Pub Date : 2024-03-21DOI: 10.1109/JTEHM.2024.3368106
Takhellambam Gautam Meitei;Wei-Chun Chang;Pou-Leng Cheong;Yi-Min Wang;Chia-Wei Sun
Osteoporosis is a prevalent chronic disease worldwide, particularly affecting the aging population. The gold standard diagnostic tool for osteoporosis is Dual-energy X-ray Absorptiometry (DXA). However, the expensive cost of the DXA machine and the need for skilled professionals to operate it restrict its accessibility to the general public. This paper builds upon previous research and proposes a novel approach for rapidly screening bone density. The method involves utilizing near-infrared light to capture local body information within the human body. Deep learning techniques are employed to analyze the obtained data and extract meaningful insights related to bone density. Our initial prediction, utilizing multi-linear regression, demonstrated a strong correlation (r = 0.98, p-value = 0.003**) with the measured Bone Mineral Density (BMD) obtained from Dual-energy X-ray Absorptiometry (DXA). This indicates a highly significant relationship between the predicted values and the actual BMD measurements. A deep learning-based algorithm is applied to analyze the underlying information further to predict bone density at the wrist, hip, and spine. The prediction of bone densities in the hip and spine holds significant importance due to their status as gold-standard sites for assessing an individual’s bone density. Our prediction rate had an error margin below 10% for the wrist and below 20% for the hip and spine bone density.
骨质疏松症是一种全球流行的慢性疾病，对老龄人口的影响尤为严重。骨质疏松症的金标准诊断工具是双能 X 射线吸收测定法（DXA）。然而，DXA 仪器价格昂贵，而且需要熟练的专业人员操作，这限制了普通大众对它的使用。本文在以往研究的基础上，提出了一种快速筛查骨密度的新方法。该方法利用近红外线捕捉人体局部信息。利用深度学习技术来分析获得的数据，并提取与骨密度相关的有意义的见解。我们利用多线性回归进行的初步预测显示，该预测与通过双能 X 射线吸收仪（DXA）测量的骨密度（BMD）之间存在很强的相关性（r = 0.98，p 值 = 0.003**）。这表明预测值与实际 BMD 测量值之间存在着非常显著的关系。应用基于深度学习的算法进一步分析基础信息，以预测手腕、髋部和脊柱的骨密度。由于髋部和脊柱是评估个人骨密度的黄金标准部位，因此预测这两个部位的骨密度具有重要意义。我们对腕部骨密度的预测误差率低于 10%，对髋部和脊柱骨密度的预测误差率低于 20%。
{"title":"A Study on Intelligent Optical Bone Densitometry","authors":"Takhellambam Gautam Meitei;Wei-Chun Chang;Pou-Leng Cheong;Yi-Min Wang;Chia-Wei Sun","doi":"10.1109/JTEHM.2024.3368106","DOIUrl":"10.1109/JTEHM.2024.3368106","url":null,"abstract":"Osteoporosis is a prevalent chronic disease worldwide, particularly affecting the aging population. The gold standard diagnostic tool for osteoporosis is Dual-energy X-ray Absorptiometry (DXA). However, the expensive cost of the DXA machine and the need for skilled professionals to operate it restrict its accessibility to the general public. This paper builds upon previous research and proposes a novel approach for rapidly screening bone density. The method involves utilizing near-infrared light to capture local body information within the human body. Deep learning techniques are employed to analyze the obtained data and extract meaningful insights related to bone density. Our initial prediction, utilizing multi-linear regression, demonstrated a strong correlation (r = 0.98, p-value = 0.003**) with the measured Bone Mineral Density (BMD) obtained from Dual-energy X-ray Absorptiometry (DXA). This indicates a highly significant relationship between the predicted values and the actual BMD measurements. A deep learning-based algorithm is applied to analyze the underlying information further to predict bone density at the wrist, hip, and spine. The prediction of bone densities in the hip and spine holds significant importance due to their status as gold-standard sites for assessing an individual’s bone density. Our prediction rate had an error margin below 10% for the wrist and below 20% for the hip and spine bone density.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"401-412"},"PeriodicalIF":3.4,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10477504","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140202996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: CHIVID is a telemedicine solution developed under tight time constraints that assists Thai healthcare practitioners in monitoring non-severe COVID-19 patients in isolation programs during crises. It assesses patient health and notifies healthcare practitioners of high-risk scenarios through a chatbot. The system was designed to integrate with the famous Thai messaging app LINE, reducing development time and enhancing user-friendliness, and the system allowed patients to upload a pulse oximeter image automatically processed by the PACMAN function to extract oxygen saturation and heart rate values to reduce patient input errors. Methods: This article describes the proposed system and presents a mixed-methods study that evaluated the system’s performance by collecting survey responses from 70 healthcare practitioners and analyzing 14,817 patient records. Results: Approximately 71.4% of healthcare practitioners use the system more than twice daily, with the majority managing 1–10 patients, while 11.4% handle over 101 patients. The progress note is a function that healthcare practitioners most frequently use and are satisfied with. Regarding patient data, 58.9%(8,724/14,817) are male, and 49.7%(7,367/14,817) within the 18 to 34 age range. The average length of isolation was 7.6 days, and patients submitted progress notes twice daily on average. Notably, individuals aged 18 to 34 demonstrated the highest utilization rates for the PACMAN function. Furthermore, most patients, totaling over 95.52%(14,153/14,817), were discharged normally. Conclusion: The findings indicate that CHIVID could be one of the telemedicine solutions for hospitals with patient overflow and healthcare practitioners unfamiliar with telemedicine technology to improve patient care during a critical crisis. Clinical and Translational Impact Statement— CHIVID’s success arises from seamlessly integrating telemedicine into third-party application within a limited timeframe and effectively using clinical decision support systems to address challenges during the COVID-19 crisis.
