Pub Date : 2019-11-01DOI: 10.1109/HI-POCT45284.2019.8962773
A. Jasuja, Varan Gupta, N. Sreenivasalu, Mary Liu, J. Monz, J. Nir, S. Bhasin
Hemiparesis is progressive muscle weakness in one half of the body, commonly observed in traumatic brain injury or stroke patients. Usually, physiotherapists design in-person assistive exercises to restore muscle strength and range of motion for affected side of the patient. Alternatively, functional electrical stimulation (FES) devices have also been used, though the equipment is expensive, non-portable, and provides limited configurability for personalized rehabilitation. This paper presents a low-cost, open architecture framework that enables: a) Remote programming of muscle stimulation routine by therapist; b) Delivery of FES sequence to patient wirelessly, and c) Provide quantitative feedback (through Electromyogram (EMG)) on dynamics of exercised muscle with progressive rehabilitation of the patient. The extensible framework overcomes the major drawback of expensive, closed commercial systems, thereby allowing integration of multiple sensors to monitor muscle function. Rehabilitation efficacy feedback will allow an opportunity to personalize rehabilitation and increase patient compliance.
{"title":"Development of an extensible, wireless framework for personalized muscle rehabilitation","authors":"A. Jasuja, Varan Gupta, N. Sreenivasalu, Mary Liu, J. Monz, J. Nir, S. Bhasin","doi":"10.1109/HI-POCT45284.2019.8962773","DOIUrl":"https://doi.org/10.1109/HI-POCT45284.2019.8962773","url":null,"abstract":"Hemiparesis is progressive muscle weakness in one half of the body, commonly observed in traumatic brain injury or stroke patients. Usually, physiotherapists design in-person assistive exercises to restore muscle strength and range of motion for affected side of the patient. Alternatively, functional electrical stimulation (FES) devices have also been used, though the equipment is expensive, non-portable, and provides limited configurability for personalized rehabilitation. This paper presents a low-cost, open architecture framework that enables: a) Remote programming of muscle stimulation routine by therapist; b) Delivery of FES sequence to patient wirelessly, and c) Provide quantitative feedback (through Electromyogram (EMG)) on dynamics of exercised muscle with progressive rehabilitation of the patient. The extensible framework overcomes the major drawback of expensive, closed commercial systems, thereby allowing integration of multiple sensors to monitor muscle function. Rehabilitation efficacy feedback will allow an opportunity to personalize rehabilitation and increase patient compliance.","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128122362","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 : 2019-11-01DOI: 10.1109/hi-poct45284.2019.8962822
{"title":"HI-POCT 2019 Committees","authors":"","doi":"10.1109/hi-poct45284.2019.8962822","DOIUrl":"https://doi.org/10.1109/hi-poct45284.2019.8962822","url":null,"abstract":"","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132112773","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 : 2019-11-01DOI: 10.1109/HI-POCT45284.2019.8962887
Yilun You, Beena Ahmed, Polly Barr, K. Ballard, M. Valenzuela
Cognitive reserve exposures are a major class of dementia risk predictors, but a biomarker has proven elusive. Here, we show that paralinguistic features extracted from audio recordings of older participants completing the LOGOS episodic memory test can be used to identify participants with high and low estimable cognitive reserve, and hence low and high dementia risk, respectively. We present a parallel classification system consisting of an ensemble of a k-NN model and SVM model that discriminates between participants at high risk and low risk of dementia with an accuracy of 94.7% when trained with paralinguistic features only and 97.2% when trained with paralinguistic and episodic memory features.
{"title":"Predicting Dementia Risk Using Paralinguistic and Memory Test Features with Machine Learning Models","authors":"Yilun You, Beena Ahmed, Polly Barr, K. Ballard, M. Valenzuela","doi":"10.1109/HI-POCT45284.2019.8962887","DOIUrl":"https://doi.org/10.1109/HI-POCT45284.2019.8962887","url":null,"abstract":"Cognitive reserve exposures are a major class of dementia risk predictors, but a biomarker has proven elusive. Here, we show that paralinguistic features extracted from audio recordings of older participants completing the LOGOS episodic memory test can be used to identify participants with high and low estimable cognitive reserve, and hence low and high dementia risk, respectively. We present a parallel classification system consisting of an ensemble of a k-NN model and SVM model that discriminates between participants at high risk and low risk of dementia with an accuracy of 94.7% when trained with paralinguistic features only and 97.2% when trained with paralinguistic and episodic memory features.","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128761362","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 : 2019-11-01DOI: 10.1109/HI-POCT45284.2019.8962856
A. Ajmal, S. Shankarnath, Mohamed Athif, E. Jayatunga
Hemoglobin concentration is a vital parameter used to detect abnormalities in the human body including anemia and polycythemia. Currently, invasive techniques are used for hemoglobin measurement despite their many disadvantages including discomfort and potential complications for the pregnant, elderly and pediatric patients. This research paper focuses on measuring the hemoglobin concentration without drawing blood. In this study, measurements were obtained from a total of 106 patients and a linear relationship was obtained between hemoglobin concentration measured using the invasive technique (Hb) and the modulation ratio (R) calculated using red light and near-IR spectroscopy. The effect of confounding factors of gender and age were studied in this relationship. Based on the mathematical model developed, a non-invasive screening tool was developed to determine hemoglobin concentration. The device was evaluated using the 22 test subjects. The state-of-the-art hemoglobin measuring techniques do not facilitate continuous and remote monitoring which is essential in a point of care screening device. The proposed non-invasive device has the advantages of prevention of infections, physical pain, and the low operational or maintenance costs while being portable.
