Stroke risk prediction based on electronic health records is currently an important research topi... more Stroke risk prediction based on electronic health records is currently an important research topic. Previous research activities have generally used single-time physiological data to build static models and have focused on algorithms to improve prediction accuracy. Few studies have considered historical measurements from a data perspective to construct dynamic models. Since it is a chronic disease, the risk of having a stroke increases and the corresponding risk factors become abnormal when healthy people are diagnosed with a stroke. Therefore, in this paper, we applied longitudinal data, with the backward joint model, to the Chinese Longitudinal Healthy Longevity and Happy Family Study’s dataset to monitor changes in individuals’ health status precisely on time and to increase the prediction accuracy of the model. The three-year prediction accuracy of our model, considering three measurements of longitudinal parameters, is 0.926. This is higher than the traditional Cox proportional...
Infrared Spectroscopy - Perspectives and Applications [Working Title]
Functional near-infrared spectroscopy (fNIRS) is an emerging wearable neuroimaging technique base... more Functional near-infrared spectroscopy (fNIRS) is an emerging wearable neuroimaging technique based on monitoring the hemodynamics of brain activity. First, the operation principle of fNIRS is described. This includes introducing the absorption spectra of the targeted molecule: the oxygenated and deoxygenated hemoglobin. Then, the optical path formed by emitters and detectors and the concentration of the molecules is determined using Beer-Lambert law. In the second part, the advantages of applying fNIRS are compared with other neuroimaging techniques, such as computed tomography and magnetic resonance imaging. The compared parameters include time and spatial resolution, immobility, etc. Next, the evolution of the fNIRS devices is shown. It includes the commercially available systems and the others under construction in academia. In the last section, the applications of fNIRS to avoid stroke are presented. The challenges of achieving good signal quality and high user comfort monitorin...
Internet addiction (IA), as a new and often unrecognized psychosocial disorder, endangers people’... more Internet addiction (IA), as a new and often unrecognized psychosocial disorder, endangers people’s health and their lives. However, the common biometric analysis based on the combination of EEG signals and results of questionnaires is not quantitative, and thus difficult to ensure a specific biomarker. This work aims to develop a deep learning algorithm (no need to identify biomarkers) used for diagnosing IA and evaluating therapy efficacy. Herein, a five-layer CNN model combined with a fast Fourier transform is proposed to diagnose IA quantitatively. This algorithm is validated in the Lemon dataset by using it to process raw data, full spectral power, and alpha-beta-gamma spectral power (related to IA). In contrast to alpha-beta-gamma spectral power, the results based on full spectral power show better performance (87.59% accuracy, 88.80% sensitivity, and 86.41% specificity), which confirms that the proposed algorithm can diagnose IA without biomarkers. In addition, this proposed C...
2021 Photonics & Electromagnetics Research Symposium (PIERS)
Objective: Photoacoustics is a novel medical imaging modality based on optical excitation and aco... more Objective: Photoacoustics is a novel medical imaging modality based on optical excitation and acoustic propagation with high optical resolution and tissues penetration. However, the attenuation of the optical signal in the human brain due to the extinction caused by optical absorption and scattering leads to poor imaging performance. It is essential to explore the mechanism of the signal generation of photoacoustic imaging inside the human brain. Photoacoustic signal generation not only refers to the penetration and absorption of the light energy but also has the other processes contained heat transfer and thermal expansion to get the initial photoacoustic signal. Here, we modeled and simulated the photoacoustic signal generation in the human brain with an embedded blood vessel using finite element analysis.Methods: A model of the human brain was simplified into a 2-dimensional layer with a blood vessel embedded. The simulation was achieved using COMSOL Multiphysics. The processes of the simulation related to optical propagation and absorption, heat transfer, thermal expansion, and solid mechanical processes.Results: Based on modeling and simulation, we got the optical fluence and absorption, temperature, pressure with the excitation of a pulsed light source in various layers following the time. The results show that the optical energy in the shallow region is higher than in the deeper region, while the optical absorption and temperature increased differently from layer to layer. Although the optical energy arrived at the blood vessel is low, the energy acquired and temperature increase are higher than the horizontal direction. And the pressure change shows the photoacoustic signal generation of the blood vessel is obviously than the surrounding.Conclusion: We achieved photoacoustic signal generation in a model of the human brain using numerical simulation. The generation of a photoacoustic signal involved multi-physical processes with pulsed light incident into tissue and converted the light energy to increase temperature and to change the pressure. Significance: This research result helps to understand the mechanism of the photoacoustic signal generation inside a model representing the human head, which is a reference to prompt the imaging performance and improve the photoacoustic imaging technique for human brain imaging.
