Pub Date : 2017-11-01DOI: 10.1109/HIC.2017.8227581
D. Blanco, A. Díaz-Méndez
In this work, EEG signals are used to detect the presence of pain in healthy subjects aiming to apply the same process to non-communicative patients. It was acquired 20 EEGs of healthy subjects in resting and pain state. Pain was induced through a cold pressor test. Phase Indexes as Phase Lag Index, Weighted Phase Lag Index were applied in four frequency bands to detect pain, getting significant results on Beta band for intra-hemispheric short and long distanced couples of electrodes for both indexes and also for interhemispheric distanced electrodes for WPLI.
{"title":"Pain detection with EEG using Phase Indexes","authors":"D. Blanco, A. Díaz-Méndez","doi":"10.1109/HIC.2017.8227581","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227581","url":null,"abstract":"In this work, EEG signals are used to detect the presence of pain in healthy subjects aiming to apply the same process to non-communicative patients. It was acquired 20 EEGs of healthy subjects in resting and pain state. Pain was induced through a cold pressor test. Phase Indexes as Phase Lag Index, Weighted Phase Lag Index were applied in four frequency bands to detect pain, getting significant results on Beta band for intra-hemispheric short and long distanced couples of electrodes for both indexes and also for interhemispheric distanced electrodes for WPLI.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125282004","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227585
Steven A. Roberts, N. Neelaveni, Nitin Agrawal
Nanoscale drug carriers have quickly risen to the forefront of translational research and promise to play a prominent role in point of care applications. The protocol for synthesizing these particles typically relies on extensive secondary post processing techniques (e.g. extrusion, dialysis, or ultracentrifugation) that are time consuming and can lead to a net loss in either the number of particles or amount of encapsulated molecules. Here we utilize filter centrifugation to efficiently purify and concentrate liposomal particle solutions. Using this technique, we are able to remove 99.99% of nonencapsulated molecules from solution in less than half of the time required for ultracentrifugation without net loss of particles from the solution.
{"title":"A novel filtration approach to create small unilamellar liposomes for drug delivery","authors":"Steven A. Roberts, N. Neelaveni, Nitin Agrawal","doi":"10.1109/HIC.2017.8227585","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227585","url":null,"abstract":"Nanoscale drug carriers have quickly risen to the forefront of translational research and promise to play a prominent role in point of care applications. The protocol for synthesizing these particles typically relies on extensive secondary post processing techniques (e.g. extrusion, dialysis, or ultracentrifugation) that are time consuming and can lead to a net loss in either the number of particles or amount of encapsulated molecules. Here we utilize filter centrifugation to efficiently purify and concentrate liposomal particle solutions. Using this technique, we are able to remove 99.99% of nonencapsulated molecules from solution in less than half of the time required for ultracentrifugation without net loss of particles from the solution.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133598117","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227615
Muhammad S. Khan, K. Dighe, Zhen Wang, A. Schwartz-Duval, Dr. Santoshi Misra, D. Pan
Cortisol, a hormone commonly released upon increased stress level, is a biomarker for numerous diseases and plays an important role in the regulation of various physiological processes. Normally a cortisol level is elevated in oral saliva during the time of anxiety and depression. A portable biosensor device could provide an interesting digital instrument to the patients and people who desire precautionary onsite cortisol diagnosis without visiting psychiatrists and/or physicians. We have developed disposable paper-based biosensor chip to monitor cortisol with a wide range of detection (RoD) from 1pg/mL to 10ng/mL with regression R2=0.9777. Ultra-sensitivity of the sensor with limit of detection (LoD) of 1 pg/mL has been achieved using nanocomposite of graphene nanoplatelet and diblock-co-polymer (poly(styrene)-block-poly(acrylic acid)) (PS-b-PAA) coated on filter paper followed by deposition of micro-Au electrodes. Standard cortisol in aqueous solution and human saliva samples were successfully tested by interfacing the sensor chip with programmable handheld impedance based analyzer. Results are finally compared with the standard ELISA and are in good agreement with R2=0.9386. We anticipate that this handheld electrochemical sensing technology has promising application to monitor psychological stress in POC setting.