{"title":"Non-Invasive Screening Tool to Detect Anemia","authors":"A. Ajmal, S. Shankarnath, Mohamed Athif, E. Jayatunga","doi":"10.1109/HI-POCT45284.2019.8962856","DOIUrl":"https://doi.org/10.1109/HI-POCT45284.2019.8962856","url":null,"abstract":"Hemoglobin concentration is a vital parameter used to detect abnormalities in the human body including anemia and polycythemia. Currently, invasive techniques are used for hemoglobin measurement despite their many disadvantages including discomfort and potential complications for the pregnant, elderly and pediatric patients. This research paper focuses on measuring the hemoglobin concentration without drawing blood. In this study, measurements were obtained from a total of 106 patients and a linear relationship was obtained between hemoglobin concentration measured using the invasive technique (Hb) and the modulation ratio (R) calculated using red light and near-IR spectroscopy. The effect of confounding factors of gender and age were studied in this relationship. Based on the mathematical model developed, a non-invasive screening tool was developed to determine hemoglobin concentration. The device was evaluated using the 22 test subjects. The state-of-the-art hemoglobin measuring techniques do not facilitate continuous and remote monitoring which is essential in a point of care screening device. The proposed non-invasive device has the advantages of prevention of infections, physical pain, and the low operational or maintenance costs while being portable.","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124380624","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 : 2019-11-01DOI: 10.1109/HI-POCT45284.2019.8962884
Divaakar Siva Baala Sundaram, Suganti Shivaram, R. Balasubramani, Anjani Muthyala, S. P. Arunachalam
Electrical recordings of the heart sounds namely, the phonocardiogram (PCG) signals contain information regarding the heart condition of diagnostic importance. Characteristic features of PCG signals have been explored using several automatic detection algorithms to aid in disease diagnosis. A major limitation is that, many of these methods have been demonstrated only on PCG clean signals with limited test data that lacks variety to provide information of diagnostic importance. A more robust method to characterize PCG signal is required that can aid in discriminating normal and diseased heart conditions such as heart murmur etc. In this work, it was hypothesized that a multiscale frequency (MSF) analysis can discriminate normal PCG and PCG with murmur based on their varying frequency content. 13 samples of normal PCG and heart sound signal with murmur from Peter Bentley Heart Sounds Database sampled at 44.1 kHz were used for analysis. A 4th order Butterworth lowpass filter was designed with cutoff frequency at 200 Hz to remove higher frequency noise and MSF estimation was performed on the filtered dataset using custom MATLAB software. Mann-Whitney test was performed for statistical significance at p < 0.05. The mean MSF for normal PCG was 108.94±13.38 Hz and the mean MSF for murmur heart sound signal was 47.71±16.31 Hz. MSF was significantly different between normal and murmur sound signal with p < 0.01. Validation of this technique with larger dataset is required. MSF technique can discriminate normal PCG and murmur sound signal. The results motivate the analysis and comparison of normal PCG’s with different cardiac conditions that can aid in disease diagnosis.
{"title":"Robust Discrimination of Phonocardiogram Signal with Normal Heart Sounds and Murmur Using a Multiscale Frequency Analysis","authors":"Divaakar Siva Baala Sundaram, Suganti Shivaram, R. Balasubramani, Anjani Muthyala, S. P. Arunachalam","doi":"10.1109/HI-POCT45284.2019.8962884","DOIUrl":"https://doi.org/10.1109/HI-POCT45284.2019.8962884","url":null,"abstract":"Electrical recordings of the heart sounds namely, the phonocardiogram (PCG) signals contain information regarding the heart condition of diagnostic importance. Characteristic features of PCG signals have been explored using several automatic detection algorithms to aid in disease diagnosis. A major limitation is that, many of these methods have been demonstrated only on PCG clean signals with limited test data that lacks variety to provide information of diagnostic importance. A more robust method to characterize PCG signal is required that can aid in discriminating normal and diseased heart conditions such as heart murmur etc. In this work, it was hypothesized that a multiscale frequency (MSF) analysis can discriminate normal PCG and PCG with murmur based on their varying frequency content. 13 samples of normal PCG and heart sound signal with murmur from Peter Bentley Heart Sounds Database sampled at 44.1 kHz were used for analysis. A 4th order Butterworth lowpass filter was designed with cutoff frequency at 200 Hz to remove higher frequency noise and MSF estimation was performed on the filtered dataset using custom MATLAB software. Mann-Whitney test was performed for statistical significance at p < 0.05. The mean MSF for normal PCG was 108.94±13.38 Hz and the mean MSF for murmur heart sound signal was 47.71±16.31 Hz. MSF was significantly different between normal and murmur sound signal with p < 0.01. Validation of this technique with larger dataset is required. MSF technique can discriminate normal PCG and murmur sound signal. The results motivate the analysis and comparison of normal PCG’s with different cardiac conditions that can aid in disease diagnosis.","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129189126","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 : 2019-11-01DOI: 10.1109/hi-poct45284.2019.8962760
