A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques.
大流行期间反复出现的一个主题是医院床位短缺。尽管做出了所有努力，但医疗保健系统仍然面临着冠状病毒第一次高峰期间25%的资源紧张。电子医疗记录(EHRs)的数字化和大流行带来了许多成功的应用递归神经网络(rnn)来预测患者当前和未来的状态。尽管它们表现出色，但对于用户来说，深入研究黑匣子仍然是一个挑战，这严重影响了研究人员利用更多可解释的技术，如id -卷积神经网络。其他人则专注于使用更具可解释性的机器学习技术，但仅在选定的患者子集上实现高性能。通过与医学专家和人工智能科学家合作，我们的研究改进了REverse Time AttentIoN EX模型(一个特征和访问级注意力网络)，以提高rnn在预测covid -19相关住院治疗方面的可解释性和可用性。我们在接收者工作特征曲线下获得了82.40%的面积，并展示了反向时间注意力扩展模型和电子病历在理解个人医疗代码如何有助于住院风险预测方面的有效使用。这项研究为旨在利用rnn和数据挖掘技术设计可解释的时间神经网络的研究人员提供了指导。
{"title":"RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks","authors":"Suraj Ramchand, Gavin Tsang, Duncan Cole, Xianghua Xie","doi":"10.1109/BHI56158.2022.9926906","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926906","url":null,"abstract":"A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126868058","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926833
Guanghang Liao, Caifeng Shan, Wenjin Wang
Non-invasive Blood Pressure (BP) measurement is highly demanded for pervasive healthcare with the development of Internet of Things, sensors and mobile technology. Camera-based Photoplethysmography (camera-PPG) has been applied for non-contact BP estimation. Most camera-PPG based approaches calculate the Pulse Transmission Time between different peripheral sites like face and palm for BP calibration, which require more than one body part to be simultaneously measured and thus introduce inconvenience to real applications. In this study, we investigate the feasibility of measuring BP from a single body site using either the forehead PPG signals or neck ballistocardiographic (BCG) motion signals. Two morphological features (K-value and Augmentation Index) that have clinical meanings for BP monitoring have been compared. The study was conducted in the ice water stimulation experiment involving 16 healthy subjects. The results show that the neck can be an attractive site for BP estimation as the neck-BCG signals show more distinct features (e.g. dicrotic wave) that have stronger correlations with BP than the forehead-PPG signals, and it eliminates the privacy issue of imaging a face. Both the K-value and Augmentation Index can well track the changes of BP. The conclusions drawn from this study inspire the selection of physiological site and features for non-contact BP estimation.
{"title":"Comparison of PPG and BCG Features for Camera-based Blood Pressure Estimation by Ice Water Stimulation","authors":"Guanghang Liao, Caifeng Shan, Wenjin Wang","doi":"10.1109/BHI56158.2022.9926833","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926833","url":null,"abstract":"Non-invasive Blood Pressure (BP) measurement is highly demanded for pervasive healthcare with the development of Internet of Things, sensors and mobile technology. Camera-based Photoplethysmography (camera-PPG) has been applied for non-contact BP estimation. Most camera-PPG based approaches calculate the Pulse Transmission Time between different peripheral sites like face and palm for BP calibration, which require more than one body part to be simultaneously measured and thus introduce inconvenience to real applications. In this study, we investigate the feasibility of measuring BP from a single body site using either the forehead PPG signals or neck ballistocardiographic (BCG) motion signals. Two morphological features (K-value and Augmentation Index) that have clinical meanings for BP monitoring have been compared. The study was conducted in the ice water stimulation experiment involving 16 healthy subjects. The results show that the neck can be an attractive site for BP estimation as the neck-BCG signals show more distinct features (e.g. dicrotic wave) that have stronger correlations with BP than the forehead-PPG signals, and it eliminates the privacy issue of imaging a face. Both the K-value and Augmentation Index can well track the changes of BP. The conclusions drawn from this study inspire the selection of physiological site and features for non-contact BP estimation.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125801728","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926915
Munib Mesinovic, Kai-Wen Yang
With myocardial infarctions accounting for the largest percent of cardiovascular-related deaths, the need for machine learning tools in prediction and prevention has never been clearer. Specifically, in the case of in-hospital complications following acute myocardial infarction (AMI), even with decreased in-hospital mortality rate due to improved hospital care, patients who survive the acute phase of MI remain at risk for MI-associated complications or recurrent AMI such as bundle branch blocks and angina. In this paper, we propose a multi-label framework to predict the occurrence of 5 complications following admission of 1,700 patients after suffering an AMI episode. We evaluate the models using several multi-label prediction metrics as a test of robustness of our method beating numerous other alternatives and comment on the balance of cost-effectiveness of a compact deep learning model versus shallow machine learning in the multi-label context. Our neural network outperformed 13 other algorithms across all metrics, except Hamming loss. We also implement Shapley value analysis to this multi-label problem and observe interesting behaviour such as the duration of arterial hypertension and time elapsed from the beginning of the attack to the hospital being key predictive features of lethal outcome. This framework presents a novel approach in using multi-label learning, and especially compact cost-effective deep learning, simultaneous for prediction of several AMI complications which has not been explored previously.
