Pub Date : 2014-10-01DOI: 10.1109/HealthCom.2014.7001865
D. Welfer, Renato Cassol Ferreira da Silva, J. Kazienko
The Community-Acquired Pneumonia (CAP) is a disease frequently detected in hospitals demanding suitable treatment. From a medical perspective, handling high amount of variables needed for CAP's diagnosis process is a problem due to the significant number of patients in nowadays hospitals and the difficulty of a physician to apply the knowledge in real-time for each patient what leads to delays and imprecisions in diagnosis. Thus, quick and precise diagnosis, besides medical penetration in hospital environment are important factors to deal with the CAP's diagnosis process problem. This paper presents a mobile application system for diagnosis and management of community-acquired pneumonia so as to solve the CAP's diagnosis process problem. As proof of concept, our system was deployed on a high circulation public hospital. Experimentation qualitative results reveal that it increases the speediness and precision in diagnosis, besides the applications' penetration in hospital environment.
{"title":"A mobile application system for diagnosis and management of Community-Acquired Pneumonia","authors":"D. Welfer, Renato Cassol Ferreira da Silva, J. Kazienko","doi":"10.1109/HealthCom.2014.7001865","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001865","url":null,"abstract":"The Community-Acquired Pneumonia (CAP) is a disease frequently detected in hospitals demanding suitable treatment. From a medical perspective, handling high amount of variables needed for CAP's diagnosis process is a problem due to the significant number of patients in nowadays hospitals and the difficulty of a physician to apply the knowledge in real-time for each patient what leads to delays and imprecisions in diagnosis. Thus, quick and precise diagnosis, besides medical penetration in hospital environment are important factors to deal with the CAP's diagnosis process problem. This paper presents a mobile application system for diagnosis and management of community-acquired pneumonia so as to solve the CAP's diagnosis process problem. As proof of concept, our system was deployed on a high circulation public hospital. Experimentation qualitative results reveal that it increases the speediness and precision in diagnosis, besides the applications' penetration in hospital environment.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127134897","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001864
N. Franco, R. Fidalgo, Edson A. Silva, Ticia F. Cacalcante, P. Brito
Communication Board (CB) is an Assistive Technology (AT) that enables people who have speech impairment to communicate their needs or desires using visual-graphic symbols. Since each patient has individual needs, it is important to offer a customizable approach to define the vocabulary of their CB. In this context, this paper proposes a modeling language for diagramming the CB vocabulary. Its feasibility, expressiveness and usefulness were validated through the construction of a software that will be described later in this paper.
{"title":"Modeling language and CASE tool for communication board customization","authors":"N. Franco, R. Fidalgo, Edson A. Silva, Ticia F. Cacalcante, P. Brito","doi":"10.1109/HealthCom.2014.7001864","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001864","url":null,"abstract":"Communication Board (CB) is an Assistive Technology (AT) that enables people who have speech impairment to communicate their needs or desires using visual-graphic symbols. Since each patient has individual needs, it is important to offer a customizable approach to define the vocabulary of their CB. In this context, this paper proposes a modeling language for diagramming the CB vocabulary. Its feasibility, expressiveness and usefulness were validated through the construction of a software that will be described later in this paper.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130713032","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001807
M. Freire, J. Faber, J. R. Santos, Nelson A. M. Lemos, M. A. Aratanha, Pedro F. Cavalcanti, E. Morya
Recovering of people suffering from spinal cord and brain lesion is a medical challenge. Brain-machine interface (BMI) emerges as a potential candidate, by allowing patients to use their own brain activity to reestablish sensorimotor control of paralyzed body parts. BMI can be divided in two main groups: non-invasive, based in the capture of the neuronal signal over the cranium, and invasive, much more effective in generating high resolution brain-derived motor control signals, despite requiring a brain surgery for implantation of recording microelectrodes. Accordingly, chronic multielectrodes implants define the fundamental component of an invasive BMI. However, it is important to characterize the impact of microwire arrays' implant on the nervous tissue before this technique can be available to human clinical trials. Here we evaluated the expression of immediate early-gene c-fos and inflammatory response (astrogliosis), as well as the quality of the neuronal signal comparing the variation of the total number and the amplitude of the recorded units after long-lasting chronic multielectrode implants. Electrode recordings remained viable for 6 months after implant, and did not alter the general physiology of the implanted tissue, as revealed by normal c-Fos expression in implanted sites. Moreover, there was a small inflammatory response across implanted regions. Our findings suggest that tungsten microwire arrays can be viable candidates to future human BMI interventions.