{"title":"CHIVID: A Rapid Deployment of Community and Home Isolation During COVID-19 Pandemics","authors":"Parpada Piamjinda;Chiraphat Boonnag;Piyalitt Ittichaiwong;Seandee Rattanasonrerk;Kanyakorn Veerakanjana;Khanita Duangchaemkarn;Warissara Limpornchitwilai;Kamonwan Thanontip;Napasara Asawalertsak;Thitikorn Kaewlee;Theerawit Wilaiprasitporn","doi":"10.1109/JTEHM.2024.3377258","DOIUrl":"10.1109/JTEHM.2024.3377258","url":null,"abstract":"Background: CHIVID is a telemedicine solution developed under tight time constraints that assists Thai healthcare practitioners in monitoring non-severe COVID-19 patients in isolation programs during crises. It assesses patient health and notifies healthcare practitioners of high-risk scenarios through a chatbot. The system was designed to integrate with the famous Thai messaging app LINE, reducing development time and enhancing user-friendliness, and the system allowed patients to upload a pulse oximeter image automatically processed by the PACMAN function to extract oxygen saturation and heart rate values to reduce patient input errors. Methods: This article describes the proposed system and presents a mixed-methods study that evaluated the system’s performance by collecting survey responses from 70 healthcare practitioners and analyzing 14,817 patient records. Results: Approximately 71.4% of healthcare practitioners use the system more than twice daily, with the majority managing 1–10 patients, while 11.4% handle over 101 patients. The progress note is a function that healthcare practitioners most frequently use and are satisfied with. Regarding patient data, 58.9%(8,724/14,817) are male, and 49.7%(7,367/14,817) within the 18 to 34 age range. The average length of isolation was 7.6 days, and patients submitted progress notes twice daily on average. Notably, individuals aged 18 to 34 demonstrated the highest utilization rates for the PACMAN function. Furthermore, most patients, totaling over 95.52%(14,153/14,817), were discharged normally. Conclusion: The findings indicate that CHIVID could be one of the telemedicine solutions for hospitals with patient overflow and healthcare practitioners unfamiliar with telemedicine technology to improve patient care during a critical crisis. Clinical and Translational Impact Statement— CHIVID’s success arises from seamlessly integrating telemedicine into third-party application within a limited timeframe and effectively using clinical decision support systems to address challenges during the COVID-19 crisis.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"390-400"},"PeriodicalIF":3.4,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10472531","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140126520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Acoustic features extracted from speech can help with the diagnosis of neurological diseases and monitoring of symptoms over time. Temporal segmentation of audio signals into individual words is an important pre-processing step needed prior to extracting acoustic features. Machine learning techniques could be used to automate speech segmentation via automatic speech recognition (ASR) and sequence to sequence alignment. While state-of-the-art ASR models achieve good performance on healthy speech, their performance significantly drops when evaluated on dysarthric speech. Fine-tuning ASR models on impaired speech can improve performance in dysarthric individuals, but it requires representative clinical data, which is difficult to collect and may raise privacy concerns. This study explores the feasibility of using two augmentation methods to increase ASR performance on dysarthric speech: 1) healthy individuals varying their speaking rate and loudness (as is often used in assessments of pathological speech); 2) synthetic speech with variations in speaking rate and accent (to ensure more diverse vocal representations and fairness). Experimental evaluations showed that fine-tuning a pre-trained ASR model with data from these two sources outperformed a model fine-tuned only on real clinical data and matched the performance of a model fine-tuned on the combination of real clinical data and synthetic speech. When evaluated on held-out acoustic data from 24 individuals with various neurological diseases, the best performing model achieved an average word error rate of 5.7% and a mean correct count accuracy of 94.4%. In segmenting the data into individual words, a mean intersection-over-union of 89.2% was obtained against manual parsing (ground truth). It can be concluded that emulated and synthetic augmentations can significantly reduce the need for real clinical data of dysarthric speech when fine-tuning ASR models and, in turn, for speech segmentation.