{"title":"Ultra-sensitive paper-based biosensor for cortisol sensing in human saliva with electrical impedance analyzer","authors":"Muhammad S. Khan, K. Dighe, Zhen Wang, A. Schwartz-Duval, Dr. Santoshi Misra, D. Pan","doi":"10.1109/HIC.2017.8227615","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227615","url":null,"abstract":"Cortisol, a hormone commonly released upon increased stress level, is a biomarker for numerous diseases and plays an important role in the regulation of various physiological processes. Normally a cortisol level is elevated in oral saliva during the time of anxiety and depression. A portable biosensor device could provide an interesting digital instrument to the patients and people who desire precautionary onsite cortisol diagnosis without visiting psychiatrists and/or physicians. We have developed disposable paper-based biosensor chip to monitor cortisol with a wide range of detection (RoD) from 1pg/mL to 10ng/mL with regression R2=0.9777. Ultra-sensitivity of the sensor with limit of detection (LoD) of 1 pg/mL has been achieved using nanocomposite of graphene nanoplatelet and diblock-co-polymer (poly(styrene)-block-poly(acrylic acid)) (PS-b-PAA) coated on filter paper followed by deposition of micro-Au electrodes. Standard cortisol in aqueous solution and human saliva samples were successfully tested by interfacing the sensor chip with programmable handheld impedance based analyzer. Results are finally compared with the standard ELISA and are in good agreement with R2=0.9386. We anticipate that this handheld electrochemical sensing technology has promising application to monitor psychological stress in POC setting.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134585572","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227628
G. Q. Mamani, F. Fraga, Guilherme Tavares, E. Johns, N. Phillips
Alzheimer's Disease (AD) is a neurodegenerative syndrome affecting millions of people worldwide. Also, individuals with mild cognitive impairment (MCI) are in a group of risk that should be followed and treated since there is a high probability of evolution to AD. In this study we carried out an Event-Related Potential (ERP) analysis on patient and control groups from 32-channel EEG recorded during N-back working memory (WM) tasks with the aim of finding an ERP-based biomarker for early diagnosis of both AD and MCI. Participants were 15 AD patients, 20 individuals diagnosed with MCI and 26 age-matched healthy elderly (HE) controls. Subjects underwent a three-level visual N-back task with ascending memory load difficulty. Nonparametric Kruskal-Wallis tests with cluster correction and 5% significance level were used for statistical analysis. A considerable amount of significant differences between patient and control groups were found in the ERP during execution of the WM tasks, predominantly in fronto-centro-parietal electrodes. Such results are promising in the direction of achieving an early EEG-based diagnosis of MCI and AD.
{"title":"EEG-based biomarkers on working memory tasks for early diagnosis of Alzheimer's disease and mild cognitive impairment","authors":"G. Q. Mamani, F. Fraga, Guilherme Tavares, E. Johns, N. Phillips","doi":"10.1109/HIC.2017.8227628","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227628","url":null,"abstract":"Alzheimer's Disease (AD) is a neurodegenerative syndrome affecting millions of people worldwide. Also, individuals with mild cognitive impairment (MCI) are in a group of risk that should be followed and treated since there is a high probability of evolution to AD. In this study we carried out an Event-Related Potential (ERP) analysis on patient and control groups from 32-channel EEG recorded during N-back working memory (WM) tasks with the aim of finding an ERP-based biomarker for early diagnosis of both AD and MCI. Participants were 15 AD patients, 20 individuals diagnosed with MCI and 26 age-matched healthy elderly (HE) controls. Subjects underwent a three-level visual N-back task with ascending memory load difficulty. Nonparametric Kruskal-Wallis tests with cluster correction and 5% significance level were used for statistical analysis. A considerable amount of significant differences between patient and control groups were found in the ERP during execution of the WM tasks, predominantly in fronto-centro-parietal electrodes. Such results are promising in the direction of achieving an early EEG-based diagnosis of MCI and AD.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"274 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121211966","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227599
R. R. Lekkala, Srinivas Kuntamalla
Currently, heart Rate Variability (HRV) is derived from ECG. Many researchers have explored the usefulness of photoplethysmography (PPG), for the analysis of HRV. However, all these studies are based on statistical approach and used the correlation coefficient for comparing the two data sets obtained using ECG and PPG, which is inappropriate as the causal relationship between the R-peaks in ECG and the peaks in PPG is a physiologically established fact. In this study, the heart beat intervals measured from PPG, are compared, beat by beat, by taking the corresponding beat intervals of same cardiac cycle obtained from ECG and the measurement error is quantized. The error is found to be within 2% across the entire sample of 42 subjects, in spite of diversified constitution of the study group in terms of age, sex and pathology. Errors are also interpreted in terms of variations in pulse transit time. A very good agreement is found between the ECG and PPG derived parameters of HRV. In view of these findings, it may be concluded that PPG provides a safer and low cost option, in place of ECG, as a wearable sensor outside hospital environment, for the analysis of HRV, without compromising on accuracy.