{"title":"Multi-label Neural Model for Prediction of Myocardial Infarction Complications with Resampling and Explainability","authors":"Munib Mesinovic, Kai-Wen Yang","doi":"10.1109/BHI56158.2022.9926915","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926915","url":null,"abstract":"With myocardial infarctions accounting for the largest percent of cardiovascular-related deaths, the need for machine learning tools in prediction and prevention has never been clearer. Specifically, in the case of in-hospital complications following acute myocardial infarction (AMI), even with decreased in-hospital mortality rate due to improved hospital care, patients who survive the acute phase of MI remain at risk for MI-associated complications or recurrent AMI such as bundle branch blocks and angina. In this paper, we propose a multi-label framework to predict the occurrence of 5 complications following admission of 1,700 patients after suffering an AMI episode. We evaluate the models using several multi-label prediction metrics as a test of robustness of our method beating numerous other alternatives and comment on the balance of cost-effectiveness of a compact deep learning model versus shallow machine learning in the multi-label context. Our neural network outperformed 13 other algorithms across all metrics, except Hamming loss. We also implement Shapley value analysis to this multi-label problem and observe interesting behaviour such as the duration of arterial hypertension and time elapsed from the beginning of the attack to the hospital being key predictive features of lethal outcome. This framework presents a novel approach in using multi-label learning, and especially compact cost-effective deep learning, simultaneous for prediction of several AMI complications which has not been explored previously.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134040527","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926875
Guanjie Huang, Fenglong Ma
Correctly classifying different sleep stages is a critical and prerequisite step in diagnosing sleep-related issues. In practice, the clinical experts must manually review the polysomnography (PSG) recordings to classify sleep stages. Such a procedure is time-consuming, laborious, and potentially prone to human subjective errors. Deep learning-based methods have been successfully adopted for automatically classifying sleep stages in recent years. However, they cannot simply say “I do not know” when they are uncertain in their predictions, which may easily create significant risk in clinical applications, despite their good performance. To address this issue, we propose a deep model, named TrustSleepNet, which contains evidential learning and cross-modality attention modules. Evidential learning predicts the probability density of the classes, which can learn an uncertainty score and make the prediction trustable in real-world clinical applications. Cross-modality attention adaptively fuses multimodal PSG data by enhancing the significant ones and suppressing irrelevant ones. Experimental results demonstrate that TrustSleepNet outperforms state-of-the-art benchmark methods, and the uncertainty score makes the prediction more trustable and reliable.