从语音中提取声学特征有助于诊断神经系统疾病和监测症状的变化。将音频信号按时间分割成单个单词是提取声学特征前所需的重要预处理步骤。机器学习技术可用于通过自动语音识别（ASR）和序列对序列配准自动进行语音分割。虽然最先进的 ASR 模型在健康语音上取得了良好的性能，但在评估听力障碍语音时，其性能却明显下降。在受损语音上对 ASR 模型进行微调可以提高发育障碍患者的性能，但这需要有代表性的临床数据，而这些数据很难收集，而且可能会引起隐私方面的担忧。本研究探讨了使用两种增强方法提高肢体运动障碍语音的 ASR 性能的可行性：1) 改变健康人的说话速度和响度（病理语音评估中常用的方法）；2) 改变说话速度和口音的合成语音（以确保更多样化的声音表现和公平性）。实验评估结果表明，利用这两种来源的数据对预先训练好的 ASR 模型进行微调，其效果优于仅根据真实临床数据进行微调的模型，并且与根据真实临床数据和合成语音组合进行微调的模型效果相当。在对 24 名患有各种神经系统疾病的患者的语音数据进行评估时，表现最好的模型的平均单词错误率为 5.7%，平均正确计数准确率为 94.4%。在将数据分割成单个单词时，与人工解析（地面实况）相比，平均交叉-重合率达到 89.2%。可以得出这样的结论：在微调 ASR 模型时，仿真和合成增强可以大大减少对真实临床语音数据的需求，进而减少对语音分段的需求。
{"title":"Improving Dysarthric Speech Segmentation With Emulated and Synthetic Augmentation","authors":"Saeid Alavi Naeini;Leif Simmatis;Deniz Jafari;Yana Yunusova;Babak Taati","doi":"10.1109/JTEHM.2024.3375323","DOIUrl":"10.1109/JTEHM.2024.3375323","url":null,"abstract":"Acoustic features extracted from speech can help with the diagnosis of neurological diseases and monitoring of symptoms over time. Temporal segmentation of audio signals into individual words is an important pre-processing step needed prior to extracting acoustic features. Machine learning techniques could be used to automate speech segmentation via automatic speech recognition (ASR) and sequence to sequence alignment. While state-of-the-art ASR models achieve good performance on healthy speech, their performance significantly drops when evaluated on dysarthric speech. Fine-tuning ASR models on impaired speech can improve performance in dysarthric individuals, but it requires representative clinical data, which is difficult to collect and may raise privacy concerns. This study explores the feasibility of using two augmentation methods to increase ASR performance on dysarthric speech: 1) healthy individuals varying their speaking rate and loudness (as is often used in assessments of pathological speech); 2) synthetic speech with variations in speaking rate and accent (to ensure more diverse vocal representations and fairness). Experimental evaluations showed that fine-tuning a pre-trained ASR model with data from these two sources outperformed a model fine-tuned only on real clinical data and matched the performance of a model fine-tuned on the combination of real clinical data and synthetic speech. When evaluated on held-out acoustic data from 24 individuals with various neurological diseases, the best performing model achieved an average word error rate of 5.7% and a mean correct count accuracy of 94.4%. In segmenting the data into individual words, a mean intersection-over-union of 89.2% was obtained against manual parsing (ground truth). It can be concluded that emulated and synthetic augmentations can significantly reduce the need for real clinical data of dysarthric speech when fine-tuning ASR models and, in turn, for speech segmentation.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"382-389"},"PeriodicalIF":3.4,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10464345","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140105378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: Blood circulation is an important indicator of wound healing. In this study, a tissue oxygen saturation detecting (TOSD) system that is based on multispectral imaging (MSI) is proposed to quantify the degree of tissue oxygen saturation (StO2) in cutaneous tissues. Methods: A wound segmentation algorithm is used to segment automatically wound and skin areas, eliminating the need for manual labeling and applying adaptive tissue optics. Animal experiments were conducted on six mice in which they were observed seven times, once every two days. The TOSD system illuminated cutaneous tissues with two wavelengths of light - red ( $mathrm {lambda } = 660$ nm) and near-infrared ( $mathrm {lambda } = 880$ nm), and StO2 levels were calculated using images that were captured using a monochrome camera. The wound segmentation algorithm using ResNet34-based U-Net was integrated with computer vision techniques to improve its performance. Results: Animal experiments revealed that the wound segmentation algorithm achieved a Dice score of 93.49%. The StO2 levels that were determined using the TOSD system varied significantly among the phases of wound healing. Changes in StO2 levels were detected before laser speckle contrast imaging (LSCI) detected changes in blood flux. Moreover, statistical features that were extracted from the TOSD system and LSCI were utilized in principal component analysis (PCA) to visualize different wound healing phases. The average silhouette coefficients of the TOSD system with segmentation (ResNet34-based U-Net) and LSCI were 0.2890 and 0.0194, respectively. Conclusion: By detecting the StO2 levels of cutaneous tissues using the TOSD system with segmentation, the phases of wound healing were accurately distinguished. This method can support medical personnel in conducting precise wound assessments. Clinical and Translational Impact Statement—This study supports efforts in monitoring StO2 levels, wound segmentation, and wound healing phase classification to improve the efficiency and accuracy of preclinical research in the field.