{"title":"A novel approach for comparison of heart rate variability derived from synchronously measured electrocardiogram and photoplethysmogram","authors":"R. R. Lekkala, Srinivas Kuntamalla","doi":"10.1109/HIC.2017.8227599","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227599","url":null,"abstract":"Currently, heart Rate Variability (HRV) is derived from ECG. Many researchers have explored the usefulness of photoplethysmography (PPG), for the analysis of HRV. However, all these studies are based on statistical approach and used the correlation coefficient for comparing the two data sets obtained using ECG and PPG, which is inappropriate as the causal relationship between the R-peaks in ECG and the peaks in PPG is a physiologically established fact. In this study, the heart beat intervals measured from PPG, are compared, beat by beat, by taking the corresponding beat intervals of same cardiac cycle obtained from ECG and the measurement error is quantized. The error is found to be within 2% across the entire sample of 42 subjects, in spite of diversified constitution of the study group in terms of age, sex and pathology. Errors are also interpreted in terms of variations in pulse transit time. A very good agreement is found between the ECG and PPG derived parameters of HRV. In view of these findings, it may be concluded that PPG provides a safer and low cost option, in place of ECG, as a wearable sensor outside hospital environment, for the analysis of HRV, without compromising on accuracy.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"6 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127402063","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227596
F. van Wyk, Anahita Khojandi, R. Kamaleswaran, O. Akbilgic, S. Nemati, R. Davis
Sepsis is an acute, life-threatening condition that results from bacterial infections, often acquired in the hospital. Undetected, sepsis can progress to severe sepsis and septic shock, with a risk of death as high as 30% to 80%. Early detection of sepsis can improve patient outcomes. Collecting and evaluating continuous physiological variables, such as vital signs, using sophisticated classification algorithms may be highly beneficial to aid diagnosis of septic patients. However, setting up a data acquisition system that can collect (and store) high frequency/high volume data is challenging both from technology management and storage standpoints. In this paper, we build two deep learning models, a convolutional neural network and a multilayer perceptron model, to classify patients into sepsis and non-sepsis groups using data collected at various frequencies from the first 12 hours after admission. Our results indicate that the convolutional neural network model outperforms the multilayer perceptron model for all data collection frequencies. In addition, our results put into perspective the value of data collection frequency and translate its value into lives saved. Such analysis can guide future investments in data acquisition systems by hospitals.