Detailed testing has shown that active dry electrodes made from conductive polymers can be applie... more Detailed testing has shown that active dry electrodes made from conductive polymers can be applied for user-friendly, high quality EEG recordings. Using a dedicated elastic interconnect technique, the dry electrodes can be integrated in a headset ensuring good skin contact. Combined with an elegant headset design, a promising solution is offered for user-friendly EEG monitoring outside the hospital.
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2013
Soft, comfortable polymer-based dry electrodes are fabricated. Impedance and biopotential measure... more Soft, comfortable polymer-based dry electrodes are fabricated. Impedance and biopotential measurements are carried out to compare the performance of conventional gel electrodes with our dry electrodes. The impedance of our dry electrodes is reduced by adding more conductive additives to the polymer material. To further lower the impedance, two skin pretreatment techniques are evaluated regarding their influence on skin impedance. However, these techniques are found to have only temporary beneficial effects. Finally biopotential measurements (both ECG and EEG) are performed using our soft polymer electrodes. The ECG signal acquired with both gel and our polymer electrodes demonstrates high degree of similarity. Therefore, heart beat detection is straightforward. To enable monitoring of EEG signals with smaller amplitudes, our dry electrodes need to be combined with pre-amplifiers. Initial EEG tests show that the alpha waves are clearly identifiable with the dry electrodes when subjec...
Dry electrodes are attractive for biopotential recordings to avoid the drawbacks related to wet g... more Dry electrodes are attractive for biopotential recordings to avoid the drawbacks related to wet gel electrodes. Commercially available EEG systems with hard metal-based dry electrodes are uncomfortable and even painful. Two types of polymer-based dry electrodes for higher user comfort are presented. Our dry electrodes are compared with wet gel electrodes regarding impedance, and EEG & ECG recording. Very promising results are obtained for ECG and EEG, resp. without and with pre-amplification.status: accepte
Conventional ECG and EEG gel electrodes are widely used in health care applications. These electr... more Conventional ECG and EEG gel electrodes are widely used in health care applications. These electrodes deliver high-quality signals due to their low impedance, but they have important drawbacks, such as time-consuming electrode set-up for EEG followed by a painful removal, skin irritation by the gel, signal degradation due to drying of the gel, etc. To solve this, various types of dry electrodes attract attention last years. Hard metal dry electrodes show low impedance, but most are not comfortable for the patient. Flexible polymer-based electrodes are presented in this work to avoid the disadvantages of gel electrodes while significantly improving user comfort. Different additives are mixed in these polymers and optimized to improve various relevant properties. An important electrode property is low impedance, which directly affects signal quality and influences the sensitivity to motion artifacts. The polymer composition influences also the mechanical properties, as well as the material flow during molding and hence the electrode fabrication yield. Moreover, various electrode shapes are tested to achieve appropriate mechanical properties and increase user comfort. For ECG & EEG applications, the best performing dry electrodes are selected and results are compared with wet electrode signals .
Wet gel electrodes are widely used for ECG/EEG monitoring, their low impedance results in high-qu... more Wet gel electrodes are widely used for ECG/EEG monitoring, their low impedance results in high-quality signals. But they have important drawbacks too, such as time-consuming electrode set-up for EEG followed by a painful removal, skin irritation by the gel and signal degradation due to gel drying. Hence various dry electrode types are investigated, such as hard metal electrodes with low impedance but limited patient comfort/safety. We focus on flexible conductive polymer-based electrodes to combine low impedance, user comfort and safety. The composition of the conductive polymers is optimized to improve various properties such as conductivity, which directly affects signal quality and sensitivity to motion artifacts, and mechanical properties of the electrodes, important with respect to patient comfort. Electrode impedance and ECG/EEG signal recordings are evaluated using various polymer compositions and compared to wet gel electrode results. Additive optimization to improve process...
We review in this paper the wearable-based technologies intended for real-time monitoring of stro... more We review in this paper the wearable-based technologies intended for real-time monitoring of stroke-related physiological parameters. These measurements are undertaken to prevent death and disability due to stroke. We compare the various characteristics, such as weight, accessibility, frequency of use, data continuity, and response time of these wearables. It was found that the most user-friendly wearables can have limitations in reporting high-precision prediction outcomes. Therefore, we report also the trend of integrating these wearables into the internet of things (IoT) and combining electronic health records (EHRs) and machine learning (ML) algorithms to establish a stroke risk prediction system. Due to different characteristics, such as accessibility, time, and spatial resolution of various wearable-based technologies, strategies of applying different types of wearables to maximize the efficacy of stroke risk prediction are also reported. In addition, based on the various appl...
Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 2007
Abstract-Over the past years, there has been a lot of efforts on the development of wireless sens... more Abstract-Over the past years, there has been a lot of efforts on the development of wireless sensor networks. However, the major constraint on broad application of wireless sensor network is still the battery lifetime on the wireless sensor nodes. In this paper, a complete power efficient ...
2021 Photonics & Electromagnetics Research Symposium (PIERS), 2021
Cerebral hemodynamics vary depending on the brain activities. Functional near-infrared spectrosco... more Cerebral hemodynamics vary depending on the brain activities. Functional near-infrared spectroscopy (fNIRS) is an emerging wearable technology to monitor hemodynamics during various cognitive activities. However, the impact of the level of sleepiness on the variations of the cerebral hemodynamics during N-back tasks and the following rest periods has not been well investigated. Twenty-five participants took part in a series of visual N-back tasks after lunch. The participants were requested not to take an afternoon nap before the measurements to present a sleepy status. Before the starting of measurements, they were asked to fill in an Epworth Sleepiness Scale (ESS) to define the level of sleepiness. Their cerebral hemodynamic variations were recorded using 20 fNIRS channels over the dorsolateral prefrontal, frontal, and the parietal cortices of the brain. Three rounds of N-back task were carried out. After each N-back task, there was a rest period. For every subject’s recording, the average oxygenated hemoglobin concentrations ([HbO2]) during the N-back task periods and during the rest periods of each fNIRS recording channel were calculated. The correlation between the level of sleepiness and the [HbO2] of each channel was determined using Pearson’s correlation coefficient. It is found that the variation of [HbO2] is negatively correlated to the ESS during the N-back task periods on the parietal cortex of the brain. In addition, the variation of [HbO2] is positively correlated to the ESS during the rest periods for some channels on dorsolateral prefrontal and frontal cortices of brain. This suggests that during N-back task, people feel sleepier may consume more oxygen in the brain to complete the N-back tasks. While after the end of N-back tasks, people feel sleepier need more oxygen to recover the oxygen consumed during the N-back tasks.
Stroke risk prediction based on electronic health records is currently an important research topi... more Stroke risk prediction based on electronic health records is currently an important research topic. Previous research activities have generally used single-time physiological data to build static models and have focused on algorithms to improve prediction accuracy. Few studies have considered historical measurements from a data perspective to construct dynamic models. Since it is a chronic disease, the risk of having a stroke increases and the corresponding risk factors become abnormal when healthy people are diagnosed with a stroke. Therefore, in this paper, we applied longitudinal data, with the backward joint model, to the Chinese Longitudinal Healthy Longevity and Happy Family Study’s dataset to monitor changes in individuals’ health status precisely on time and to increase the prediction accuracy of the model. The three-year prediction accuracy of our model, considering three measurements of longitudinal parameters, is 0.926. This is higher than the traditional Cox proportional...
Infrared Spectroscopy - Perspectives and Applications [Working Title]
Functional near-infrared spectroscopy (fNIRS) is an emerging wearable neuroimaging technique base... more Functional near-infrared spectroscopy (fNIRS) is an emerging wearable neuroimaging technique based on monitoring the hemodynamics of brain activity. First, the operation principle of fNIRS is described. This includes introducing the absorption spectra of the targeted molecule: the oxygenated and deoxygenated hemoglobin. Then, the optical path formed by emitters and detectors and the concentration of the molecules is determined using Beer-Lambert law. In the second part, the advantages of applying fNIRS are compared with other neuroimaging techniques, such as computed tomography and magnetic resonance imaging. The compared parameters include time and spatial resolution, immobility, etc. Next, the evolution of the fNIRS devices is shown. It includes the commercially available systems and the others under construction in academia. In the last section, the applications of fNIRS to avoid stroke are presented. The challenges of achieving good signal quality and high user comfort monitorin...
Internet addiction (IA), as a new and often unrecognized psychosocial disorder, endangers people’... more Internet addiction (IA), as a new and often unrecognized psychosocial disorder, endangers people’s health and their lives. However, the common biometric analysis based on the combination of EEG signals and results of questionnaires is not quantitative, and thus difficult to ensure a specific biomarker. This work aims to develop a deep learning algorithm (no need to identify biomarkers) used for diagnosing IA and evaluating therapy efficacy. Herein, a five-layer CNN model combined with a fast Fourier transform is proposed to diagnose IA quantitatively. This algorithm is validated in the Lemon dataset by using it to process raw data, full spectral power, and alpha-beta-gamma spectral power (related to IA). In contrast to alpha-beta-gamma spectral power, the results based on full spectral power show better performance (87.59% accuracy, 88.80% sensitivity, and 86.41% specificity), which confirms that the proposed algorithm can diagnose IA without biomarkers. In addition, this proposed C...