{"title":"Multispectral Imaging-Based System for Detecting Tissue Oxygen Saturation With Wound Segmentation for Monitoring Wound Healing","authors":"Chih-Lung Lin;Meng-Hsuan Wu;Yuan-Hao Ho;Fang-Yi Lin;Yu-Hsien Lu;Yuan-Yu Hsueh;Chia-Chen Chen","doi":"10.1109/JTEHM.2024.3399232","DOIUrl":"10.1109/JTEHM.2024.3399232","url":null,"abstract":"Objective: Blood circulation is an important indicator of wound healing. In this study, a tissue oxygen saturation detecting (TOSD) system that is based on multispectral imaging (MSI) is proposed to quantify the degree of tissue oxygen saturation (StO2) in cutaneous tissues. Methods: A wound segmentation algorithm is used to segment automatically wound and skin areas, eliminating the need for manual labeling and applying adaptive tissue optics. Animal experiments were conducted on six mice in which they were observed seven times, once every two days. The TOSD system illuminated cutaneous tissues with two wavelengths of light - red (\u0000<inline-formula> <tex-math>$mathrm {lambda } = 660$ </tex-math></inline-formula>\u0000 nm) and near-infrared (\u0000<inline-formula> <tex-math>$mathrm {lambda } = 880$ </tex-math></inline-formula>\u0000 nm), and StO2 levels were calculated using images that were captured using a monochrome camera. The wound segmentation algorithm using ResNet34-based U-Net was integrated with computer vision techniques to improve its performance. Results: Animal experiments revealed that the wound segmentation algorithm achieved a Dice score of 93.49%. The StO2 levels that were determined using the TOSD system varied significantly among the phases of wound healing. Changes in StO2 levels were detected before laser speckle contrast imaging (LSCI) detected changes in blood flux. Moreover, statistical features that were extracted from the TOSD system and LSCI were utilized in principal component analysis (PCA) to visualize different wound healing phases. The average silhouette coefficients of the TOSD system with segmentation (ResNet34-based U-Net) and LSCI were 0.2890 and 0.0194, respectively. Conclusion: By detecting the StO2 levels of cutaneous tissues using the TOSD system with segmentation, the phases of wound healing were accurately distinguished. This method can support medical personnel in conducting precise wound assessments. Clinical and Translational Impact Statement—This study supports efforts in monitoring StO2 levels, wound segmentation, and wound healing phase classification to improve the efficiency and accuracy of preclinical research in the field.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"468-479"},"PeriodicalIF":3.4,"publicationDate":"2024-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10528306","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140925707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-09DOI: 10.1109/JTEHM.2024.3399261
Wenyu Xing;Yanping Yang;Yannan Zhou;Tao Jiang;Yifang Li;Yuanlin Song;Dongni Hou;Dean TA
Objective: Pulmonary cavity lesion is one of the commonly seen lesions in lung caused by a variety of malignant and non-malignant diseases. Diagnosis of a cavity lesion is commonly based on accurate recognition of the typical morphological characteristics. A deep learning-based model to automatically detect, segment, and quantify the region of cavity lesion on CT scans has potential in clinical diagnosis, monitoring, and treatment efficacy assessment. Methods: A weakly-supervised deep learning-based method named CSA2-ResNet was proposed to quantitatively characterize cavity lesions in this paper. The lung parenchyma was firstly segmented using a pretrained 2D segmentation model, and then the output with or without cavity lesions was fed into the developed deep neural network containing hybrid attention modules. Next, the visualized lesion was generated from the activation region of the classification network using gradient-weighted class activation mapping, and image processing was applied for post-processing to obtain the expected segmentation results of cavity lesions. Finally, the automatic characteristic measurement of cavity lesions (e.g., area and thickness) was developed and verified. Results: the proposed weakly-supervised segmentation method achieved an accuracy, precision, specificity, recall, and F1-score of 98.48%, 96.80%, 97.20%, 100%, and 98.36%, respectively. There is a significant improvement (P < 0.05) compared to other methods. Quantitative characterization of morphology also obtained good analysis effects. Conclusions: The proposed easily-trained and high-performance deep learning model provides a fast and effective way for the diagnosis and dynamic monitoring of pulmonary cavity lesions in clinic. Clinical and Translational Impact Statement: This model used artificial intelligence to achieve the detection and quantitative analysis of pulmonary cavity lesions in CT scans. The morphological features revealed in experiments can be utilized as potential indicators for diagnosis and dynamic monitoring of patients with cavity lesions
{"title":"Weakly-Supervised Segmentation-Based Quantitative Characterization of Pulmonary Cavity Lesions in CT Scans","authors":"Wenyu Xing;Yanping Yang;Yannan Zhou;Tao Jiang;Yifang Li;Yuanlin Song;Dongni Hou;Dean TA","doi":"10.1109/JTEHM.2024.3399261","DOIUrl":"10.1109/JTEHM.2024.3399261","url":null,"abstract":"Objective: Pulmonary cavity lesion is one of the commonly seen lesions in lung caused by a variety of malignant and non-malignant diseases. Diagnosis of a cavity lesion is commonly based on accurate recognition of the typical morphological characteristics. A deep learning-based model to automatically detect, segment, and quantify the region of cavity lesion on CT scans has potential in clinical diagnosis, monitoring, and treatment efficacy assessment. Methods: A weakly-supervised deep learning-based method named CSA2-ResNet was proposed to quantitatively characterize cavity lesions in this paper. The lung parenchyma was firstly segmented using a pretrained 2D segmentation model, and then the output with or without cavity lesions was fed into the developed deep neural network containing hybrid attention modules. Next, the visualized lesion was generated from the activation region of the classification network using gradient-weighted class activation mapping, and image processing was applied for post-processing to obtain the expected segmentation results of cavity lesions. Finally, the automatic characteristic measurement of cavity lesions (e.g., area and thickness) was developed and verified. Results: the proposed weakly-supervised segmentation method achieved an accuracy, precision, specificity, recall, and F1-score of 98.48%, 96.80%, 97.20%, 100%, and 98.36%, respectively. There is a significant improvement (P < 0.05) compared to other methods. Quantitative characterization of morphology also obtained good analysis effects. Conclusions: The proposed easily-trained and high-performance deep learning model provides a fast and effective way for the diagnosis and dynamic monitoring of pulmonary cavity lesions in clinic. Clinical and Translational Impact Statement: This model used artificial intelligence to achieve the detection and quantitative analysis of pulmonary cavity lesions in CT scans. The morphological features revealed in experiments can be utilized as potential indicators for diagnosis and dynamic monitoring of patients with cavity lesions","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"457-467"},"PeriodicalIF":3.4,"publicationDate":"2024-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10528288","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140925641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: Non-sustained supraventricular tachycardia (nsSVT) is associated with a higher risk of developing atrial fibrillation (AF), and, therefore, detection of nsSVT can improve AF screening efficiency. However, the detection is challenged by the lower signal quality of ECGs recorded using handheld devices and the presence of ectopic beats which may mimic the rhythm characteristics of nsSVT.Methods: The present study introduces a new nsSVT detector for use in single-lead, 30-s ECGs, based on the assumption that beats in an nsSVT episode exhibits similar morphology, implying that episodes with beats of deviating morphology, either due to ectopic beats or noise/artifacts, are excluded. A support vector machine is used to classify successive 5-beat sequences in a sliding window with respect to similar morphology. Due to the lack of adequate training data, the classifier is trained using simulated ECGs with varying signal-to-noise ratio. In a subsequent step, a set of rhythm criteria is applied to similar beat sequences to ensure that episode duration and heart rate is acceptable.Results: The performance of the proposed detector is evaluated using the StrokeStop II database, resulting in sensitivity, specificity, and positive predictive value of 84.6%, 99.4%, and 18.5%, respectively. Conclusion: The results show that a significant reduction in expert review burden (factor of 6) can be achieved using the proposed detector.Clinical and Translational Impact: The reduction in the expert review burden shows that nsSVT detection in AF screening can be made considerably more efficiently.
{"title":"Detection of Non-Sustained Supraventricular Tachycardia in Atrial Fibrillation Screening","authors":"Hesam Halvaei;Tove Hygrell;Emma Svennberg;Valentina D.A. Corino;Leif Sörnmo;Martin Stridh","doi":"10.1109/JTEHM.2024.3397739","DOIUrl":"10.1109/JTEHM.2024.3397739","url":null,"abstract":"Objective: Non-sustained supraventricular tachycardia (nsSVT) is associated with a higher risk of developing atrial fibrillation (AF), and, therefore, detection of nsSVT can improve AF screening efficiency. However, the detection is challenged by the lower signal quality of ECGs recorded using handheld devices and the presence of ectopic beats which may mimic the rhythm characteristics of nsSVT.Methods: The present study introduces a new nsSVT detector for use in single-lead, 30-s ECGs, based on the assumption that beats in an nsSVT episode exhibits similar morphology, implying that episodes with beats of deviating morphology, either due to ectopic beats or noise/artifacts, are excluded. A support vector machine is used to classify successive 5-beat sequences in a sliding window with respect to similar morphology. Due to the lack of adequate training data, the classifier is trained using simulated ECGs with varying signal-to-noise ratio. In a subsequent step, a set of rhythm criteria is applied to similar beat sequences to ensure that episode duration and heart rate is acceptable.Results: The performance of the proposed detector is evaluated using the StrokeStop II database, resulting in sensitivity, specificity, and positive predictive value of 84.6%, 99.4%, and 18.5%, respectively. Conclusion: The results show that a significant reduction in expert review burden (factor of 6) can be achieved using the proposed detector.Clinical and Translational Impact: The reduction in the expert review burden shows that nsSVT detection in AF screening can be made considerably more efficiently.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"480-487"},"PeriodicalIF":3.4,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521724","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140925721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-07DOI: 10.1109/JTEHM.2024.3397737
Ahmed Al-Hindawi;Marcela Vizcaychipi;Yiannis Demiris
Objective: Delirium, an acute confusional state, affects 20-80% of patients in Intensive Care Units (ICUs), one in three medically hospitalized patients, and up to 50% of all patients who have had surgery. Its development is associated with short- and long-term morbidity, and increased risk of death. Yet, we lack any rapid, objective, and automated method to diagnose delirium. Here, we detail the prospective deployment of a novel dual-camera contextual eye-tracking platform. We then use the data from this platform to contemporaneously classify delirium.Results: We recruited 42 patients, resulting in 210 (114 with delirium, 96 without) recordings of hospitalized patients in ICU across two centers, as part of a prospective multi-center feasibility pilot study. All recordings made with our platform were usable for analysis. We divided the collected data into training and validation cohorts based on the data originating center. We trained two Temporal Convolutional Network (TCN) models that can classify delirium using a pre-existing manual scoring system (Confusion Assessment Method in ICU (CAM-ICU)) as the training target. The first model uses eye movements only which achieves an Area Under the Receiver Operator Curve (AUROC) of 0.67 and a mean Average Precision (mAP) of 0.68. The second model uses the point of regard, the part of the scene the patient is looking at, and increases the AUROC to 0.76 and the mAP to 0.81. These models are the first to classify delirium using continuous non-invasive eye-tracking but will require further clinical prospective validation prior to use as a decision-support tool.Clinical impact: Eye-tracking is a biological signal that can be used to identify delirium in patients in ICU. The platform, alongside the trained neural networks, can automatically, objectively, and continuously classify delirium aiding in the early detection of the deteriorating patient. Future work is aimed at prospective evaluation and clinical translation.
