BACKGROUND Obstructive sleep apnea-hypopnea syndrome(OSAHS)is primarily caused by airway obstruction due to narrowing and blockage in the nasal and nasopha-ryngeal,oropharyngeal,soft palate,and tongue base areas.The m...BACKGROUND Obstructive sleep apnea-hypopnea syndrome(OSAHS)is primarily caused by airway obstruction due to narrowing and blockage in the nasal and nasopha-ryngeal,oropharyngeal,soft palate,and tongue base areas.The mid-frequency anti-snoring device is a new technology based on sublingual nerve stimulation.Its principle is to improve the degree of oropharyngeal airway stenosis in OSAHS patients under mid-frequency wave stimulation.Nevertheless,there is a lack of clinical application and imaging evidence.METHODS We selected 50 patients diagnosed with moderate OSAHS in our hospital between July 2022 and August 2023.They underwent a 4-wk treatment regimen involving the mid-frequency anti-snoring device during nighttime sleep.Following the treatment,we monitored and assessed the sleep apnea quality of life index and Epworth Sleepiness Scale scores.Additionally,we performed computed tomo-graphy scans of the oropharynx in the awake state,during snoring,and while using the mid-frequency anti-snoring device.Cross-sectional area measurements in different states were taken at the narrowest airway point in the soft palate posterior and retrolingual areas.RESULTS Compared to pretreatment measurements,patients exhibited a significant reduction in the apnea-hypopnea index,the percentage of time with oxygen saturation below 90%,snoring frequency,and the duration of the most prolonged apnea event.The lowest oxygen saturation showed a notable increase,and both sleep apnea quality of life index and Epworth Sleepiness Scale scores improved.Oropharyngeal computed tomography scans revealed that in OSAHS patients cross-sectional areas of the oropharyngeal airway in the soft palate posterior area and retrolingual area decreased during snoring compared to the awake state.Conversely,during mid-frequency anti-snoring device treatment,these areas increased compared to snoring.CONCLUSION The mid-frequency anti-snoring device demonstrates the potential to enhance various sleep parameters in patients with moderate OSAHS,thereby improving their quality of life and reducing daytime sleepiness.These therapeutic effects are attributed to the device’s ability to ameliorate the narrowing of the oropharynx in OSAHS patients.展开更多
Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideb...Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideband radar system.We collected radiofrequency data from two radars positioned over and at the side of the bed for 16 patients performing four sleep postures(supine,left and right lateral,and prone).We proposed and evaluated deep learning approaches that streamlined feature extraction and classification,and the traditional machine learning approaches that involved different combinations of feature extractors and classifiers.Our results showed that the dual radar system performed better than either single radar.Predetermined statistical features with random forest classifier yielded the best accuracy(0.887),which could be further improved via an ablation study(0.938).Deep learning approach using transformer yielded accuracy of 0.713.展开更多
AIM:To validate the sleep-disordered breathing components of a portable electrocardiography and hemodynamic monitor to be used for sleep apnea screening.METHODS:Sleep-disordered breathing(SDB) is associated with cardi...AIM:To validate the sleep-disordered breathing components of a portable electrocardiography and hemodynamic monitor to be used for sleep apnea screening.METHODS:Sleep-disordered breathing(SDB) is associated with cardiovascular disease.Patients with existing cardiovascular disease may have unrecognized SDB or may develop SDB while under the care of a cardiologist.A screening device for SDB,easy to use and appealing to cardiologists,would assist in referral of appropriate patients for full polysomnography(PSG).A cardiac and respiratory monitor(CPAM) was attached to patients undergoing PSG and an apnea/hypopnea index(AHI) generated.The CPAM device produced respiration rate,snoring rate,individual apnea/hypopnea events and an SDB severity score(SDBSS).In addition to AHI,an expert over-reader annotated individual breaths,snores and SDB breathing events to which the automated algorithms were compared.RESULTS:The test set consisted of data from 85 patients(age:50.5 ± 12.4 years).Of these,57 had a positive PSG defined as AHI ≥ 5.0(mean:30.0 ± 29.8,negative group mean:1.5 ± 1.2).The sensitivity and specificity of the SDBSS compared to AHI was 57.9% and 89.3%,respectively.The correlation of snoring rate by CPAM compared to the expert overreader was r = 0.58(mean error:1.52 snores/min),while the automated respiration rate had a correlation of r = 0.90(mean error:0.70 breaths/min).CONCLUSION:This performance assessment shows that CPAM can be a useful portable monitor for screening and follow-up of subjects for SDB.展开更多