2021 Photonics & Electromagnetics Research Symposium (PIERS)
Objective: Photoacoustics is a novel medical imaging modality based on optical excitation and aco... more Objective: Photoacoustics is a novel medical imaging modality based on optical excitation and acoustic propagation with high optical resolution and tissues penetration. However, the attenuation of the optical signal in the human brain due to the extinction caused by optical absorption and scattering leads to poor imaging performance. It is essential to explore the mechanism of the signal generation of photoacoustic imaging inside the human brain. Photoacoustic signal generation not only refers to the penetration and absorption of the light energy but also has the other processes contained heat transfer and thermal expansion to get the initial photoacoustic signal. Here, we modeled and simulated the photoacoustic signal generation in the human brain with an embedded blood vessel using finite element analysis.Methods: A model of the human brain was simplified into a 2-dimensional layer with a blood vessel embedded. The simulation was achieved using COMSOL Multiphysics. The processes of the simulation related to optical propagation and absorption, heat transfer, thermal expansion, and solid mechanical processes.Results: Based on modeling and simulation, we got the optical fluence and absorption, temperature, pressure with the excitation of a pulsed light source in various layers following the time. The results show that the optical energy in the shallow region is higher than in the deeper region, while the optical absorption and temperature increased differently from layer to layer. Although the optical energy arrived at the blood vessel is low, the energy acquired and temperature increase are higher than the horizontal direction. And the pressure change shows the photoacoustic signal generation of the blood vessel is obviously than the surrounding.Conclusion: We achieved photoacoustic signal generation in a model of the human brain using numerical simulation. The generation of a photoacoustic signal involved multi-physical processes with pulsed light incident into tissue and converted the light energy to increase temperature and to change the pressure. Significance: This research result helps to understand the mechanism of the photoacoustic signal generation inside a model representing the human head, which is a reference to prompt the imaging performance and improve the photoacoustic imaging technique for human brain imaging.
Detailed testing has shown that active dry electrodes made from conductive polymers can be applie... more Detailed testing has shown that active dry electrodes made from conductive polymers can be applied for user-friendly, high quality EEG recordings. Using a dedicated elastic interconnect technique, the dry electrodes can be integrated in a headset ensuring good skin contact. Combined with an elegant headset design, a promising solution is offered for user-friendly EEG monitoring outside the hospital.
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2013
Soft, comfortable polymer-based dry electrodes are fabricated. Impedance and biopotential measure... more Soft, comfortable polymer-based dry electrodes are fabricated. Impedance and biopotential measurements are carried out to compare the performance of conventional gel electrodes with our dry electrodes. The impedance of our dry electrodes is reduced by adding more conductive additives to the polymer material. To further lower the impedance, two skin pretreatment techniques are evaluated regarding their influence on skin impedance. However, these techniques are found to have only temporary beneficial effects. Finally biopotential measurements (both ECG and EEG) are performed using our soft polymer electrodes. The ECG signal acquired with both gel and our polymer electrodes demonstrates high degree of similarity. Therefore, heart beat detection is straightforward. To enable monitoring of EEG signals with smaller amplitudes, our dry electrodes need to be combined with pre-amplifiers. Initial EEG tests show that the alpha waves are clearly identifiable with the dry electrodes when subjec...
Dry electrodes are attractive for biopotential recordings to avoid the drawbacks related to wet g... more Dry electrodes are attractive for biopotential recordings to avoid the drawbacks related to wet gel electrodes. Commercially available EEG systems with hard metal-based dry electrodes are uncomfortable and even painful. Two types of polymer-based dry electrodes for higher user comfort are presented. Our dry electrodes are compared with wet gel electrodes regarding impedance, and EEG & ECG recording. Very promising results are obtained for ECG and EEG, resp. without and with pre-amplification.status: accepte
Conventional ECG and EEG gel electrodes are widely used in health care applications. These electr... more Conventional ECG and EEG gel electrodes are widely used in health care applications. These electrodes deliver high-quality signals due to their low impedance, but they have important drawbacks, such as time-consuming electrode set-up for EEG followed by a painful removal, skin irritation by the gel, signal degradation due to drying of the gel, etc. To solve this, various types of dry electrodes attract attention last years. Hard metal dry electrodes show low impedance, but most are not comfortable for the patient. Flexible polymer-based electrodes are presented in this work to avoid the disadvantages of gel electrodes while significantly improving user comfort. Different additives are mixed in these polymers and optimized to improve various relevant properties. An important electrode property is low impedance, which directly affects signal quality and influences the sensitivity to motion artifacts. The polymer composition influences also the mechanical properties, as well as the material flow during molding and hence the electrode fabrication yield. Moreover, various electrode shapes are tested to achieve appropriate mechanical properties and increase user comfort. For ECG & EEG applications, the best performing dry electrodes are selected and results are compared with wet electrode signals .