{"title":"A Dual-Camera Eye-Tracking Platform for Rapid Real-Time Diagnosis of Acute Delirium: A Pilot Study","authors":"Ahmed Al-Hindawi;Marcela Vizcaychipi;Yiannis Demiris","doi":"10.1109/JTEHM.2024.3397737","DOIUrl":"10.1109/JTEHM.2024.3397737","url":null,"abstract":"Objective: Delirium, an acute confusional state, affects 20-80% of patients in Intensive Care Units (ICUs), one in three medically hospitalized patients, and up to 50% of all patients who have had surgery. Its development is associated with short- and long-term morbidity, and increased risk of death. Yet, we lack any rapid, objective, and automated method to diagnose delirium. Here, we detail the prospective deployment of a novel dual-camera contextual eye-tracking platform. We then use the data from this platform to contemporaneously classify delirium.Results: We recruited 42 patients, resulting in 210 (114 with delirium, 96 without) recordings of hospitalized patients in ICU across two centers, as part of a prospective multi-center feasibility pilot study. All recordings made with our platform were usable for analysis. We divided the collected data into training and validation cohorts based on the data originating center. We trained two Temporal Convolutional Network (TCN) models that can classify delirium using a pre-existing manual scoring system (Confusion Assessment Method in ICU (CAM-ICU)) as the training target. The first model uses eye movements only which achieves an Area Under the Receiver Operator Curve (AUROC) of 0.67 and a mean Average Precision (mAP) of 0.68. The second model uses the point of regard, the part of the scene the patient is looking at, and increases the AUROC to 0.76 and the mAP to 0.81. These models are the first to classify delirium using continuous non-invasive eye-tracking but will require further clinical prospective validation prior to use as a decision-support tool.Clinical impact: Eye-tracking is a biological signal that can be used to identify delirium in patients in ICU. The platform, alongside the trained neural networks, can automatically, objectively, and continuously classify delirium aiding in the early detection of the deteriorating patient. Future work is aimed at prospective evaluation and clinical translation.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"488-498"},"PeriodicalIF":3.7,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140925709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-26DOI: 10.1109/JTEHM.2024.3369764
Shuanglin Li;Rajesh Nair;Syed Mohsen Naqvi
Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder commonly seen in childhood that leads to behavioural changes in social development and communication patterns, often continues into undiagnosed adulthood due to a global shortage of psychiatrists, resulting in delayed diagnoses with lasting consequences on individual’s well-being and the societal impact. Recently, machine learning methodologies have been incorporated into healthcare systems to facilitate the diagnosis and enhance the potential prediction of treatment outcomes for mental health conditions. In ADHD detection, the previous research focused on utilizing functional magnetic resonance imaging (fMRI) or Electroencephalography (EEG) signals, which require costly equipment and trained personnel for data collection. In recent years, speech and text modalities have garnered increasing attention due to their cost-effectiveness and non-wearable sensing in data collection. In this research, conducted in collaboration with the Cumbria, Northumberland, Tyne and Wear NHS Foundation Trust, we gathered audio data from both ADHD patients and normal controls based on the clinically popular Diagnostic Interview for ADHD in adults (DIVA). Subsequently, we transformed the speech data into text modalities through the utilization of the Google Cloud Speech API. We extracted both acoustic and text features from the data, encompassing traditional acoustic features (e.g., MFCC), specialized feature sets (e.g., eGeMAPS), as well as deep-learned linguistic and semantic features derived from pre-trained deep learning models. These features are employed in conjunction with a support vector machine for ADHD classification, yielding promising outcomes in the utilization of audio and text data for effective adult ADHD screening. Clinical impact: This research introduces a transformative approach in ADHD diagnosis, employing speech and text analysis to facilitate early and more accessible detection, particularly beneficial in areas with limited psychiatric resources. Clinical and Translational Impact Statement: The successful application of machine learning techniques in analyzing audio and text data for ADHD screening represents a significant advancement in mental health diagnostics, paving the way for its integration into clinical settings and potentially improving patient outcomes on a broader scale.