{"title":"How much data should we collect? A case study in sepsis detection using deep learning","authors":"F. van Wyk, Anahita Khojandi, R. Kamaleswaran, O. Akbilgic, S. Nemati, R. Davis","doi":"10.1109/HIC.2017.8227596","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227596","url":null,"abstract":"Sepsis is an acute, life-threatening condition that results from bacterial infections, often acquired in the hospital. Undetected, sepsis can progress to severe sepsis and septic shock, with a risk of death as high as 30% to 80%. Early detection of sepsis can improve patient outcomes. Collecting and evaluating continuous physiological variables, such as vital signs, using sophisticated classification algorithms may be highly beneficial to aid diagnosis of septic patients. However, setting up a data acquisition system that can collect (and store) high frequency/high volume data is challenging both from technology management and storage standpoints. In this paper, we build two deep learning models, a convolutional neural network and a multilayer perceptron model, to classify patients into sepsis and non-sepsis groups using data collected at various frequencies from the first 12 hours after admission. Our results indicate that the convolutional neural network model outperforms the multilayer perceptron model for all data collection frequencies. In addition, our results put into perspective the value of data collection frequency and translate its value into lives saved. Such analysis can guide future investments in data acquisition systems by hospitals.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127478397","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227616
A. Phan, Phuong Truong, A. Kief, Milien Dhome, A. Camp, R. Weinreb, F. Talke
This paper reports on ex-vivo studies with rabbit eyes using an optical intraocular pressure (IOP) measurement system. The system consists of an optical reader and a miniaturized interferometric pressure sensor integrated onto a standard intraocular lens. The results show that the measurement sensitivity of the sensor is on the order of 22 nm/mmHg with an accuracy of ±0.5 mmHg post implantation. The optical method developed is a promising approach for monitoring intraocular pressure for glaucoma patients. The portability of the measurement system may allow patients and physicians to conveniently obtain measurements in a patient point-of-care setting or a clinical environment.
{"title":"Optical intraocular pressure measurement system for glaucoma management","authors":"A. Phan, Phuong Truong, A. Kief, Milien Dhome, A. Camp, R. Weinreb, F. Talke","doi":"10.1109/HIC.2017.8227616","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227616","url":null,"abstract":"This paper reports on ex-vivo studies with rabbit eyes using an optical intraocular pressure (IOP) measurement system. The system consists of an optical reader and a miniaturized interferometric pressure sensor integrated onto a standard intraocular lens. The results show that the measurement sensitivity of the sensor is on the order of 22 nm/mmHg with an accuracy of ±0.5 mmHg post implantation. The optical method developed is a promising approach for monitoring intraocular pressure for glaucoma patients. The portability of the measurement system may allow patients and physicians to conveniently obtain measurements in a patient point-of-care setting or a clinical environment.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131141300","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227570
S. Almouahed, C. Hamitouche, P. Poignet, E. Stindel
Energy harvesting inside human body is crucial for powering implantable long-term biomedical devices. In this paper, the performance of a piezoelectric energy harvester embedded within custom-designed knee implant in powering RF transmitter was evaluated through simulations. This power harvester is composed of four piezoelectric generators along with four off-the-shelf power conditioning circuits. It can harvest electric power from dynamic forces dissipated inside knee implant during walking. The results demonstrate the possibility to deliver a constant electric power of 59.4mW during a simulated walking cycle. This conditioned power can operate an off-the-shelf ultra-low power RF transmitter. This may eliminate the need for rechargeable batteries to power instrumented knee implants. The proposed piezoelectric generator along with the ultra-miniature power conditioning and telemetry circuits may be integrated within the knee implant without increasing its physical size or changing its geometrical shape significantly with respect to the conventional one. Therefore, its dynamic functionality and mechanical longevity may not be affected.
