Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749438
W. Liu, T. Mundie, U. Krieger, Eun Kyo Park, S. S. Zhu
As the e-Health world is geared up for a more efficient rollout of fast healthcare resources, we designed our new Rapid Delivery e-Health Service (RDeHS) platform, which not only streamlines standard conformance through emerging technologies in e-Health resources. This paper reports the evolution in our new architectural approach for the purpose of rapid development and deployment of e-Health services to reduce healthcare costs and enhance quality of care.
{"title":"Rapid delivery e-Health service (RDeHS) platform","authors":"W. Liu, T. Mundie, U. Krieger, Eun Kyo Park, S. S. Zhu","doi":"10.1109/HealthCom.2016.7749438","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749438","url":null,"abstract":"As the e-Health world is geared up for a more efficient rollout of fast healthcare resources, we designed our new Rapid Delivery e-Health Service (RDeHS) platform, which not only streamlines standard conformance through emerging technologies in e-Health resources. This paper reports the evolution in our new architectural approach for the purpose of rapid development and deployment of e-Health services to reduce healthcare costs and enhance quality of care.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131657849","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749514
Amandine Dufaug, C. Barthod, L. Goujon, N. Forestier
The success of any surgical intervention is narrowly linked to the operating comfort of the surgeon. Nicknamed "chicken wings", the typical posture adopted by a practitioner during a laparoscopic intervention leads to cervical, shoulders and back pains. To avoid such a posture is one of the main challenge of medical devices designers. Instruments length, lack of articulations as well as non-adapted tables heights have to be reconsidered to surgeon's benefit. Moreover, the smoothness of the gesture is of great deal for the surgeon. It allows a more accurate gesture by reducing the disjointed contractions of the muscles. It has been observed that the recourse to an articulated instrument, the Dex™, leads to shoulder's adduction. The influence of its articulations, especially handle's one, on the surgeon's comfort, has to be quantified. This influence is confronted to several working conditions representative of operating room situations. An optimal surgical environment is proposed through the analysis of electromyography on shoulder's muscles and of elbow's acceleration.
{"title":"Ergonomic surgical practice analysed through sEMG monitoring of muscular activity","authors":"Amandine Dufaug, C. Barthod, L. Goujon, N. Forestier","doi":"10.1109/HealthCom.2016.7749514","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749514","url":null,"abstract":"The success of any surgical intervention is narrowly linked to the operating comfort of the surgeon. Nicknamed \"chicken wings\", the typical posture adopted by a practitioner during a laparoscopic intervention leads to cervical, shoulders and back pains. To avoid such a posture is one of the main challenge of medical devices designers. Instruments length, lack of articulations as well as non-adapted tables heights have to be reconsidered to surgeon's benefit. Moreover, the smoothness of the gesture is of great deal for the surgeon. It allows a more accurate gesture by reducing the disjointed contractions of the muscles. It has been observed that the recourse to an articulated instrument, the Dex™, leads to shoulder's adduction. The influence of its articulations, especially handle's one, on the surgeon's comfort, has to be quantified. This influence is confronted to several working conditions representative of operating room situations. An optimal surgical environment is proposed through the analysis of electromyography on shoulder's muscles and of elbow's acceleration.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115625195","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749424
Hamzah Osop, T. Sahama
The readily available and accessible large collection of electronic health records has encouraged an increasing interest on its secondary use. It is especially true for the approach of practice-based evidence where the secondary use of EHR data, collected during routine care, has the potential to improve healthcare professionals' decision-making capabilities and effectiveness, and broadens their knowledge regarding treatments, medications and clinical conditions. Through effective and quality decision-making, healthcare professionals are able to deliver care that positively improves patient health outcomes in a cost-effective and safe manner. However, privacy and security breaches potentially impact the integrity of data captured in electronic health records, and this invalidates its perceived usefulness in providing evidence to support care. In order to design a secure and effective EHR system for the adoption of practice-based evidence approaches, recommendations for privacy and security measures can follow the security control protocol of preventive, detective and corrective control. Within each control, different security solutions are recommended so that security design is truly holistic.
