intelligent suggestion on choosing suitable hospital, finding a doctor, emergency service calling, first aid information, alarm system for medication, Body Mass Index(BMI) calculator etc. This application will be a helping hand for people who find it difficult to select hospital, book cabin, contacting doctor for appointment or seeking help in emergency situation. Besides, it will help the masses in their everyday life by providing health care information, aid and medication information, medicine reminder system, etc.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114973165","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835361
K. Wahid, S. Kabir, Haider Adnan Khan, Abduallh Al Helal, M. A. Mukit, R. Mostafa
Wireless Capsule Endoscopy (WCE) has emerged as a popular non-invasive imaging tool for inspection of human Gastrointestinal (GI) tract. In order to identify the location of an anomaly or intestinal disease, the physicians need to know the exact location of the endoscopic capsule which influences the treatment plan. In this paper, we present a displacement estimation technique based on feature point tracking which utilizes the images captured by a commercial capsule, named PillCam. The proposed displacement calculation approach is tested using a virtual testbed. Results show that, with assistance of ASIFT-RANSAC algorithms, the proposed algorithm is able to estimate the linear displacement of the endoscopic capsule with an accuracy of 93.7% on average.
{"title":"A localization algorithm for capsule endoscopy based on feature point tracking","authors":"K. Wahid, S. Kabir, Haider Adnan Khan, Abduallh Al Helal, M. A. Mukit, R. Mostafa","doi":"10.1109/MEDITEC.2016.7835361","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835361","url":null,"abstract":"Wireless Capsule Endoscopy (WCE) has emerged as a popular non-invasive imaging tool for inspection of human Gastrointestinal (GI) tract. In order to identify the location of an anomaly or intestinal disease, the physicians need to know the exact location of the endoscopic capsule which influences the treatment plan. In this paper, we present a displacement estimation technique based on feature point tracking which utilizes the images captured by a commercial capsule, named PillCam. The proposed displacement calculation approach is tested using a virtual testbed. Results show that, with assistance of ASIFT-RANSAC algorithms, the proposed algorithm is able to estimate the linear displacement of the endoscopic capsule with an accuracy of 93.7% on average.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116098227","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835379
N. Sultana, S. Das, M. Gani
We study the two-variable FitzHugh-Nagumo reaction-diffusion system for neuron excitation. The periodic action potentials of the nerve cells can be treated as the periodic traveling waves in one dimension. That motivates us to study the existence and the stability of periodic traveling waves in a one-parameter family of solutions. It is observed that periodic traveling waves change their stability by a stability change of Eckhaus type in a two-dimensional parameter plane. We determine the stability boundary between stable and unstable periodic traveling waves. We also calculate essential spectra of the periodic traveling waves.
{"title":"Bifurcation analysis of periodic action potentials of nerve cells in the FitzHugh-Nagumo model","authors":"N. Sultana, S. Das, M. Gani","doi":"10.1109/MEDITEC.2016.7835379","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835379","url":null,"abstract":"We study the two-variable FitzHugh-Nagumo reaction-diffusion system for neuron excitation. The periodic action potentials of the nerve cells can be treated as the periodic traveling waves in one dimension. That motivates us to study the existence and the stability of periodic traveling waves in a one-parameter family of solutions. It is observed that periodic traveling waves change their stability by a stability change of Eckhaus type in a two-dimensional parameter plane. We determine the stability boundary between stable and unstable periodic traveling waves. We also calculate essential spectra of the periodic traveling waves.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126187945","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 : 2016-12-01DOI: 10.1109/MEDITEC.2016.7835374
S. Sabab, Md. Ahadur Rahman Munshi, Ahmed Iqbal Pritom, Shihabuzzaman
Cardiovascular disease is a worldwide health problem and according to American Heart Association (AHA), it also causes an approximate death of 17.3 million each year. Therefore early detection and treatment of asymptomatic cardiovascular disease which can significantly reduce the chances of death. An important fact regarding such life-threatening disease prognosis is to identify the patient's physical state (healthy or sick) based on the analysis of health checkup data. This paper aims at optimized cardiovascular disease prognosis using different data mining techniques. We also provide a technique to improve the accuracy of proposed classifier models using feature selection technique. Patient's data were collected from Department of Computing of Goldsmiths University of London. This dataset contains total 14 attributes in which we applied SMO (SVM - Support Vector Machine), C4.5 (J48 - Decision Tree) and Naïve Bayes classification algorithms and calculated their prediction accuracy. An efficient feature selection algorithm helped us to improve the accuracy of each model by reducing some lower ranked attributes. Which helped us to gain an accuracy of 87.8%, 86.80% & 79.9% in case of SMO, Naïve Bayes and C4.5 Decision Tree algorithms respectively.
心血管疾病是一个全球性的健康问题，根据美国心脏协会(AHA)的数据，它每年也导致大约1730万人死亡。因此早期发现和治疗无症状心血管疾病可显著降低死亡机会。对于这种危及生命的疾病的预后，一个重要的事实是通过健康检查数据的分析来确定患者的身体状态(健康或生病)。本文旨在利用不同的数据挖掘技术优化心血管疾病的预后。我们还提供了一种使用特征选择技术来提高所提出的分类器模型的准确性的技术。患者数据收集自伦敦金史密斯大学计算机系。该数据集共包含14个属性，我们分别应用SMO (SVM - Support Vector Machine)、C4.5 (J48 - Decision Tree)和Naïve贝叶斯分类算法，并计算了它们的预测精度。一种高效的特征选择算法通过减少一些排名较低的属性来帮助我们提高每个模型的准确性。这使得我们在SMO、Naïve贝叶斯和C4.5决策树算法下分别获得了87.8%、86.80%和79.9%的准确率。
{"title":"Cardiovascular disease prognosis using effective classification and feature selection technique","authors":"S. Sabab, Md. Ahadur Rahman Munshi, Ahmed Iqbal Pritom, Shihabuzzaman","doi":"10.1109/MEDITEC.2016.7835374","DOIUrl":"https://doi.org/10.1109/MEDITEC.2016.7835374","url":null,"abstract":"Cardiovascular disease is a worldwide health problem and according to American Heart Association (AHA), it also causes an approximate death of 17.3 million each year. Therefore early detection and treatment of asymptomatic cardiovascular disease which can significantly reduce the chances of death. An important fact regarding such life-threatening disease prognosis is to identify the patient's physical state (healthy or sick) based on the analysis of health checkup data. This paper aims at optimized cardiovascular disease prognosis using different data mining techniques. We also provide a technique to improve the accuracy of proposed classifier models using feature selection technique. Patient's data were collected from Department of Computing of Goldsmiths University of London. This dataset contains total 14 attributes in which we applied SMO (SVM - Support Vector Machine), C4.5 (J48 - Decision Tree) and Naïve Bayes classification algorithms and calculated their prediction accuracy. An efficient feature selection algorithm helped us to improve the accuracy of each model by reducing some lower ranked attributes. Which helped us to gain an accuracy of 87.8%, 86.80% & 79.9% in case of SMO, Naïve Bayes and C4.5 Decision Tree algorithms respectively.","PeriodicalId":325916,"journal":{"name":"2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130956402","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：