There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for...There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.展开更多
Background：Sleep disturbance is one of the major non-motor symptoms which cause the disability of Parkinson’s disease （PD） patients. Cystatin C （CysC） is a more sensitive biomarker than serum creatinine or estim...Background：Sleep disturbance is one of the major non-motor symptoms which cause the disability of Parkinson’s disease （PD） patients. Cystatin C （CysC） is a more sensitive biomarker than serum creatinine or estimated glomerular filtration rate. Previous studies have reported altered CysC levels in neurodegenerative disorders and sleep disorders. This study aimed to explore the correlations of serum CysC levels and objective sleep disturbances in early PD.Methods：We recruited 106 early PD patients and 146 age- and sex-matched controls. All participants underwent clinical investigation and video-polysomnography. Sleep parameters and serum levels of CysC were measured. Then, we investigated the relationships between CysC and clinical variables and objective sleep disturbances in early PD patients.Results：The mean serum level of CysC was significantly higher in patients with early PD （1.03 ± 0.19 mg/L） compared to controls （0.96 ± 0.15 mg/L, P = 0.009）. There were significantly positive correlations between serum CysC levels and age （r = 0.334, P 〈 0.001）, gender （r = 0.264, P = 0.013）, and creatinine levels （r = 0.302, P = 0.018） in early PD patients. Increased serum CysC levels in early PD patients were significantly associated with higher apnea and hypopnea index （AHI） （r = 0.231, P = 0.017）, especially hypopnea index （r = 0.333, P 〈 0.001）. In early PD patients, elevated serum CysC levels were positively correlated with oxygen desaturation index （r = 0.223, P = 0.021）, percentage of time spent at oxygen saturation （SaO2） 〈90% （r = 0.644, P 〈 0.001）, arousal with respiratory event during sleep （r = 0.247, P = 0.013）. On the contrary, the elevated serum CysC levels were negatively correlated with mean and minimal SaO2 （r = ？0.323, ？0.315, both P = 0.001） in PD patients.Conclusions：The level of serum CysC was higher in early PD patients. PD patients with elevated serum CysC levels had more respiratory events and more severe oxygen desaturation. Therefore, the serum CysC levels may predict the severities of sleep-disordered breathing problems in early PD patients.展开更多
Parkinson＇s disease （PD） is a typical degenerative disease, which is characterized by the most obvious symptoms of movement dysfunction, including shaking, rigidity, slowness of movement and difficulty in walking a...Parkinson＇s disease （PD） is a typical degenerative disease, which is characterized by the most obvious symptoms of movement dysfunction, including shaking, rigidity, slowness of movement and difficulty in walking and gait. This disease can not be clearly identified through laboratory tests at present, thus application of high-throughput technique in studying the expression profiles of PD helps to find the genetic markers for its early diagnosis. Studies on expression profiles of neurodegenerative diseases have revealed the novel genes and pathways involved in the progress of illness. In this study, the expression profiles of PD in blood were compared, showing that 181 differentially expressed genes （DEG） exhibit a similar expression trend both in patients and in normal controls.展开更多
文摘There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.
文摘Background：Sleep disturbance is one of the major non-motor symptoms which cause the disability of Parkinson’s disease （PD） patients. Cystatin C （CysC） is a more sensitive biomarker than serum creatinine or estimated glomerular filtration rate. Previous studies have reported altered CysC levels in neurodegenerative disorders and sleep disorders. This study aimed to explore the correlations of serum CysC levels and objective sleep disturbances in early PD.Methods：We recruited 106 early PD patients and 146 age- and sex-matched controls. All participants underwent clinical investigation and video-polysomnography. Sleep parameters and serum levels of CysC were measured. Then, we investigated the relationships between CysC and clinical variables and objective sleep disturbances in early PD patients.Results：The mean serum level of CysC was significantly higher in patients with early PD （1.03 ± 0.19 mg/L） compared to controls （0.96 ± 0.15 mg/L, P = 0.009）. There were significantly positive correlations between serum CysC levels and age （r = 0.334, P 〈 0.001）, gender （r = 0.264, P = 0.013）, and creatinine levels （r = 0.302, P = 0.018） in early PD patients. Increased serum CysC levels in early PD patients were significantly associated with higher apnea and hypopnea index （AHI） （r = 0.231, P = 0.017）, especially hypopnea index （r = 0.333, P 〈 0.001）. In early PD patients, elevated serum CysC levels were positively correlated with oxygen desaturation index （r = 0.223, P = 0.021）, percentage of time spent at oxygen saturation （SaO2） 〈90% （r = 0.644, P 〈 0.001）, arousal with respiratory event during sleep （r = 0.247, P = 0.013）. On the contrary, the elevated serum CysC levels were negatively correlated with mean and minimal SaO2 （r = ？0.323, ？0.315, both P = 0.001） in PD patients.Conclusions：The level of serum CysC was higher in early PD patients. PD patients with elevated serum CysC levels had more respiratory events and more severe oxygen desaturation. Therefore, the serum CysC levels may predict the severities of sleep-disordered breathing problems in early PD patients.
基金supported by the National Natural Science Foundation of China(81101302,31270185)SKLID Development Grant(2014,SKLID201)
文摘Parkinson＇s disease （PD） is a typical degenerative disease, which is characterized by the most obvious symptoms of movement dysfunction, including shaking, rigidity, slowness of movement and difficulty in walking and gait. This disease can not be clearly identified through laboratory tests at present, thus application of high-throughput technique in studying the expression profiles of PD helps to find the genetic markers for its early diagnosis. Studies on expression profiles of neurodegenerative diseases have revealed the novel genes and pathways involved in the progress of illness. In this study, the expression profiles of PD in blood were compared, showing that 181 differentially expressed genes （DEG） exhibit a similar expression trend both in patients and in normal controls.