Wet gel electrodes are widely used for ECG/EEG monitoring, their low impedance results in high-qu... more Wet gel electrodes are widely used for ECG/EEG monitoring, their low impedance results in high-quality signals. But they have important drawbacks too, such as time-consuming electrode set-up for EEG followed by a painful removal, skin irritation by the gel and signal degradation due to gel drying. Hence various dry electrode types are investigated, such as hard metal electrodes with low impedance but limited patient comfort/safety. We focus on flexible conductive polymer-based electrodes to combine low impedance, user comfort and safety. The composition of the conductive polymers is optimized to improve various properties such as conductivity, which directly affects signal quality and sensitivity to motion artifacts, and mechanical properties of the electrodes, important with respect to patient comfort. Electrode impedance and ECG/EEG signal recordings are evaluated using various polymer compositions and compared to wet gel electrode results. Additive optimization to improve process...
We review in this paper the wearable-based technologies intended for real-time monitoring of stro... more We review in this paper the wearable-based technologies intended for real-time monitoring of stroke-related physiological parameters. These measurements are undertaken to prevent death and disability due to stroke. We compare the various characteristics, such as weight, accessibility, frequency of use, data continuity, and response time of these wearables. It was found that the most user-friendly wearables can have limitations in reporting high-precision prediction outcomes. Therefore, we report also the trend of integrating these wearables into the internet of things (IoT) and combining electronic health records (EHRs) and machine learning (ML) algorithms to establish a stroke risk prediction system. Due to different characteristics, such as accessibility, time, and spatial resolution of various wearable-based technologies, strategies of applying different types of wearables to maximize the efficacy of stroke risk prediction are also reported. In addition, based on the various appl...
Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 2007
Abstract-Over the past years, there has been a lot of efforts on the development of wireless sens... more Abstract-Over the past years, there has been a lot of efforts on the development of wireless sensor networks. However, the major constraint on broad application of wireless sensor network is still the battery lifetime on the wireless sensor nodes. In this paper, a complete power efficient ...
2021 Photonics & Electromagnetics Research Symposium (PIERS), 2021
Cerebral hemodynamics vary depending on the brain activities. Functional near-infrared spectrosco... more Cerebral hemodynamics vary depending on the brain activities. Functional near-infrared spectroscopy (fNIRS) is an emerging wearable technology to monitor hemodynamics during various cognitive activities. However, the impact of the level of sleepiness on the variations of the cerebral hemodynamics during N-back tasks and the following rest periods has not been well investigated. Twenty-five participants took part in a series of visual N-back tasks after lunch. The participants were requested not to take an afternoon nap before the measurements to present a sleepy status. Before the starting of measurements, they were asked to fill in an Epworth Sleepiness Scale (ESS) to define the level of sleepiness. Their cerebral hemodynamic variations were recorded using 20 fNIRS channels over the dorsolateral prefrontal, frontal, and the parietal cortices of the brain. Three rounds of N-back task were carried out. After each N-back task, there was a rest period. For every subject’s recording, the average oxygenated hemoglobin concentrations ([HbO2]) during the N-back task periods and during the rest periods of each fNIRS recording channel were calculated. The correlation between the level of sleepiness and the [HbO2] of each channel was determined using Pearson’s correlation coefficient. It is found that the variation of [HbO2] is negatively correlated to the ESS during the N-back task periods on the parietal cortex of the brain. In addition, the variation of [HbO2] is positively correlated to the ESS during the rest periods for some channels on dorsolateral prefrontal and frontal cortices of brain. This suggests that during N-back task, people feel sleepier may consume more oxygen in the brain to complete the N-back tasks. While after the end of N-back tasks, people feel sleepier need more oxygen to recover the oxygen consumed during the N-back tasks.
Uploads