{"title":"TrustSleepNet: A Trustable Deep Multimodal Network for Sleep Stage Classification","authors":"Guanjie Huang, Fenglong Ma","doi":"10.1109/BHI56158.2022.9926875","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926875","url":null,"abstract":"Correctly classifying different sleep stages is a critical and prerequisite step in diagnosing sleep-related issues. In practice, the clinical experts must manually review the polysomnography (PSG) recordings to classify sleep stages. Such a procedure is time-consuming, laborious, and potentially prone to human subjective errors. Deep learning-based methods have been successfully adopted for automatically classifying sleep stages in recent years. However, they cannot simply say “I do not know” when they are uncertain in their predictions, which may easily create significant risk in clinical applications, despite their good performance. To address this issue, we propose a deep model, named TrustSleepNet, which contains evidential learning and cross-modality attention modules. Evidential learning predicts the probability density of the classes, which can learn an uncertainty score and make the prediction trustable in real-world clinical applications. Cross-modality attention adaptively fuses multimodal PSG data by enhancing the significant ones and suppressing irrelevant ones. Experimental results demonstrate that TrustSleepNet outperforms state-of-the-art benchmark methods, and the uncertainty score makes the prediction more trustable and reliable.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133686924","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926823
P. Sahoo, S. Saha, S. Mondal, Suraj Gowda
The fast proliferation of the coronavirus around the globe has put several countries' healthcare systems in danger of collapsing. As a result, locating and separating COVID-19-positive patients is a critical task. Deep Learning approaches were used in several computer-aided automated systems that utilized chest computed tomography (CT-scan) or X-ray images to create diagnostic tools. However, current Convolutional Neural Network (CNN) based approaches cannot capture the global context because of inherent image-specific inductive bias. These techniques also require large and labeled datasets to train the algorithm, but not many labeled COVID-19 datasets exist publicly. To mitigate the problem, we have developed a self-attention-based Vision Transformer (ViT) architecture using CT-scan. The proposed ViT model achieves an accuracy of 98.39% on the popular SARS-CoV-2 datasets, outperforming the existing state-of-the-art CNN-based models by 1%. We also provide the characteristics of CT scan images of the COVID-19-affected patients and an error analysis of the model's outcome. Our findings show that the proposed ViT-based model can be an alternative option for medical professionals for effective COVID-19 screening. The implementation details of the proposed model can be accessed at https://github.com/Pranabiitp/ViT.
{"title":"Vision Transformer Based COVID-19 Detection Using Chest CT-scan images","authors":"P. Sahoo, S. Saha, S. Mondal, Suraj Gowda","doi":"10.1109/BHI56158.2022.9926823","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926823","url":null,"abstract":"The fast proliferation of the coronavirus around the globe has put several countries' healthcare systems in danger of collapsing. As a result, locating and separating COVID-19-positive patients is a critical task. Deep Learning approaches were used in several computer-aided automated systems that utilized chest computed tomography (CT-scan) or X-ray images to create diagnostic tools. However, current Convolutional Neural Network (CNN) based approaches cannot capture the global context because of inherent image-specific inductive bias. These techniques also require large and labeled datasets to train the algorithm, but not many labeled COVID-19 datasets exist publicly. To mitigate the problem, we have developed a self-attention-based Vision Transformer (ViT) architecture using CT-scan. The proposed ViT model achieves an accuracy of 98.39% on the popular SARS-CoV-2 datasets, outperforming the existing state-of-the-art CNN-based models by 1%. We also provide the characteristics of CT scan images of the COVID-19-affected patients and an error analysis of the model's outcome. Our findings show that the proposed ViT-based model can be an alternative option for medical professionals for effective COVID-19 screening. The implementation details of the proposed model can be accessed at https://github.com/Pranabiitp/ViT.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132008240","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926957
V. Pezoulas, F. Kalatzis, T. Exarchos, Antreas Goules, A. Tzioufas, D. Fotiadis
Nowadays there is an intensive need to move towards a universal health data ecosystem by breaking down data silos. Faced with a wealth of dispersed health data, there are still critical open issues and unmet needs to make this feasible, varying from secure data sharing to data quality and heterogeneity. Considering these challenges, we propose a novel federated platform to unlock the full potential of data from health data intermediaries through the secure sharing, curation, and Natural Language Processing (NLP)-based harmonization of dispersed and complex clinical data structures. The platform was deployed to establish a first Pan-European data hub on rare autoimmune and chronic diseases with 7551 harmonized patient records across 21 European countries with a 90% terminology overlap. An advanced data driven imputer was built to predict missing records in the real patient data based on high-quality synthetic data profiles (with Kullback-Leibler divergence less than 0.01). with reduced fault detection rate (less than 2%) compared to conventional imputers, such as, the kNN imputer. Customized and explainable federated AI algorithms were trained on top of the established data hub for lymphomagenesis modeling with 0.87 sensitivity and 0.74 specificity along with a set of validated biomarkers for disease onset and progression.