{"title":"Quality evidence, quality decisions: Ways to improve security and privacy of EHR systems","authors":"Hamzah Osop, T. Sahama","doi":"10.1109/HealthCom.2016.7749424","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749424","url":null,"abstract":"The readily available and accessible large collection of electronic health records has encouraged an increasing interest on its secondary use. It is especially true for the approach of practice-based evidence where the secondary use of EHR data, collected during routine care, has the potential to improve healthcare professionals' decision-making capabilities and effectiveness, and broadens their knowledge regarding treatments, medications and clinical conditions. Through effective and quality decision-making, healthcare professionals are able to deliver care that positively improves patient health outcomes in a cost-effective and safe manner. However, privacy and security breaches potentially impact the integrity of data captured in electronic health records, and this invalidates its perceived usefulness in providing evidence to support care. In order to design a secure and effective EHR system for the adoption of practice-based evidence approaches, recommendations for privacy and security measures can follow the security control protocol of preventive, detective and corrective control. Within each control, different security solutions are recommended so that security design is truly holistic.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115952181","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749433
Pawel Stelmach, Lukasz Falas, Grzegorz Kasiukiewicz, Paulina Kwasnicka, P. Swiatek
E-Health services are a topic of many Internet of Things (IoT) related research. In this paper a model-centric platform for Internet of Things and e-Health scenarios is presented. Multiple e-Health scenarios showcase the ability of the platform to model, support configuration and gathering data at runtime for multiple use cases at the same time, often with option to share Tools for creating metamodels, ontologies and IoT and service repositories are presented and their role in the proposed IoT platform discussed.
{"title":"IoT modelling and runtime suite for e-Health","authors":"Pawel Stelmach, Lukasz Falas, Grzegorz Kasiukiewicz, Paulina Kwasnicka, P. Swiatek","doi":"10.1109/HealthCom.2016.7749433","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749433","url":null,"abstract":"E-Health services are a topic of many Internet of Things (IoT) related research. In this paper a model-centric platform for Internet of Things and e-Health scenarios is presented. Multiple e-Health scenarios showcase the ability of the platform to model, support configuration and gathering data at runtime for multiple use cases at the same time, often with option to share Tools for creating metamodels, ontologies and IoT and service repositories are presented and their role in the proposed IoT platform discussed.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121179388","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749418
E. Naves, T. Filho, G. Bourhis, Yuri Silva, V. Silva, V. Lucena
New research reports shows that important progresses for controlling electric-powered wheelchair have been made recently aiming people with severe disabilities. In fact, a significant amount of people affected by those physical disabilities still cannot take advantage of autonomous mobility, even electronic or automated ones. For those people, the use of proper biological signals to control the assisted environment may be the only existing solution. In such scenario, the act of commanding an electric-powered wheelchair without proper training may be a serious safety risk. To avoid this kind of dangerous situation and to permit users to make use of such technology, one viable solution would be to be trained by using virtual driving simulators. Nevertheless, when using biomedical signals as commands it is not possible to ensure a continuous and reliable control of the wheelchair, it is necessary to associate the control possibilities with autonomous features such as semiautomatic obstacle detection or contour. Thus, it is interesting to offer to new wheelchair users the possibility of using simulators to allow them to learn to drive at distance, making use of telematics techniques combined with mobile and wearable devices, and publishing their progress and worries in social networks, which is the objective of this work. This project joints complementary skills from researchers from the Federal University of Amazonas, Federal University of Espirito Santo, and Federal University of Uberlandia, with the collaboration of researches from the University of Lorraine in Metz-France.
{"title":"Virtual and augmented reality environment for remote training of wheelchairs users: Social, mobile, and wearable technologies applied to rehabilitation","authors":"E. Naves, T. Filho, G. Bourhis, Yuri Silva, V. Silva, V. Lucena","doi":"10.1109/HealthCom.2016.7749418","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749418","url":null,"abstract":"New research reports shows that important progresses for controlling electric-powered wheelchair have been made recently aiming people with severe disabilities. In fact, a significant amount of people affected by those physical disabilities still cannot take advantage of autonomous mobility, even electronic or automated ones. For those people, the use of proper biological signals to control the assisted environment may be the only existing solution. In such scenario, the act of commanding an electric-powered wheelchair without proper training may be a serious safety risk. To avoid this kind of dangerous situation and to permit users to make use of such technology, one viable solution would be to be trained by using virtual driving simulators. Nevertheless, when using biomedical signals as commands it is not possible to ensure a continuous and reliable control of the wheelchair, it is necessary to associate the control possibilities with autonomous features such as semiautomatic obstacle detection or contour. Thus, it is interesting to offer to new wheelchair users the possibility of using simulators to allow them to learn to drive at distance, making use of telematics techniques combined with mobile and wearable devices, and publishing their progress and worries in social networks, which is the objective of this work. This project joints complementary skills from researchers from the Federal University of Amazonas, Federal University of Espirito Santo, and Federal University of Uberlandia, with the collaboration of researches from the University of Lorraine in Metz-France.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116603752","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749497
Nadiya Straton, Kjeld Hansen, R. Mukkamala, Abid Hussain, Tor-Morten Grønli, H. Langberg, Ravikiran Vatrapu
In recent years, social media has offered new opportunities for interaction and distribution of public health information within and across organisations. In this paper, we analysed data from Facebook walls of 153 public organisations using unsupervised machine learning techniques to understand the characteristics of user engagement and post performance. Our analysis indicates an increasing trend of user engagement on public health posts during recent years. Based on the clustering results, our analysis shows that Photo and Link type posts are most favourable for high and medium user engagement respectively.