{"title":"Acoustic and Text Features Analysis for Adult ADHD Screening: A Data-Driven Approach Utilizing DIVA Interview","authors":"Shuanglin Li;Rajesh Nair;Syed Mohsen Naqvi","doi":"10.1109/JTEHM.2024.3369764","DOIUrl":"10.1109/JTEHM.2024.3369764","url":null,"abstract":"Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder commonly seen in childhood that leads to behavioural changes in social development and communication patterns, often continues into undiagnosed adulthood due to a global shortage of psychiatrists, resulting in delayed diagnoses with lasting consequences on individual’s well-being and the societal impact. Recently, machine learning methodologies have been incorporated into healthcare systems to facilitate the diagnosis and enhance the potential prediction of treatment outcomes for mental health conditions. In ADHD detection, the previous research focused on utilizing functional magnetic resonance imaging (fMRI) or Electroencephalography (EEG) signals, which require costly equipment and trained personnel for data collection. In recent years, speech and text modalities have garnered increasing attention due to their cost-effectiveness and non-wearable sensing in data collection. In this research, conducted in collaboration with the Cumbria, Northumberland, Tyne and Wear NHS Foundation Trust, we gathered audio data from both ADHD patients and normal controls based on the clinically popular Diagnostic Interview for ADHD in adults (DIVA). Subsequently, we transformed the speech data into text modalities through the utilization of the Google Cloud Speech API. We extracted both acoustic and text features from the data, encompassing traditional acoustic features (e.g., MFCC), specialized feature sets (e.g., eGeMAPS), as well as deep-learned linguistic and semantic features derived from pre-trained deep learning models. These features are employed in conjunction with a support vector machine for ADHD classification, yielding promising outcomes in the utilization of audio and text data for effective adult ADHD screening. Clinical impact: This research introduces a transformative approach in ADHD diagnosis, employing speech and text analysis to facilitate early and more accessible detection, particularly beneficial in areas with limited psychiatric resources. Clinical and Translational Impact Statement: The successful application of machine learning techniques in analyzing audio and text data for ADHD screening represents a significant advancement in mental health diagnostics, paving the way for its integration into clinical settings and potentially improving patient outcomes on a broader scale.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"359-370"},"PeriodicalIF":3.4,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10445184","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139980103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-20DOI: 10.1109/JTEHM.2024.3368291
James Skoric;Yannick D’Mello;David V. Plant
Wearable sensing has become a vital approach to cardiac health monitoring, and seismocardiography (SCG) is emerging as a promising technology in this field. However, the applicability of SCG is hindered by motion artifacts, including those encountered in practice of which the strongest source is walking. This holds back the translation of SCG to clinical settings. We therefore investigated techniques to enhance the quality of SCG signals in the presence of motion artifacts. To simulate ambulant recordings, we corrupted a clean SCG dataset with real-walking-vibrational noise. We decomposed the signal using several empirical-mode-decomposition methods and the maximum overlap discrete wavelet transform (MODWT). By combining MODWT, time-frequency masking, and nonnegative matrix factorization, we developed a novel algorithm which leveraged the vertical axis accelerometer to reduce walking vibrations in dorsoventral SCG. The accuracy and applicability of our method was verified using heart rate estimation. We used an interactive selection approach to improve estimation accuracy. The best decomposition method for reduction of motion artifact noise was the MODWT. Our algorithm improved heart rate estimation from 0.1 to 0.8 r-squared at −15 dB signal-to-noise ratio (SNR). Our method reduces motion artifacts in SCG signals up to a SNR of −19 dB without requiring any external assistance from electrocardiography (ECG). Such a standalone solution is directly applicable to the usage of SCG in daily life, as a content-rich replacement for other wearables in clinical settings, and other continuous monitoring scenarios. In applications with higher noise levels, ECG may be incorporated to further enhance SCG and extend its usable range. This work addresses the challenges posed by motion artifacts, enabling SCG to offer reliable cardiovascular insights in more difficult scenarios, and thereby facilitating wearable monitoring in daily life and the clinic.
{"title":"A Wavelet-Based Approach for Motion Artifact Reduction in Ambulatory Seismocardiography","authors":"James Skoric;Yannick D’Mello;David V. Plant","doi":"10.1109/JTEHM.2024.3368291","DOIUrl":"10.1109/JTEHM.2024.3368291","url":null,"abstract":"Wearable sensing has become a vital approach to cardiac health monitoring, and seismocardiography (SCG) is emerging as a promising technology in this field. However, the applicability of SCG is hindered by motion artifacts, including those encountered in practice of which the strongest source is walking. This holds back the translation of SCG to clinical settings. We therefore investigated techniques to enhance the quality of SCG signals in the presence of motion artifacts. To simulate ambulant recordings, we corrupted a clean SCG dataset with real-walking-vibrational noise. We decomposed the signal using several empirical-mode-decomposition methods and the maximum overlap discrete wavelet transform (MODWT). By combining MODWT, time-frequency masking, and nonnegative matrix factorization, we developed a novel algorithm which leveraged the vertical axis accelerometer to reduce walking vibrations in dorsoventral SCG. The accuracy and applicability of our method was verified using heart rate estimation. We used an interactive selection approach to improve estimation accuracy. The best decomposition method for reduction of motion artifact noise was the MODWT. Our algorithm improved heart rate estimation from 0.1 to 0.8 r-squared at −15 dB signal-to-noise ratio (SNR). Our method reduces motion artifacts in SCG signals up to a SNR of −19 dB without requiring any external assistance from electrocardiography (ECG). Such a standalone solution is directly applicable to the usage of SCG in daily life, as a content-rich replacement for other wearables in clinical settings, and other continuous monitoring scenarios. In applications with higher noise levels, ECG may be incorporated to further enhance SCG and extend its usable range. This work addresses the challenges posed by motion artifacts, enabling SCG to offer reliable cardiovascular insights in more difficult scenarios, and thereby facilitating wearable monitoring in daily life and the clinic.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"348-358"},"PeriodicalIF":3.4,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10440609","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139953785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-19DOI: 10.1109/JTEHM.2024.3366504
Satya P. Singh;Sukrit Gupta;Jagath C. Rajapakse
Brain state classification by applying deep learning techniques on neuroimaging data has become a recent topic of research. However, unlike domains where the data is low dimensional or there are large number of available training samples, neuroimaging data is high dimensional and has few training samples. To tackle these issues, we present a sparse feedforward deep neural architecture for encoding and decoding the structural connectome of the human brain. We use a sparsely connected element-wise multiplication as the first hidden layer and a fixed transform layer as the output layer. The number of trainable parameters and the training time is significantly reduced compared to feedforward networks. We demonstrate superior performance of this architecture in encoding the structural connectome implicated in Alzheimer’s disease (AD) and Parkinson’s disease (PD) from DTI brain scans. For decoding, we propose recursive feature elimination (RFE) algorithm based on DeepLIFT, layer-wise relevance propagation (LRP), and Integrated Gradients (IG) algorithms to remove irrelevant features and thereby identify key biomarkers associated with AD and PD. We show that the proposed architecture reduces 45.1% and 47.1% of the trainable parameters compared to a feedforward DNN with an increase in accuracy by 2.6 % and 3.1% for cognitively normal (CN) vs AD and CN vs PD classification, respectively. We also show that the proposed RFE method leads to a further increase in accuracy by 2.1% and 4% for CN vs AD and CN vs PD classification, while removing approximately 90% to 95% irrelevant features. Furthermore, we argue that the biomarkers (i.e., key brain regions and connections) identified are consistent with previous literature. We show that relevancy score-based methods can yield high discriminative power and are suitable for brain decoding. We also show that the proposed approach led to a reduction in the number of trainable network parameters, an increase in classification accuracy, and a detection of brain connections and regions that were consistent with earlier studies.