{"title":"A federated AI-empowered platform for disease management across a Pan-European data driven hub","authors":"V. Pezoulas, F. Kalatzis, T. Exarchos, Antreas Goules, A. Tzioufas, D. Fotiadis","doi":"10.1109/BHI56158.2022.9926957","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926957","url":null,"abstract":"Nowadays there is an intensive need to move towards a universal health data ecosystem by breaking down data silos. Faced with a wealth of dispersed health data, there are still critical open issues and unmet needs to make this feasible, varying from secure data sharing to data quality and heterogeneity. Considering these challenges, we propose a novel federated platform to unlock the full potential of data from health data intermediaries through the secure sharing, curation, and Natural Language Processing (NLP)-based harmonization of dispersed and complex clinical data structures. The platform was deployed to establish a first Pan-European data hub on rare autoimmune and chronic diseases with 7551 harmonized patient records across 21 European countries with a 90% terminology overlap. An advanced data driven imputer was built to predict missing records in the real patient data based on high-quality synthetic data profiles (with Kullback-Leibler divergence less than 0.01). with reduced fault detection rate (less than 2%) compared to conventional imputers, such as, the kNN imputer. Customized and explainable federated AI algorithms were trained on top of the established data hub for lymphomagenesis modeling with 0.87 sensitivity and 0.74 specificity along with a set of validated biomarkers for disease onset and progression.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129353980","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926889
V. Pezoulas, Eygenia Mylona, C. Papaloukas, Angelos Liontos, Dimitrios Biros, Orestis I. Milionis, C. Kyriakopoulos, K. Kostikas, H. Milionis, D. Fotiadis
Since the World Health Organization (WHO) has declared Artificial Intelligence (AI) as a powerful tool in the fight against COVID-19, multiple studies have been launched aiming to shed light into risk factors for ICU admission and mortality. None of the existing studies, however, have captured the dynamic trajectories of hospitalized COVID-19 patients who receive steroids nor have explored trajectory-based mortality indicators. In this work, we present a novel, hybrid approach to address this need. Latent Growth Mixture Modelling (LGMM) was used to analyze the trajectories of patients who received steroids. The patients were then grouped into clusters based on the similarity of their dynamic trajectories. State-of-the art machine learning classifiers are trained on the original dataset with and without dynamic trajectories to assess whether their inclusion can enhance the prediction of mortality. Our results highlight the importance of trajectories for predicting mortality in patients who receive steroids yielding 4% and 5% increase in the sensitivity (0.84) and specificity (0.85). The FiO2 and percentage of neutrophils at day 5, along with the percentage of lymphocytes at day 7, were identified as the main causes for mortality in patients who receive steroids, where the SatO2 levels showed significant alterations in the dynamic trajectories.
{"title":"A hybrid approach based on dynamic trajectories to predict mortality in COVID-19 patients upon steroids administration","authors":"V. Pezoulas, Eygenia Mylona, C. Papaloukas, Angelos Liontos, Dimitrios Biros, Orestis I. Milionis, C. Kyriakopoulos, K. Kostikas, H. Milionis, D. Fotiadis","doi":"10.1109/BHI56158.2022.9926889","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926889","url":null,"abstract":"Since the World Health Organization (WHO) has declared Artificial Intelligence (AI) as a powerful tool in the fight against COVID-19, multiple studies have been launched aiming to shed light into risk factors for ICU admission and mortality. None of the existing studies, however, have captured the dynamic trajectories of hospitalized COVID-19 patients who receive steroids nor have explored trajectory-based mortality indicators. In this work, we present a novel, hybrid approach to address this need. Latent Growth Mixture Modelling (LGMM) was used to analyze the trajectories of patients who received steroids. The patients were then grouped into clusters based on the similarity of their dynamic trajectories. State-of-the art machine learning classifiers are trained on the original dataset with and without dynamic trajectories to assess whether their inclusion can enhance the prediction of mortality. Our results highlight the importance of trajectories for predicting mortality in patients who receive steroids yielding 4% and 5% increase in the sensitivity (0.84) and specificity (0.85). The FiO2 and percentage of neutrophils at day 5, along with the percentage of lymphocytes at day 7, were identified as the main causes for mortality in patients who receive steroids, where the SatO2 levels showed significant alterations in the dynamic trajectories.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121072448","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926744