{"title":"Big social data analytics for public health: Facebook engagement and performance","authors":"Nadiya Straton, Kjeld Hansen, R. Mukkamala, Abid Hussain, Tor-Morten Grønli, H. Langberg, Ravikiran Vatrapu","doi":"10.1109/HealthCom.2016.7749497","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749497","url":null,"abstract":"In recent years, social media has offered new opportunities for interaction and distribution of public health information within and across organisations. In this paper, we analysed data from Facebook walls of 153 public organisations using unsupervised machine learning techniques to understand the characteristics of user engagement and post performance. Our analysis indicates an increasing trend of user engagement on public health posts during recent years. Based on the clustering results, our analysis shows that Photo and Link type posts are most favourable for high and medium user engagement respectively.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122658055","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749456
Juan Li, Jun Kong
The epidemic of diabetes in American Indian (AI) communities is a serious public health challenge. The incidence and prevalence of diabetes have increased dramatically with accompanying increases in body weight and diminished physical activity. Daily diabetes care is primarily handled by the patients and their families, and the effectiveness of diabetes control is largely impacted by self-care strategies and behaviors. Thanks to the quasi-ubiquitous use of cell phones in most AI tribes, in this paper we propose a cell phone- based proactive diabetes self-care system, MobiDiaBTs. It is customized for AI patients using a personalized approach that considers the unique social, cultural, political, and demographic characteristic of AIs. The platform effectively and automatically collects users' physical and social behavior data and offers real-time diabetes health recommendations. It also can help a patient to interact with fellow patients in a trust-worthy and privacy-preserving environment.
{"title":"Cell phone-based diabetes self-management and social networking system for American Indians","authors":"Juan Li, Jun Kong","doi":"10.1109/HealthCom.2016.7749456","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749456","url":null,"abstract":"The epidemic of diabetes in American Indian (AI) communities is a serious public health challenge. The incidence and prevalence of diabetes have increased dramatically with accompanying increases in body weight and diminished physical activity. Daily diabetes care is primarily handled by the patients and their families, and the effectiveness of diabetes control is largely impacted by self-care strategies and behaviors. Thanks to the quasi-ubiquitous use of cell phones in most AI tribes, in this paper we propose a cell phone- based proactive diabetes self-care system, MobiDiaBTs. It is customized for AI patients using a personalized approach that considers the unique social, cultural, political, and demographic characteristic of AIs. The platform effectively and automatically collects users' physical and social behavior data and offers real-time diabetes health recommendations. It also can help a patient to interact with fellow patients in a trust-worthy and privacy-preserving environment.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122932541","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749477
J. Muñoz, Fábio Pereira, E. Karapanos
The active monitoring of workload levels has been found to significantly reduce work-related stress. Heart rate and heart rate variability (HRV) measurements via photoplethysmography (PPG) sensors have shown a strong potential to accurately describe daily workload levels. However, due its complexity, HRV is commonly misunderstood and the associated measurements are rarely incorporated for workload monitoring in novel technological devices such as smartwatches and activity trackers. In this paper we explore the potential of consumer-grade smartwatches, equipped with PPG sensors, to assist in the active monitoring of workload during work hours. We develop a prototype that employs the SDNN index, a powerful HRV marker for cardiac resilience to differentiate between high and low workload levels along the work day, and presents feedback in glanceable form, by highlighting workload levels and physical activity over the past hour in 5-minutes blocks at the periphery of the smartwatch. A field study with 9 participants and 3 variations of our prototype attempts to quantify the impact of the HRV feedback over subjective and objective workload as well as users' engagement with the smartwatch. Results showed workload levels as inferred from the PPG sensor to positively correlate with self-reported workload and HRV feedback to result to lower levels of workload as compared to a conventional activity tracker. Moreover, users engaged more frequently with the smartwatch when HRV feedback was presented, than when only physical activity feedback was provided. The results suggest that HRV as inferred from PPG sensors in wearables can effectively be used to monitor workload levels during work hours.
