Epilepsy is a common neurological disease and severely affects the daily life of patients.The automatic detection and diagnosis system of epilepsy based on electroencephalogram(EEG)is of great significance to help pat...Epilepsy is a common neurological disease and severely affects the daily life of patients.The automatic detection and diagnosis system of epilepsy based on electroencephalogram(EEG)is of great significance to help patients with epilepsy return to normal life.With the development of deep learning technology and the increase in the amount of EEG data,the performance of deep learning based automatic detection algorithm for epilepsy EEG has gradually surpassed the traditional hand-crafted approaches.However,the neural architecture design for epilepsy EEG analysis is time-consuming and laborious,and the designed structure is difficult to adapt to the changing EEG collection environment,which limits the application of the epilepsy EEG automatic detection system.In this paper,we explore the possibility of Automated Machine Learning(AutoML)playing a role in the task of epilepsy EEG detection.We apply the neural architecture search(NAS)algorithm in the AutoKeras platform to design the model for epilepsy EEG analysis and utilize feature interpretability methods to ensure the reliability of the searched model.The experimental results show that the model obtained through NAS outperforms the baseline model in performance.The searched model improves classification accuracy,F1-score and Cohen’s kappa coefficient by 7.68%,7.82%and 9.60%respectively than the baseline model.Furthermore,NASbased model is capable of extracting EEG features related to seizures for classification.展开更多
Objective Evidence on potential cardiovascular benefits of personal-level intervention among the elderly exposed to high levels of particulate matter(PM)remains limited.We aimed to assess improvements in surrogate mar...Objective Evidence on potential cardiovascular benefits of personal-level intervention among the elderly exposed to high levels of particulate matter(PM)remains limited.We aimed to assess improvements in surrogate markers of cardiovascular injury in vulnerable populations at risks by using indoor air filtration units.Methods We conducted a randomized crossover trial for 2 separate 2-week air filtration interventions in 20 households of patients with stable chronic obstructive pulmonary disease and their partners in the winter of 2013,with concurrent measurements of indoor PM.The changes in biomarkers indicative of cardiac injury,atherosclerosis progression and systemic inflammation following intervention were evaluated using linear mixed-effect models.Results In the analysis,average levels of indoor PM with aerodynamic diameters<2.5µm(PM2.5)decreased significantly by 59.2%(from 59.6 to 24.3µg/m3,P<0.001)during the active air filtration.The reduction was accompanied by improvements in levels of high-sensitivity cardiac troponin I by−84.6%(95%confidence interval[CI]:−90.7 to−78.6),growth differentiation factor-15 by−48.1%(95%CI:−31.2 to−25.6),osteoprotegerin by−65.4%(95%CI:−56.5 to−18.7),interleukin-4 by−46.6%(95%CI:−62.3 to−31.0)and myeloperoxidase by−60.3%(95%CI:−83.7 to−3.0),respectively.Conclusion Indoor air filtration intervention may provide potential cardiovascular benefits in vulnerable populations at risks.展开更多
基金This work is supported by Fundamental Research Funds for the Central Universities(Grant No.FRF-TP-19-006A3).
文摘Epilepsy is a common neurological disease and severely affects the daily life of patients.The automatic detection and diagnosis system of epilepsy based on electroencephalogram(EEG)is of great significance to help patients with epilepsy return to normal life.With the development of deep learning technology and the increase in the amount of EEG data,the performance of deep learning based automatic detection algorithm for epilepsy EEG has gradually surpassed the traditional hand-crafted approaches.However,the neural architecture design for epilepsy EEG analysis is time-consuming and laborious,and the designed structure is difficult to adapt to the changing EEG collection environment,which limits the application of the epilepsy EEG automatic detection system.In this paper,we explore the possibility of Automated Machine Learning(AutoML)playing a role in the task of epilepsy EEG detection.We apply the neural architecture search(NAS)algorithm in the AutoKeras platform to design the model for epilepsy EEG analysis and utilize feature interpretability methods to ensure the reliability of the searched model.The experimental results show that the model obtained through NAS outperforms the baseline model in performance.The searched model improves classification accuracy,F1-score and Cohen’s kappa coefficient by 7.68%,7.82%and 9.60%respectively than the baseline model.Furthermore,NASbased model is capable of extracting EEG features related to seizures for classification.
基金This work was supported by Beijing Natural Science Foundation(7222246)Royal Dutch Philips Electronics Ltd.(Grant NL18-2100478471).
文摘Objective Evidence on potential cardiovascular benefits of personal-level intervention among the elderly exposed to high levels of particulate matter(PM)remains limited.We aimed to assess improvements in surrogate markers of cardiovascular injury in vulnerable populations at risks by using indoor air filtration units.Methods We conducted a randomized crossover trial for 2 separate 2-week air filtration interventions in 20 households of patients with stable chronic obstructive pulmonary disease and their partners in the winter of 2013,with concurrent measurements of indoor PM.The changes in biomarkers indicative of cardiac injury,atherosclerosis progression and systemic inflammation following intervention were evaluated using linear mixed-effect models.Results In the analysis,average levels of indoor PM with aerodynamic diameters<2.5µm(PM2.5)decreased significantly by 59.2%(from 59.6 to 24.3µg/m3,P<0.001)during the active air filtration.The reduction was accompanied by improvements in levels of high-sensitivity cardiac troponin I by−84.6%(95%confidence interval[CI]:−90.7 to−78.6),growth differentiation factor-15 by−48.1%(95%CI:−31.2 to−25.6),osteoprotegerin by−65.4%(95%CI:−56.5 to−18.7),interleukin-4 by−46.6%(95%CI:−62.3 to−31.0)and myeloperoxidase by−60.3%(95%CI:−83.7 to−3.0),respectively.Conclusion Indoor air filtration intervention may provide potential cardiovascular benefits in vulnerable populations at risks.