S. M. Deniz, Hamraz Javaheri, J. F. Vargas, Dogan Urgun, Fariza Sabit, Mahmut Tok, Mehmet Haklıdır, Bo Zhou, P. Lukowicz
In brain-computer interface and neuroscience, electroencephalography (EEG) signals have been well studied with not only cognitive activities but also physical activities. This work investigates if EEG can be used for detecting the motion as well as the variable weights a person is lifting. To this end, we used both commercial EEG headsets as well as open-source and open-protocol EEG hardware that is suitable for do-it-yourself designers. EEG data were obtained during performing biceps flexion-extension motions for different weight categories: lifting with no weight (empty), medium, and heavy lifting. Through two experiments of the bicep curl lifting scenario, we validated the concept with a study designed according to neuroscience standards and explored the pathway towards real-world applications with wearable sensing and smart garments. Both feature-based classification methods and deep learning models were designed and evaluated, showing accuracy up to 78% of differentiating three levels of weight (empty, medium, and heavy) consistently outperforming similar the state of the art. Our approach to predict different categories of lifted weight could be used in further optimizations in different research areas such as rehabilitation, sport as well as industrial applications. To encourage further research in this direction, the data sets acquired during this study will be publicly available.
{"title":"Prediction of Lifted Weight Category Using EEG Equipped Headgear","authors":"S. M. Deniz, Hamraz Javaheri, J. F. Vargas, Dogan Urgun, Fariza Sabit, Mahmut Tok, Mehmet Haklıdır, Bo Zhou, P. Lukowicz","doi":"10.1109/BHI56158.2022.9926744","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926744","url":null,"abstract":"In brain-computer interface and neuroscience, electroencephalography (EEG) signals have been well studied with not only cognitive activities but also physical activities. This work investigates if EEG can be used for detecting the motion as well as the variable weights a person is lifting. To this end, we used both commercial EEG headsets as well as open-source and open-protocol EEG hardware that is suitable for do-it-yourself designers. EEG data were obtained during performing biceps flexion-extension motions for different weight categories: lifting with no weight (empty), medium, and heavy lifting. Through two experiments of the bicep curl lifting scenario, we validated the concept with a study designed according to neuroscience standards and explored the pathway towards real-world applications with wearable sensing and smart garments. Both feature-based classification methods and deep learning models were designed and evaluated, showing accuracy up to 78% of differentiating three levels of weight (empty, medium, and heavy) consistently outperforming similar the state of the art. Our approach to predict different categories of lifted weight could be used in further optimizations in different research areas such as rehabilitation, sport as well as industrial applications. To encourage further research in this direction, the data sets acquired during this study will be publicly available.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116873477","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926966
Brendan Lyden, Zachary Dair, Ruairi O'Reilly
Sleep apnea is one of the most common sleep disorders. To diagnose sleep apnea, a patient must undertake a polysomnography where multiple physiological signals are recorded in a specialised sleep laboratory. Reducing the number of physiological signals necessary for a diagnosis and enabling data monitoring in a distributed fashion would assist in the detection of sleep apnea. Smartwatches are becoming more advanced, with the current generation capable of deriving blood oxygen saturation, which can indicate sleep apnea. This work evaluates the efficacy of sleep apnea classifiers in a simulated smartwatch environment. Results demonstrate that SpO2 is a performant signal for classifying sleep apnea. Naive Bayes trained with features extracted from a Long Short Term Memory Network is capable of classifying sleep apnea with an accuracy of 97.04%, outperforming state-of-the-art approaches. Classification within the simulated smartwatch environment demonstrates robustness up to a signal-to-noise ratio of 50 dB and maintains high levels of accuracy at sampling frequencies above 25 Hz. These encouraging results show substantial potential for smartwatches to provide timely, accessible sleep apnea screening and enable automated diagnostics reducing the reliance on specialist centres.