{"title":"c-Fos immunoreactivity and variation of neuronal units in rat's motor cortex after chronic implants","authors":"M. Freire, J. Faber, J. R. Santos, Nelson A. M. Lemos, M. A. Aratanha, Pedro F. Cavalcanti, E. Morya","doi":"10.1109/HealthCom.2014.7001807","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001807","url":null,"abstract":"Recovering of people suffering from spinal cord and brain lesion is a medical challenge. Brain-machine interface (BMI) emerges as a potential candidate, by allowing patients to use their own brain activity to reestablish sensorimotor control of paralyzed body parts. BMI can be divided in two main groups: non-invasive, based in the capture of the neuronal signal over the cranium, and invasive, much more effective in generating high resolution brain-derived motor control signals, despite requiring a brain surgery for implantation of recording microelectrodes. Accordingly, chronic multielectrodes implants define the fundamental component of an invasive BMI. However, it is important to characterize the impact of microwire arrays' implant on the nervous tissue before this technique can be available to human clinical trials. Here we evaluated the expression of immediate early-gene c-fos and inflammatory response (astrogliosis), as well as the quality of the neuronal signal comparing the variation of the total number and the amplitude of the recorded units after long-lasting chronic multielectrode implants. Electrode recordings remained viable for 6 months after implant, and did not alter the general physiology of the implanted tissue, as revealed by normal c-Fos expression in implanted sites. Moreover, there was a small inflammatory response across implanted regions. Our findings suggest that tungsten microwire arrays can be viable candidates to future human BMI interventions.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131852959","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001877
Jochen Meyer, Susanne CJ Boll
Smart health systems such as networked activity trackers, scales, or sports watches allow monitoring many aspects of a healthy lifestyle. Nevertheless there is a semantic gap between these systems' measurements and the users' personal health action plan that is not bridged by existing health data aggregators. We describe representative types of health data as measured today and suggest a simple classification of data based on temporality of the data. We present a mapping of physical devices to health action plans that is device-agnostic and bridges this semantic gap. A key concept is the mapping of logical devices to primary health features that translates measurements to a meaningful health concept. We describe a prototype system implementing our mapping and providing lessons learned. The approach shows to be feasible to describe typical personal health action plans.
{"title":"Smart health systems for personal health action plans","authors":"Jochen Meyer, Susanne CJ Boll","doi":"10.1109/HealthCom.2014.7001877","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001877","url":null,"abstract":"Smart health systems such as networked activity trackers, scales, or sports watches allow monitoring many aspects of a healthy lifestyle. Nevertheless there is a semantic gap between these systems' measurements and the users' personal health action plan that is not bridged by existing health data aggregators. We describe representative types of health data as measured today and suggest a simple classification of data based on temporality of the data. We present a mapping of physical devices to health action plans that is device-agnostic and bridges this semantic gap. A key concept is the mapping of logical devices to primary health features that translates measurements to a meaningful health concept. We describe a prototype system implementing our mapping and providing lessons learned. The approach shows to be feasible to describe typical personal health action plans.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115069181","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001898
Özgür Kafali, Ulrich Schaechtle, Kostas Stathis
We present Hydra: a multi-agent hybrid diagnosis and monitoring architecture that is aimed at helping diabetic patients manage their illness. It makes use of model-based diagnosis techniques, where the model can be developed by two different approaches combined in a novel way. In the first approach, we build the model based on the medical guidelines provided for diabetes. A computational logic agent monitors the patient and provides feedback based on the model whenever the current observations regarding the patient are sufficient to draw a conclusion. In the second approach, we assume a function for the model, and learn its parameters through data. The model is consistently updated via incoming observations about the patients, and allows prediction of possible future values. We describe the components of such an architecture, and how it can integrated into the existing COMMODITY12 personal health system. We implement a prototype of Hydra, and present its workings on a case study on hypoglycemia monitoring. We report our prediction results for this scenario.
{"title":"Hydra: A hybrid diagnosis and monitoring architecture for diabetes","authors":"Özgür Kafali, Ulrich Schaechtle, Kostas Stathis","doi":"10.1109/HealthCom.2014.7001898","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001898","url":null,"abstract":"We present Hydra: a multi-agent hybrid diagnosis and monitoring architecture that is aimed at helping diabetic patients manage their illness. It makes use of model-based diagnosis techniques, where the model can be developed by two different approaches combined in a novel way. In the first approach, we build the model based on the medical guidelines provided for diabetes. A computational logic agent monitors the patient and provides feedback based on the model whenever the current observations regarding the patient are sufficient to draw a conclusion. In the second approach, we assume a function for the model, and learn its parameters through data. The model is consistently updated via incoming observations about the patients, and allows prediction of possible future values. We describe the components of such an architecture, and how it can integrated into the existing COMMODITY12 personal health system. We implement a prototype of Hydra, and present its workings on a case study on hypoglycemia monitoring. We report our prediction results for this scenario.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122905127","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001878
Marijke Vandermaesen, Karel Robert, K. Luyten, K. Coninx
We present ReHoblet; a physical rehabilitation game on tablets, designed to be used in a residential setting. ReHoblet trains two gross motor movements of the upper limbs by lifting (up-down) and transporting (left-right) the tablet to control a simple platform game. By using its accelerometers and gyroscope, the tablet is capable of detecting movements made by the user and steer the interaction based on this data. A formative evaluation with five Multiple Sclerosis (MS) patients and their therapists showed high appreciation for ReHoblet. Patients stated they liked ReHoblet not only to improve their physical abilities, but to train on performing technology-related tasks. Based on the results, we reflect on tablet-based games in home-based rehabilitation.
