Brain-computer interface (BCI) systems are new human-computer interaction technology, and the electroencephalography (EEG) signals can be translated as the control commands. For more operational dimensions, a hybrid experimental paradigm with motor imagery and speech imagery has been proposed in our previous study. To improve the practicality of BCIs, a personalized channel selection and spatial filtering model is proposed in this paper. Correlated channels are chosen by Pearson's correlation coefficient, and spatial filters are obtained by common spatial pattern (CSP) from these channels. The features of EEG signals are extracted and classified by the spatial filters and support vector machine (SVM), respectively. The average classification accuracy of ten subjects is 73.9%, and it is 2.1% higher than the accuracy without channel selection. Suitable channels can reduce the complexity of BCIs, and the classification results of EEG are also improved.
{"title":"A Personalized Channel Selection and Spatial filtering Model for Brain-Computer Interface","authors":"Li Wang, L. Hu, Jing Wang, Danni Liang","doi":"10.1145/3498731.3498746","DOIUrl":"https://doi.org/10.1145/3498731.3498746","url":null,"abstract":"Brain-computer interface (BCI) systems are new human-computer interaction technology, and the electroencephalography (EEG) signals can be translated as the control commands. For more operational dimensions, a hybrid experimental paradigm with motor imagery and speech imagery has been proposed in our previous study. To improve the practicality of BCIs, a personalized channel selection and spatial filtering model is proposed in this paper. Correlated channels are chosen by Pearson's correlation coefficient, and spatial filters are obtained by common spatial pattern (CSP) from these channels. The features of EEG signals are extracted and classified by the spatial filters and support vector machine (SVM), respectively. The average classification accuracy of ten subjects is 73.9%, and it is 2.1% higher than the accuracy without channel selection. Suitable channels can reduce the complexity of BCIs, and the classification results of EEG are also improved.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128619974","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}
Stem cell therapy for the treatment of cardiovascular disease is increasingly being researched during the past few decades. Due to the risk of cardiac transplantation surgery and the nature of cardiac cell lines, the regenerative potential of stem cell therapy is being extremely expected. Popular cell lines are discussed in this study, which includes mesenchymal stem cells, bone marrow-derived mononuclear stem cells, embryonic stem cells, hematopoietic stem cells, endothelial progenitor cells, tissue-specific stem cells, umbilical cord blood stem cells, skeletal myoblast and induced pluripotent stem cells. The purpose of this study is to review the current use of various cell types for stem cell therapy in cardiovascular patients, as mentioned above. Additionally, optimal delivery methods of stem cell therapies are also discussed in patients with and without secondary stroke conditions. Literature from the Internet was searched and primary studies with the cell types of interest were carefully examined and included in the study. Although from current literature in the field stem cell therapies have great potential to be used in cardiovascular patients, more extensive research with a greater number is warranted before widespread application in the clinical setting.
{"title":"Stem Cell Therapies for Cardiac Disease: Which Cell Types Are the Best","authors":"Ji Wen","doi":"10.1145/3498731.3498762","DOIUrl":"https://doi.org/10.1145/3498731.3498762","url":null,"abstract":"Stem cell therapy for the treatment of cardiovascular disease is increasingly being researched during the past few decades. Due to the risk of cardiac transplantation surgery and the nature of cardiac cell lines, the regenerative potential of stem cell therapy is being extremely expected. Popular cell lines are discussed in this study, which includes mesenchymal stem cells, bone marrow-derived mononuclear stem cells, embryonic stem cells, hematopoietic stem cells, endothelial progenitor cells, tissue-specific stem cells, umbilical cord blood stem cells, skeletal myoblast and induced pluripotent stem cells. The purpose of this study is to review the current use of various cell types for stem cell therapy in cardiovascular patients, as mentioned above. Additionally, optimal delivery methods of stem cell therapies are also discussed in patients with and without secondary stroke conditions. Literature from the Internet was searched and primary studies with the cell types of interest were carefully examined and included in the study. Although from current literature in the field stem cell therapies have great potential to be used in cardiovascular patients, more extensive research with a greater number is warranted before widespread application in the clinical setting.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128824047","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}
Since the first case of Coronavirus Disease 2019 (COVID-19) was discovered in Wuhan, Hubei, China, on December 31, 2019, the disease has spread globally at an unimaginable speed. COVID-19 has taken a huge toll on the society and the economy, and everyone is looking forward to its end. In this work, we established a mathematical model of COVID-19 epidemic development. First, we obtained a differential equation to describe the spreading of COVID-19: , in which is the total number of patients who are infected by COVID-19 at time . There are three parameters in this equation: the spreading coefficient , which is the average number of people infected by an unquarantined patient in a unit time; the average quarantine ratio , which is the number of quarantined patients divided by the total number of patients; and the incubation period , which is the time lapse between infection and exhibition of symptoms. In addition, we have written a Python program according to our equation, and have further used our program to analyze the COVID-19 epidemic development in various places around the world, including China, Western Europe, Latin America and Caribbean, Southern Asia, and the entire world. Through numerical fitting, we have obtained the values of the spreading coefficient and the isolation ratio for these places around the world, and predicted the development of the epidemic using these parameters we obtained. In order to ensure data consistency, we have used the data from COVID-19 case reports from Johns Hopkins University. We found that using the parameters we obtained, our calculated curves of fit the actually reported values very well, and we were able to accurately predict the values of in the near future. Lastly, we calculated the value (the number of infected persons per patient at the beginning of the epidemic) to be 2.94∼5.88, which is consistent with the current estimated value of . In summary, our results serve as a reliable guideline to understand the spreading of COVID-19 and to predict the future outcome of this epidemic, and can be provided as a reference for the government to formulate policies.