在神经影像数据上应用深度学习技术进行大脑状态分类已成为近期的研究课题。然而，与数据维度低或有大量可用训练样本的领域不同，神经影像数据维度高且训练样本少。为了解决这些问题，我们提出了一种用于编码和解码人脑结构连接组的稀疏前馈深度神经架构。我们使用稀疏连接的元素相乘作为第一隐层，使用固定变换层作为输出层。与前馈网络相比，可训练参数的数量和训练时间大大减少。我们从 DTI 脑扫描中提取了与阿尔茨海默病（AD）和帕金森病（PD）有关的结构连接组，证明了这种架构在编码方面的卓越性能。在解码方面，我们提出了基于 DeepLIFT、层相关性传播（LRP）和集成梯度（IG）算法的递归特征消除（RFE）算法，以去除不相关的特征，从而识别出与 AD 和 PD 相关的关键生物标记物。我们的研究表明，与前馈 DNN 相比，所提出的架构减少了 45.1% 和 47.1% 的可训练参数，在认知正常 (CN) vs AD 和 CN vs PD 分类中的准确率分别提高了 2.6% 和 3.1%。我们还表明，在去除约 90% 到 95% 的无关特征的同时，所提出的 RFE 方法还能将 CN vs AD 和 CN vs PD 分类的准确率进一步提高 2.1% 和 4%。此外，我们还认为所识别的生物标志物（即关键脑区和连接）与之前的文献一致。我们表明，基于相关性得分的方法可以产生很高的判别能力，适用于大脑解码。我们还表明，所提出的方法减少了可训练网络参数的数量，提高了分类准确性，并发现了与先前研究一致的大脑连接和区域。
{"title":"Sparse Deep Neural Network for Encoding and Decoding the Structural Connectome","authors":"Satya P. Singh;Sukrit Gupta;Jagath C. Rajapakse","doi":"10.1109/JTEHM.2024.3366504","DOIUrl":"10.1109/JTEHM.2024.3366504","url":null,"abstract":"Brain state classification by applying deep learning techniques on neuroimaging data has become a recent topic of research. However, unlike domains where the data is low dimensional or there are large number of available training samples, neuroimaging data is high dimensional and has few training samples. To tackle these issues, we present a sparse feedforward deep neural architecture for encoding and decoding the structural connectome of the human brain. We use a sparsely connected element-wise multiplication as the first hidden layer and a fixed transform layer as the output layer. The number of trainable parameters and the training time is significantly reduced compared to feedforward networks. We demonstrate superior performance of this architecture in encoding the structural connectome implicated in Alzheimer’s disease (AD) and Parkinson’s disease (PD) from DTI brain scans. For decoding, we propose recursive feature elimination (RFE) algorithm based on DeepLIFT, layer-wise relevance propagation (LRP), and Integrated Gradients (IG) algorithms to remove irrelevant features and thereby identify key biomarkers associated with AD and PD. We show that the proposed architecture reduces 45.1% and 47.1% of the trainable parameters compared to a feedforward DNN with an increase in accuracy by 2.6 % and 3.1% for cognitively normal (CN) vs AD and CN vs PD classification, respectively. We also show that the proposed RFE method leads to a further increase in accuracy by 2.1% and 4% for CN vs AD and CN vs PD classification, while removing approximately 90% to 95% irrelevant features. Furthermore, we argue that the biomarkers (i.e., key brain regions and connections) identified are consistent with previous literature. We show that relevancy score-based methods can yield high discriminative power and are suitable for brain decoding. We also show that the proposed approach led to a reduction in the number of trainable network parameters, an increase in classification accuracy, and a detection of brain connections and regions that were consistent with earlier studies.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"371-381"},"PeriodicalIF":3.4,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10440083","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139953798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：