The prevalence and severity of obstructive sleep apnea(OSA) is higher in specific population: children, elderly,obese and patients with pulmonary and cardiovascular diseases, compared to the general population. OSA is...The prevalence and severity of obstructive sleep apnea(OSA) is higher in specific population: children, elderly,obese and patients with pulmonary and cardiovascular diseases, compared to the general population. OSA is associated with greater morbidity and mortality in these patients. Although full-night polysomnography is still the gold standard diagnostic sleep study for OSA, it is a time consuming, expensive and technically demanding exam. Over the last few years, there is growing evidence on the use of portable monitors(PM) as an alternative for the diagnosis of OSA. These devices were developed specially for sleep evaluation at home, at a familiar environment, with easy selfapplication of monitoring, unattended. The use of PM is stablished for populations with high pre-test probability of OSA. However, there is a lack of studies on the use of PM in age extremes and patients with comorbidities. The purpose of this review is to present the studies that evaluated the use of PM in specific population, as well as to describe the advantages, limitations and applications of these devices in this particular group of patients. Although the total loss rate of recordings is variable in different studies, the agreement with fullnight polysomnography justifies the use of PM in this population.展开更多
人体呼吸系统相关疾病常常伴随着呼吸深度和节律的异常,因此呼吸信号监测和呼吸模式识别在医疗健康领域中尤其是对于睡眠监测、疾病预断具有重要意义。其中,非接触式的脉冲式超宽带雷达(Impulse Radio Ultra-Wideband,IR-UWB)因具有良...人体呼吸系统相关疾病常常伴随着呼吸深度和节律的异常,因此呼吸信号监测和呼吸模式识别在医疗健康领域中尤其是对于睡眠监测、疾病预断具有重要意义。其中,非接触式的脉冲式超宽带雷达(Impulse Radio Ultra-Wideband,IR-UWB)因具有良好的距离分辨率和穿透能力以及全天候全天时、安全无创的检测优势,正逐步成为睡眠健康监护领域中最关键的感知技术之一。然而受睡眠监测特定的室内场景影响,复杂的测量环境给呼吸模式特征的准确提取带来了限制和挑战,传统的雷达呼吸模式识别算法主要关注一维呼吸时、频域特征,而IR-UWB雷达目标回波信息分散在多个距离门内,使用一维特征识别准确率较低。为此,本文针对IR-UWB雷达中人体呼吸在时间上慢速起伏运动、在距离上是扩展目标的信号模型特点,提出了一种引入时距信息的IR-UWB雷达多域特征融合呼吸模式识别方法。算法在提取一维呼吸信号波形时、频域特征的基础上更进一步挖掘雷达二维时距图像中潜在的呼吸模式形态特征,通过多域特征融合实现呼吸模式的非接触式检测和识别。在图像处理上,针对图像受呼吸异常节律影响呈现局部粘连特性导致呼吸周期提取难的问题,提出一种通过相位矩阵图像处理来检测雷达图像中的呼吸时距条带从而获取图像特征的方法。实验结果表明,利用该算法提取的多域特征对六种呼吸模式进行机器学习的分类识别,可以实现96.3%的识别准确率。展开更多
文摘BACKGROUND Obstructive sleep apnea-hypopnea syndrome(OSAHS)is primarily caused by airway obstruction due to narrowing and blockage in the nasal and nasopha-ryngeal,oropharyngeal,soft palate,and tongue base areas.The mid-frequency anti-snoring device is a new technology based on sublingual nerve stimulation.Its principle is to improve the degree of oropharyngeal airway stenosis in OSAHS patients under mid-frequency wave stimulation.Nevertheless,there is a lack of clinical application and imaging evidence.METHODS We selected 50 patients diagnosed with moderate OSAHS in our hospital between July 2022 and August 2023.They underwent a 4-wk treatment regimen involving the mid-frequency anti-snoring device during nighttime sleep.Following the treatment,we monitored and assessed the sleep apnea quality of life index and Epworth Sleepiness Scale scores.Additionally,we performed computed tomo-graphy scans of the oropharynx in the awake state,during snoring,and while using the mid-frequency anti-snoring device.Cross-sectional area measurements in different states were taken at the narrowest airway point in the soft palate posterior and retrolingual areas.RESULTS Compared to pretreatment measurements,patients exhibited a significant reduction in the apnea-hypopnea index,the percentage of time with oxygen saturation below 90%,snoring frequency,and the duration of the most prolonged apnea event.The lowest oxygen saturation showed a notable increase,and both sleep apnea quality of life index and Epworth Sleepiness Scale scores improved.Oropharyngeal computed tomography scans revealed that in OSAHS patients cross-sectional areas of the oropharyngeal airway in the soft palate posterior area and retrolingual area decreased during snoring compared to the awake state.Conversely,during mid-frequency anti-snoring device treatment,these areas increased compared to snoring.CONCLUSION The mid-frequency anti-snoring device demonstrates the potential to enhance various sleep parameters in patients with moderate OSAHS,thereby improving their quality of life and reducing daytime sleepiness.These therapeutic effects are attributed to the device’s ability to ameliorate the narrowing of the oropharynx in OSAHS patients.