{"title":"ReHoblet — A home-based rehabilitation game on the tablet","authors":"Marijke Vandermaesen, Karel Robert, K. Luyten, K. Coninx","doi":"10.1109/HealthCom.2014.7001878","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001878","url":null,"abstract":"We present ReHoblet; a physical rehabilitation game on tablets, designed to be used in a residential setting. ReHoblet trains two gross motor movements of the upper limbs by lifting (up-down) and transporting (left-right) the tablet to control a simple platform game. By using its accelerometers and gyroscope, the tablet is capable of detecting movements made by the user and steer the interaction based on this data. A formative evaluation with five Multiple Sclerosis (MS) patients and their therapists showed high appreciation for ReHoblet. Patients stated they liked ReHoblet not only to improve their physical abilities, but to train on performing technology-related tasks. Based on the results, we reflect on tablet-based games in home-based rehabilitation.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125818109","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001840
L. M. E. Silva, Roberto Araújo, Felipe Leite da Silva, E. Cerqueira
Cloud computing is a technological service that has become a trend. This paradigm adds many benefits to storage of personal health records (PHR) and electronic health records (EHR), such as availability and on-demand provisioning. It also facilitates sharing of health records among doctors, family members, friends and clinicians in general. However, this technology increases the risk of leaking sensitive health data. Aiming at mitigating this problem, we present here a new architecture that takes advantage of identity federation for secure storage and sharing of PHR and EHR in the cloud environment.
{"title":"A new architecture for secure storage and sharing of health records in the cloud using federated identity attributes","authors":"L. M. E. Silva, Roberto Araújo, Felipe Leite da Silva, E. Cerqueira","doi":"10.1109/HealthCom.2014.7001840","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001840","url":null,"abstract":"Cloud computing is a technological service that has become a trend. This paradigm adds many benefits to storage of personal health records (PHR) and electronic health records (EHR), such as availability and on-demand provisioning. It also facilitates sharing of health records among doctors, family members, friends and clinicians in general. However, this technology increases the risk of leaking sensitive health data. Aiming at mitigating this problem, we present here a new architecture that takes advantage of identity federation for secure storage and sharing of PHR and EHR in the cloud environment.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125825442","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001901
Fábio Rafael Damasceno, Eliseo Reategui, D. Epstein, C. A. Schmitz, E. Harzheim
In the primary care scenario, telehealth appears as an option for continuing professional development. Questions submitted by physicians and their respective answers in the Brazilian health ministry telehealth platform were mined using a text mining tool. Graphs about the concepts present in the database were extracted using this tool, which gave a clearer view of the subjects addressed by teleconsultants. A questionnaire has been given to teleconsultants asking them about the current protocol they follow in their answering process in the TelehealthRS Project. Results showed that the graphs obtained in the mining process can make teleconsultation answering easier. A recorded interview was conducted with nine physician teleconsultants, deepening the first questionnaire topics. Their comments are now being used to guide the implementation of new features of the current Brazilian health ministry platform. This initiative should impact in the accuracy and response speed offered to professionals, improving their training and contributing to their continuing professional development.