{"title":"HI-POCT 2019 Sponsors","authors":"","doi":"10.1109/hi-poct45284.2019.8962760","DOIUrl":"https://doi.org/10.1109/hi-poct45284.2019.8962760","url":null,"abstract":"","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126066605","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 : 2019-11-01DOI: 10.1109/HI-POCT45284.2019.8962792
Julia Loegering, Kevin Krause, Jesse Ahlquist, Kevin Webb, Karen Xu, N. Tran, D. Greenhalgh, T. Palmieri
Total body surface area (TBSA) is a critical biometric for accurate body fluid restoration and drug dosing in medical treatments. However, current clinical equation calculations of TBSA are highly inaccurate, resulting in error up to 25%. Within burn care, this error leads to misinformed fluid resuscitation that result in increased medical complications. Our team sought to combine recently developed mathematical equations that are clinically unutilized with 3D scanning methods to better the accuracy of TBSA calculations in treatment. To bridge the gap between modern TBSA equations and the clinic, we developed an algorithm that indexes an equation best suited to a patient according to inputs such as age, height and weight. For patients that cannot be matched to an appropriate equation, our team developed a time-of-flight scanning protocol to capture 3D models of the human body. From these models, TBSA can be extrapolated finite analysis deconstruction and image processing tools. Our scanning device reduced error of TBSA to an average of 4% across all scanned subjects and it proved to be one of the first 3D scanning devices compatible to the clinic workflow.
{"title":"Point-of-care 3D body-mapping for determining total body surface area of severely burned patients","authors":"Julia Loegering, Kevin Krause, Jesse Ahlquist, Kevin Webb, Karen Xu, N. Tran, D. Greenhalgh, T. Palmieri","doi":"10.1109/HI-POCT45284.2019.8962792","DOIUrl":"https://doi.org/10.1109/HI-POCT45284.2019.8962792","url":null,"abstract":"Total body surface area (TBSA) is a critical biometric for accurate body fluid restoration and drug dosing in medical treatments. However, current clinical equation calculations of TBSA are highly inaccurate, resulting in error up to 25%. Within burn care, this error leads to misinformed fluid resuscitation that result in increased medical complications. Our team sought to combine recently developed mathematical equations that are clinically unutilized with 3D scanning methods to better the accuracy of TBSA calculations in treatment. To bridge the gap between modern TBSA equations and the clinic, we developed an algorithm that indexes an equation best suited to a patient according to inputs such as age, height and weight. For patients that cannot be matched to an appropriate equation, our team developed a time-of-flight scanning protocol to capture 3D models of the human body. From these models, TBSA can be extrapolated finite analysis deconstruction and image processing tools. Our scanning device reduced error of TBSA to an average of 4% across all scanned subjects and it proved to be one of the first 3D scanning devices compatible to the clinic workflow.","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133374077","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 : 2019-09-05DOI: 10.1109/HI-POCT45284.2019.8962827
Md Sirajus Salekin, Ghada Zamzami, Rahul Paul, Dmitry Goldgof, R. Kasturi, T. Ho, Yu Sun
Neonatal pain assessment in clinical environments is challenging as it is discontinuous and biased. Facial/body occlusion can occur in such settings due to clinical condition, developmental delays, prone position, or other external factors. In such cases, crying sound can be used to effectively assess neonatal pain. In this paper, we investigate the use of a novel CNN architecture (N-CNN) along with other CNN architectures (VGG16 and ResNet50) for assessing pain from crying sounds of neonates. The experimental results demonstrate that using our novel N-CNN for assessing pain from the sounds of neonates has a strong clinical potential and provides a viable alternative to the current assessment practice.
{"title":"Harnessing the Power of Deep Learning Methods in Healthcare: Neonatal Pain Assessment from Crying Sound","authors":"Md Sirajus Salekin, Ghada Zamzami, Rahul Paul, Dmitry Goldgof, R. Kasturi, T. Ho, Yu Sun","doi":"10.1109/HI-POCT45284.2019.8962827","DOIUrl":"https://doi.org/10.1109/HI-POCT45284.2019.8962827","url":null,"abstract":"Neonatal pain assessment in clinical environments is challenging as it is discontinuous and biased. Facial/body occlusion can occur in such settings due to clinical condition, developmental delays, prone position, or other external factors. In such cases, crying sound can be used to effectively assess neonatal pain. In this paper, we investigate the use of a novel CNN architecture (N-CNN) along with other CNN architectures (VGG16 and ResNet50) for assessing pain from crying sounds of neonates. The experimental results demonstrate that using our novel N-CNN for assessing pain from the sounds of neonates has a strong clinical potential and provides a viable alternative to the current assessment practice.","PeriodicalId":269346,"journal":{"name":"2019 IEEE Healthcare Innovations and Point of Care Technologies, (HI-POCT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114622461","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：