{"title":"Using Mathematical Model to Analyze COVID-19 Spreading","authors":"Shi-Guang Zhao, T. Peng, Yuan Liu, Geng Wu","doi":"10.1145/3498731.3498751","DOIUrl":"https://doi.org/10.1145/3498731.3498751","url":null,"abstract":"Since the first case of Coronavirus Disease 2019 (COVID-19) was discovered in Wuhan, Hubei, China, on December 31, 2019, the disease has spread globally at an unimaginable speed. COVID-19 has taken a huge toll on the society and the economy, and everyone is looking forward to its end. In this work, we established a mathematical model of COVID-19 epidemic development. First, we obtained a differential equation to describe the spreading of COVID-19: , in which is the total number of patients who are infected by COVID-19 at time . There are three parameters in this equation: the spreading coefficient , which is the average number of people infected by an unquarantined patient in a unit time; the average quarantine ratio , which is the number of quarantined patients divided by the total number of patients; and the incubation period , which is the time lapse between infection and exhibition of symptoms. In addition, we have written a Python program according to our equation, and have further used our program to analyze the COVID-19 epidemic development in various places around the world, including China, Western Europe, Latin America and Caribbean, Southern Asia, and the entire world. Through numerical fitting, we have obtained the values of the spreading coefficient and the isolation ratio for these places around the world, and predicted the development of the epidemic using these parameters we obtained. In order to ensure data consistency, we have used the data from COVID-19 case reports from Johns Hopkins University. We found that using the parameters we obtained, our calculated curves of fit the actually reported values very well, and we were able to accurately predict the values of in the near future. Lastly, we calculated the value (the number of infected persons per patient at the beginning of the epidemic) to be 2.94∼5.88, which is consistent with the current estimated value of . In summary, our results serve as a reliable guideline to understand the spreading of COVID-19 and to predict the future outcome of this epidemic, and can be provided as a reference for the government to formulate policies.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124617442","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}
Cytochrome P450 2C19 (CYP2C19) and 2D6 (CYP2D6) are vital drug metabolic enzymes involved in the metabolism of many important prescription drugs. Importantly, CYP2C19 and CYP2D6 genes are highly polymorphic and harbor a plethora of genetic variants that change enzyme activity and consequently result in individual differences in drug metabolism, response and toxicity. While CYP2C19 and CYP2D6 alleles are highly population-specific, we overviewed distribution of 6 clinically important CYP2C19 (CYP2C19*2, *3 and *17) and CYP2D6 (CYP2D6*5, *10 and duplications) alleles within East Asian populations (including Chinese, South Korean and Japanese) as well as Chinese subethnic populations based on 30 original studies and 25,948 healthy individuals. We found that the frequency of CYP2C19*3 shows an obvious West-to-East gradient, ranging from 4.3% in Han Chinese to 12% in Japanese. Within the Chinese subethnic populations, we observed that the frequencies of CYP2C19*2 were graded similarly from West to East China and Hui population harbors strikingly high CYP2C19*2 frequency (42.7%) among all studied populations. In addition, there is a very clear South-to-North gradient of CYP2C19*3 frequencies across China, ranging from 1.5% in Li to 8% in Kazakh. Patterns of CYP2D6 allele distributions are difficult to conclude due to the lack of reported frequency data. In summary, we described frequencies of important CYP2C19 and CYP2D6 alleles in East Asian populations and Chinese ethnic populations, which can serve as important information for the guidance of East Asian population-specific genotyping strategies as well as dose adjustment in drug prescriptions.