{"title":"TelehealthRS project: Supporting teleconsulting with text mining to improve continuing professional development","authors":"Fábio Rafael Damasceno, Eliseo Reategui, D. Epstein, C. A. Schmitz, E. Harzheim","doi":"10.1109/HealthCom.2014.7001901","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001901","url":null,"abstract":"In the primary care scenario, telehealth appears as an option for continuing professional development. Questions submitted by physicians and their respective answers in the Brazilian health ministry telehealth platform were mined using a text mining tool. Graphs about the concepts present in the database were extracted using this tool, which gave a clearer view of the subjects addressed by teleconsultants. A questionnaire has been given to teleconsultants asking them about the current protocol they follow in their answering process in the TelehealthRS Project. Results showed that the graphs obtained in the mining process can make teleconsultation answering easier. A recorded interview was conducted with nine physician teleconsultants, deepening the first questionnaire topics. Their comments are now being used to guide the implementation of new features of the current Brazilian health ministry platform. This initiative should impact in the accuracy and response speed offered to professionals, improving their training and contributing to their continuing professional development.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114641977","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001893
A. Inácio, Rafael Andrade, A. V. Wangenheim, D. D. J. D. Macedo
The Santa Catarina State Telemedicine and Telehealth System - STT/SC stores well over 2 million examinations and every month about 20 thousand new imaging exams are sent to the system database. As a significant part of the findings associated to these medical data are stored as text documents, the precise extraction of information is a difficult task. In the healthcare domain it is common to find different terms, some of them appearing as composed expressions, used to represent the same concept, whereas the existence of simple modifiers can turn an expression into another, different concept. This work presents an information retrieval architecture developed for the STT/SC. It consists in a module integrated into the STT/SC and was developed in order to support both experienced and inexperienced users to perform queries. Experiments were performed to evaluate the accuracy of the proposed system in real situations. Results show that the search can be performed more much faster and with acceptable precision.
{"title":"Designing an information retrieval system for the STT/SC","authors":"A. Inácio, Rafael Andrade, A. V. Wangenheim, D. D. J. D. Macedo","doi":"10.1109/HealthCom.2014.7001893","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001893","url":null,"abstract":"The Santa Catarina State Telemedicine and Telehealth System - STT/SC stores well over 2 million examinations and every month about 20 thousand new imaging exams are sent to the system database. As a significant part of the findings associated to these medical data are stored as text documents, the precise extraction of information is a difficult task. In the healthcare domain it is common to find different terms, some of them appearing as composed expressions, used to represent the same concept, whereas the existence of simple modifiers can turn an expression into another, different concept. This work presents an information retrieval architecture developed for the STT/SC. It consists in a module integrated into the STT/SC and was developed in order to support both experienced and inexperienced users to perform queries. Experiments were performed to evaluate the accuracy of the proposed system in real situations. Results show that the search can be performed more much faster and with acceptable precision.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116906436","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 : 2014-10-01DOI: 10.1109/HealthCom.2014.7001857
Te-Wei Ho, Horng-Yih Lai, Yu-Jie Wang, Wei-Hsin Chen, F. Lai, Y. Ho, C. Hung
Telehealthcare is a global trend affecting clinical practice in the world. With the progress and development of telecommunication technologies, telecom facilities have afforded telehealthcare a new approach for chronic disease management. The electrocardiogram (ECG) is commonly used to detect abnormal heart rhythms and to investigate the cause of heart abnormalities. To reduce the cardiologists' loading and to provide a continuously telehealthcare, we developed a clinical decision and support system (CDSS) with automatic recognition of the ECG in real-time analysis. In addition, we adopted the approach of noise reduction and feature extraction for support vector machine (SVM) implementation with automatic learning algorithms. The automatic interpretation of ECG could provide assistance to physicians in decision-making, especially with large volumes of data. According to the preliminary results of automatic classification models, we acquired 88.4% sensitivity, for noise detection model, 85.9% specificity for sinus classification model and 89.1% sensitivity for disease classification model, respectively. However, it is not reliable enough to obviate the need for physician's diagnosis and confirmation. We should put much effort on enhancing the performance of ECG interpretation in the future.
{"title":"A clinical decision and support system with automatically ECG classification in telehealthcare","authors":"Te-Wei Ho, Horng-Yih Lai, Yu-Jie Wang, Wei-Hsin Chen, F. Lai, Y. Ho, C. Hung","doi":"10.1109/HealthCom.2014.7001857","DOIUrl":"https://doi.org/10.1109/HealthCom.2014.7001857","url":null,"abstract":"Telehealthcare is a global trend affecting clinical practice in the world. With the progress and development of telecommunication technologies, telecom facilities have afforded telehealthcare a new approach for chronic disease management. The electrocardiogram (ECG) is commonly used to detect abnormal heart rhythms and to investigate the cause of heart abnormalities. To reduce the cardiologists' loading and to provide a continuously telehealthcare, we developed a clinical decision and support system (CDSS) with automatic recognition of the ECG in real-time analysis. In addition, we adopted the approach of noise reduction and feature extraction for support vector machine (SVM) implementation with automatic learning algorithms. The automatic interpretation of ECG could provide assistance to physicians in decision-making, especially with large volumes of data. According to the preliminary results of automatic classification models, we acquired 88.4% sensitivity, for noise detection model, 85.9% specificity for sinus classification model and 89.1% sensitivity for disease classification model, respectively. However, it is not reliable enough to obviate the need for physician's diagnosis and confirmation. We should put much effort on enhancing the performance of ECG interpretation in the future.","PeriodicalId":269964,"journal":{"name":"2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117231499","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：