{"title":"Classification of Sleep Apnea via SpO2 in a Simulated Smartwatch Environment","authors":"Brendan Lyden, Zachary Dair, Ruairi O'Reilly","doi":"10.1109/BHI56158.2022.9926966","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926966","url":null,"abstract":"Sleep apnea is one of the most common sleep disorders. To diagnose sleep apnea, a patient must undertake a polysomnography where multiple physiological signals are recorded in a specialised sleep laboratory. Reducing the number of physiological signals necessary for a diagnosis and enabling data monitoring in a distributed fashion would assist in the detection of sleep apnea. Smartwatches are becoming more advanced, with the current generation capable of deriving blood oxygen saturation, which can indicate sleep apnea. This work evaluates the efficacy of sleep apnea classifiers in a simulated smartwatch environment. Results demonstrate that SpO2 is a performant signal for classifying sleep apnea. Naive Bayes trained with features extracted from a Long Short Term Memory Network is capable of classifying sleep apnea with an accuracy of 97.04%, outperforming state-of-the-art approaches. Classification within the simulated smartwatch environment demonstrates robustness up to a signal-to-noise ratio of 50 dB and maintains high levels of accuracy at sampling frequencies above 25 Hz. These encouraging results show substantial potential for smartwatches to provide timely, accessible sleep apnea screening and enable automated diagnostics reducing the reliance on specialist centres.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"12 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116584940","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 : 2022-09-27DOI: 10.1109/BHI56158.2022.9926949
Tsakaneli Stavroula, E. Bei, M. Zervakis
Multiple sclerosis (MS) is a chronic inflammatory demyelinating disease that affects approximately 2.8 million persons globally. While there is currently no cure for this neurodegenerative disease, MS has become a highly manageable disease through treatment options like disease-modifying medications, that can help to control the symptoms and slow disease progression. Among them, interferon beta (IFNβ) therapy is a first-line treatment for MS but has shown to be only partially effective. Thus, it is important to identify biomarkers that aid in early identification of IFNβ responders. In this study, based on gene expression profiles from untreated and interferon treated patients from a publicly available dataset, we performed differential expression analysis and Pigengene network association (weighted correlation network analysis (WGCNA) and Bayesian networks modeling) in order to construct a high-confidence protein-protein (PPI) interaction network. Subsequently, aiming to find the most significant clustering modules and hub genes, we applied a number of topological analysis methods (cytoHubba plugin) followed by MCODE clustering algorithm. Our approach resulted in highly connected hub genes generating a reliable 21-hubgene signature that could predict the response of interferon beta (IFNβ) therapy in patients with MS. The 21-hub-gene signature showed high classification performance (Accuracy = 91,49%, Sensitivity = 94.55%, Specificity = 87.15%) demonstrating potential clinical benefit.
{"title":"Tsakaneli Stavroula","authors":"Tsakaneli Stavroula, E. Bei, M. Zervakis","doi":"10.1109/BHI56158.2022.9926949","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926949","url":null,"abstract":"Multiple sclerosis (MS) is a chronic inflammatory demyelinating disease that affects approximately 2.8 million persons globally. While there is currently no cure for this neurodegenerative disease, MS has become a highly manageable disease through treatment options like disease-modifying medications, that can help to control the symptoms and slow disease progression. Among them, interferon beta (IFNβ) therapy is a first-line treatment for MS but has shown to be only partially effective. Thus, it is important to identify biomarkers that aid in early identification of IFNβ responders. In this study, based on gene expression profiles from untreated and interferon treated patients from a publicly available dataset, we performed differential expression analysis and Pigengene network association (weighted correlation network analysis (WGCNA) and Bayesian networks modeling) in order to construct a high-confidence protein-protein (PPI) interaction network. Subsequently, aiming to find the most significant clustering modules and hub genes, we applied a number of topological analysis methods (cytoHubba plugin) followed by MCODE clustering algorithm. Our approach resulted in highly connected hub genes generating a reliable 21-hubgene signature that could predict the response of interferon beta (IFNβ) therapy in patients with MS. The 21-hub-gene signature showed high classification performance (Accuracy = 91,49%, Sensitivity = 94.55%, Specificity = 87.15%) demonstrating potential clinical benefit.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126847401","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：