{"title":"Workload management through glanceable feedback: The role of heart rate variability","authors":"J. Muñoz, Fábio Pereira, E. Karapanos","doi":"10.1109/HealthCom.2016.7749477","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749477","url":null,"abstract":"The active monitoring of workload levels has been found to significantly reduce work-related stress. Heart rate and heart rate variability (HRV) measurements via photoplethysmography (PPG) sensors have shown a strong potential to accurately describe daily workload levels. However, due its complexity, HRV is commonly misunderstood and the associated measurements are rarely incorporated for workload monitoring in novel technological devices such as smartwatches and activity trackers. In this paper we explore the potential of consumer-grade smartwatches, equipped with PPG sensors, to assist in the active monitoring of workload during work hours. We develop a prototype that employs the SDNN index, a powerful HRV marker for cardiac resilience to differentiate between high and low workload levels along the work day, and presents feedback in glanceable form, by highlighting workload levels and physical activity over the past hour in 5-minutes blocks at the periphery of the smartwatch. A field study with 9 participants and 3 variations of our prototype attempts to quantify the impact of the HRV feedback over subjective and objective workload as well as users' engagement with the smartwatch. Results showed workload levels as inferred from the PPG sensor to positively correlate with self-reported workload and HRV feedback to result to lower levels of workload as compared to a conventional activity tracker. Moreover, users engaged more frequently with the smartwatch when HRV feedback was presented, than when only physical activity feedback was provided. The results suggest that HRV as inferred from PPG sensors in wearables can effectively be used to monitor workload levels during work hours.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133971886","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749465
N. Cardoso, João Madureira, N. Pereira
Smartphones are everywhere, and they are a very attractive platform to perform unobtrusive monitoring of users. In this work, we use common features of modern smartphones to build a human activity recognition (HAR) system for elderly care. We have built a classifier that detects the transport mode of the user including whether an individual is inactive, walking, in bus, in car, in train or in metro. We evaluated our approach using over 24 hours of transportation data from a group of 15 individuals. Our tests show that our classifier can detect the transportation mode with over 90% accuracy.
{"title":"Smartphone-based transport mode detection for elderly care","authors":"N. Cardoso, João Madureira, N. Pereira","doi":"10.1109/HealthCom.2016.7749465","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749465","url":null,"abstract":"Smartphones are everywhere, and they are a very attractive platform to perform unobtrusive monitoring of users. In this work, we use common features of modern smartphones to build a human activity recognition (HAR) system for elderly care. We have built a classifier that detects the transport mode of the user including whether an individual is inactive, walking, in bus, in car, in train or in metro. We evaluated our approach using over 24 hours of transportation data from a group of 15 individuals. Our tests show that our classifier can detect the transportation mode with over 90% accuracy.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115746809","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 : 2016-09-01DOI: 10.1109/HealthCom.2016.7749471
Hussein Alawieh, H. Hammoud, Mortada Haidar, M. Nassralla, Ahmad M. El-Hajj, Z. Dawy
This work proposes a novel patient-aware approach that utilizes an n-gram based pattern recognition algorithm to analyze scalp electroencephalogram (EEG) data and predict epileptic seizures. The method addresses the major challenge of extracting distinctive features from EEG signals through a detection of spatio-temporal signatures related to neurological events. By counting the number of occurrences of amplitude patterns with predefined lengths, the algorithm generates a probabilistic measure (anomalies ratio) that is used as a prediction marker. These extracted ratios are classified using state of the art machine learning algorithms into seizure and non-seizure windows. The efficacy of the prediction model is tested on patient records from the Freiburg database with more than 100 hours of recordings per patient and for a total of 145 seizures. The proposed algorithm is further optimized to obtain the n-gram parameters for enhanced feature extraction. Results demonstrate an average accuracy of 93.83%, sensitivity of 96.12%, and false alarm rate of 8.44%.
{"title":"Patient-aware adaptive ngram-based algorithm for epileptic seizure prediction using EEG signals","authors":"Hussein Alawieh, H. Hammoud, Mortada Haidar, M. Nassralla, Ahmad M. El-Hajj, Z. Dawy","doi":"10.1109/HealthCom.2016.7749471","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749471","url":null,"abstract":"This work proposes a novel patient-aware approach that utilizes an n-gram based pattern recognition algorithm to analyze scalp electroencephalogram (EEG) data and predict epileptic seizures. The method addresses the major challenge of extracting distinctive features from EEG signals through a detection of spatio-temporal signatures related to neurological events. By counting the number of occurrences of amplitude patterns with predefined lengths, the algorithm generates a probabilistic measure (anomalies ratio) that is used as a prediction marker. These extracted ratios are classified using state of the art machine learning algorithms into seizure and non-seizure windows. The efficacy of the prediction model is tested on patient records from the Freiburg database with more than 100 hours of recordings per patient and for a total of 145 seizures. The proposed algorithm is further optimized to obtain the n-gram parameters for enhanced feature extraction. Results demonstrate an average accuracy of 93.83%, sensitivity of 96.12%, and false alarm rate of 8.44%.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123193135","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：