基金supported by General Research Fund from the Research Grants Council of Hong Kong,China (Project No.PolyU15223822)Internal fund from the Research Institute for Smart Ageing (Project No.P0039001)Department of Biomedical Engineering (Project No.P0033913 and P0035896)from the Hong Kong Polytechnic University.
文摘Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideband radar system.We collected radiofrequency data from two radars positioned over and at the side of the bed for 16 patients performing four sleep postures(supine,left and right lateral,and prone).We proposed and evaluated deep learning approaches that streamlined feature extraction and classification,and the traditional machine learning approaches that involved different combinations of feature extractors and classifiers.Our results showed that the dual radar system performed better than either single radar.Predetermined statistical features with random forest classifier yielded the best accuracy(0.887),which could be further improved via an ablation study(0.938).Deep learning approach using transformer yielded accuracy of 0.713.
基金Supported by An equipment grant from Inovise Medical,Inc.,Beaverton OR,United States,for clinical data collection
文摘AIM:To validate the sleep-disordered breathing components of a portable electrocardiography and hemodynamic monitor to be used for sleep apnea screening.METHODS:Sleep-disordered breathing(SDB) is associated with cardiovascular disease.Patients with existing cardiovascular disease may have unrecognized SDB or may develop SDB while under the care of a cardiologist.A screening device for SDB,easy to use and appealing to cardiologists,would assist in referral of appropriate patients for full polysomnography(PSG).A cardiac and respiratory monitor(CPAM) was attached to patients undergoing PSG and an apnea/hypopnea index(AHI) generated.The CPAM device produced respiration rate,snoring rate,individual apnea/hypopnea events and an SDB severity score(SDBSS).In addition to AHI,an expert over-reader annotated individual breaths,snores and SDB breathing events to which the automated algorithms were compared.RESULTS:The test set consisted of data from 85 patients(age:50.5 ± 12.4 years).Of these,57 had a positive PSG defined as AHI ≥ 5.0(mean:30.0 ± 29.8,negative group mean:1.5 ± 1.2).The sensitivity and specificity of the SDBSS compared to AHI was 57.9% and 89.3%,respectively.The correlation of snoring rate by CPAM compared to the expert overreader was r = 0.58(mean error:1.52 snores/min),while the automated respiration rate had a correlation of r = 0.90(mean error:0.70 breaths/min).CONCLUSION:This performance assessment shows that CPAM can be a useful portable monitor for screening and follow-up of subjects for SDB.
文摘The prevalence and severity of obstructive sleep apnea(OSA) is higher in specific population: children, elderly,obese and patients with pulmonary and cardiovascular diseases, compared to the general population. OSA is associated with greater morbidity and mortality in these patients. Although full-night polysomnography is still the gold standard diagnostic sleep study for OSA, it is a time consuming, expensive and technically demanding exam. Over the last few years, there is growing evidence on the use of portable monitors(PM) as an alternative for the diagnosis of OSA. These devices were developed specially for sleep evaluation at home, at a familiar environment, with easy selfapplication of monitoring, unattended. The use of PM is stablished for populations with high pre-test probability of OSA. However, there is a lack of studies on the use of PM in age extremes and patients with comorbidities. The purpose of this review is to present the studies that evaluated the use of PM in specific population, as well as to describe the advantages, limitations and applications of these devices in this particular group of patients. Although the total loss rate of recordings is variable in different studies, the agreement with fullnight polysomnography justifies the use of PM in this population.
文摘人体呼吸系统相关疾病常常伴随着呼吸深度和节律的异常,因此呼吸信号监测和呼吸模式识别在医疗健康领域中尤其是对于睡眠监测、疾病预断具有重要意义。其中,非接触式的脉冲式超宽带雷达(Impulse Radio Ultra-Wideband,IR-UWB)因具有良好的距离分辨率和穿透能力以及全天候全天时、安全无创的检测优势,正逐步成为睡眠健康监护领域中最关键的感知技术之一。然而受睡眠监测特定的室内场景影响,复杂的测量环境给呼吸模式特征的准确提取带来了限制和挑战,传统的雷达呼吸模式识别算法主要关注一维呼吸时、频域特征,而IR-UWB雷达目标回波信息分散在多个距离门内,使用一维特征识别准确率较低。为此,本文针对IR-UWB雷达中人体呼吸在时间上慢速起伏运动、在距离上是扩展目标的信号模型特点,提出了一种引入时距信息的IR-UWB雷达多域特征融合呼吸模式识别方法。算法在提取一维呼吸信号波形时、频域特征的基础上更进一步挖掘雷达二维时距图像中潜在的呼吸模式形态特征,通过多域特征融合实现呼吸模式的非接触式检测和识别。在图像处理上,针对图像受呼吸异常节律影响呈现局部粘连特性导致呼吸周期提取难的问题,提出一种通过相位矩阵图像处理来检测雷达图像中的呼吸时距条带从而获取图像特征的方法。实验结果表明,利用该算法提取的多域特征对六种呼吸模式进行机器学习的分类识别,可以实现96.3%的识别准确率。