{"title":"Battery-free force sensor for instrumented knee implant","authors":"S. Almouahed, C. Hamitouche, P. Poignet, E. Stindel","doi":"10.1109/HIC.2017.8227570","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227570","url":null,"abstract":"Energy harvesting inside human body is crucial for powering implantable long-term biomedical devices. In this paper, the performance of a piezoelectric energy harvester embedded within custom-designed knee implant in powering RF transmitter was evaluated through simulations. This power harvester is composed of four piezoelectric generators along with four off-the-shelf power conditioning circuits. It can harvest electric power from dynamic forces dissipated inside knee implant during walking. The results demonstrate the possibility to deliver a constant electric power of 59.4mW during a simulated walking cycle. This conditioned power can operate an off-the-shelf ultra-low power RF transmitter. This may eliminate the need for rechargeable batteries to power instrumented knee implants. The proposed piezoelectric generator along with the ultra-miniature power conditioning and telemetry circuits may be integrated within the knee implant without increasing its physical size or changing its geometrical shape significantly with respect to the conventional one. Therefore, its dynamic functionality and mechanical longevity may not be affected.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123685249","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227576
Chen Lin, Yuan Zhou, Hu Wang, Yao Wang
Cuff-less blood pressure (BP) estimation using pulse transit time (PTT) is a promising method for long-term BP monitoring. However, state-of-art PTT models are unable to trace the change of pressure baseline in subjects, which limits their application in long-term BP tracking. This study investigated the relationship between the change of pressure baseline and pulse waveform in long-term BP monitoring. In the study, a total of 36 subjects received daily monitoring of systolic BP (SBP) and PTT for over one month. Linear regression was used to develop the SBP-ln(PTT) model for each subject. SBP predictions with regression differences greater than + SD (7.63 mmHg) were assumed to be with positive/negative baseline offset. For each subject, 12 features extracted from pulse waveform were obtained and their values were converted to standard scores to quantify pulse waveform variation. Independent two-sample t-test showed five pulse wave features changed significantly when subjects' pressure baseline varied. Furthermore, the consistency of pulse waveform variation was validated over the change of pressure baseline in subjects. In summary, this study demonstrated that pulse waveform could indicate baseline offset in PTT-based BP estimation. By highlighting five pulse wave features, this study provides novel insights to overcome the challenge of frequent calibrations in long-term PTT-based BP monitoring.
{"title":"Pulse waveform as an indicator of baseline offset in pulse transit time based blood pressure estimation","authors":"Chen Lin, Yuan Zhou, Hu Wang, Yao Wang","doi":"10.1109/HIC.2017.8227576","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227576","url":null,"abstract":"Cuff-less blood pressure (BP) estimation using pulse transit time (PTT) is a promising method for long-term BP monitoring. However, state-of-art PTT models are unable to trace the change of pressure baseline in subjects, which limits their application in long-term BP tracking. This study investigated the relationship between the change of pressure baseline and pulse waveform in long-term BP monitoring. In the study, a total of 36 subjects received daily monitoring of systolic BP (SBP) and PTT for over one month. Linear regression was used to develop the SBP-ln(PTT) model for each subject. SBP predictions with regression differences greater than + SD (7.63 mmHg) were assumed to be with positive/negative baseline offset. For each subject, 12 features extracted from pulse waveform were obtained and their values were converted to standard scores to quantify pulse waveform variation. Independent two-sample t-test showed five pulse wave features changed significantly when subjects' pressure baseline varied. Furthermore, the consistency of pulse waveform variation was validated over the change of pressure baseline in subjects. In summary, this study demonstrated that pulse waveform could indicate baseline offset in PTT-based BP estimation. By highlighting five pulse wave features, this study provides novel insights to overcome the challenge of frequent calibrations in long-term PTT-based BP monitoring.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"221 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121389913","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 : 2017-11-01DOI: 10.1109/HIC.2017.8227625
D. Bender, R. Morgan, V. Nadkarni, C. Nataraj
In this study we address an important pediatric cardiopulmonary resuscitation problem to identify the cause of a cardiac arrest during the beginning of cardiopulmonary resuscitation. A support vector algorithm was trained and tested using a feature set constructed through wavelet transform analysis of experimental electrocardiography and heart rate data provided by Children's Hospital of Philadelphia. The approach developed in this study yielded an average classification accuracy above 93%.
{"title":"Classification of asphyxia & ventricular fibrillation induced cardiac arrest for cardiopulmonary resuscitation","authors":"D. Bender, R. Morgan, V. Nadkarni, C. Nataraj","doi":"10.1109/HIC.2017.8227625","DOIUrl":"https://doi.org/10.1109/HIC.2017.8227625","url":null,"abstract":"In this study we address an important pediatric cardiopulmonary resuscitation problem to identify the cause of a cardiac arrest during the beginning of cardiopulmonary resuscitation. A support vector algorithm was trained and tested using a feature set constructed through wavelet transform analysis of experimental electrocardiography and heart rate data provided by Children's Hospital of Philadelphia. The approach developed in this study yielded an average classification accuracy above 93%.","PeriodicalId":120815,"journal":{"name":"2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129773899","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：