{"title":"Frequencies of Clinically Important CYP2C19 and CYP2D6 Alleles across East Asian populations","authors":"Gufeng Zhang","doi":"10.1145/3498731.3498740","DOIUrl":"https://doi.org/10.1145/3498731.3498740","url":null,"abstract":"Cytochrome P450 2C19 (CYP2C19) and 2D6 (CYP2D6) are vital drug metabolic enzymes involved in the metabolism of many important prescription drugs. Importantly, CYP2C19 and CYP2D6 genes are highly polymorphic and harbor a plethora of genetic variants that change enzyme activity and consequently result in individual differences in drug metabolism, response and toxicity. While CYP2C19 and CYP2D6 alleles are highly population-specific, we overviewed distribution of 6 clinically important CYP2C19 (CYP2C19*2, *3 and *17) and CYP2D6 (CYP2D6*5, *10 and duplications) alleles within East Asian populations (including Chinese, South Korean and Japanese) as well as Chinese subethnic populations based on 30 original studies and 25,948 healthy individuals. We found that the frequency of CYP2C19*3 shows an obvious West-to-East gradient, ranging from 4.3% in Han Chinese to 12% in Japanese. Within the Chinese subethnic populations, we observed that the frequencies of CYP2C19*2 were graded similarly from West to East China and Hui population harbors strikingly high CYP2C19*2 frequency (42.7%) among all studied populations. In addition, there is a very clear South-to-North gradient of CYP2C19*3 frequencies across China, ranging from 1.5% in Li to 8% in Kazakh. Patterns of CYP2D6 allele distributions are difficult to conclude due to the lack of reported frequency data. In summary, we described frequencies of important CYP2C19 and CYP2D6 alleles in East Asian populations and Chinese ethnic populations, which can serve as important information for the guidance of East Asian population-specific genotyping strategies as well as dose adjustment in drug prescriptions.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"91 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133523230","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}
G. Improta, Ylenia Colella, Giovanni Rossi, A. Borrelli, Giuseppe Russo, M. Triassi
Overcrowding is a serious issue that Emergency Departments (EDs) must deal with, since it is leading to longer delays and greater patients’ dissatisfaction, which are directly connected with an increasing number of patients who leave the ED prematurely. Hospital is affected by this aspect in terms of lost revenues from opportunities missed in providing care and adverse outcomes deriving from ED process. For this reason, the ability to control and predict in advance patients who leave ED without any evaluation becomes strategic for healthcare administrators. The purpose of this work is to investigate causes that determine patients who leave the ED without being seen. Machine Learning algorithms are used in order to build and compare different models for LWBS prediction, with the aim of obtaining a helpful support tool for the ED management in healthcare facilities.
{"title":"Use of machine learning to predict abandonment rates in an emergency department","authors":"G. Improta, Ylenia Colella, Giovanni Rossi, A. Borrelli, Giuseppe Russo, M. Triassi","doi":"10.1145/3498731.3498755","DOIUrl":"https://doi.org/10.1145/3498731.3498755","url":null,"abstract":"Overcrowding is a serious issue that Emergency Departments (EDs) must deal with, since it is leading to longer delays and greater patients’ dissatisfaction, which are directly connected with an increasing number of patients who leave the ED prematurely. Hospital is affected by this aspect in terms of lost revenues from opportunities missed in providing care and adverse outcomes deriving from ED process. For this reason, the ability to control and predict in advance patients who leave ED without any evaluation becomes strategic for healthcare administrators. The purpose of this work is to investigate causes that determine patients who leave the ED without being seen. Machine Learning algorithms are used in order to build and compare different models for LWBS prediction, with the aim of obtaining a helpful support tool for the ED management in healthcare facilities.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115630899","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}
Wanying Dou, Yihang Liu, Zehai Liu, D. Yerezhepov, U. Kozhamkulov, A. Akilzhanova, Omar Dib, Chee-Kai Chan
Tuberculosis (TB) is a worldwide health challenge. Mycobacterium tuberculosis(M.tb) is capable of evading the host immune system which can lead to tuberculosis infection. Household contacts (HHCs) of TB cases have a higher risk of infection. Novel predictive techniques to identify high-risk TB susceptible groups are needed. Susceptibility to Tuberculosis is associated with host genetic variations. This research work uses the TPOT autoML tool to map genetic variations and TB infection status mathematically. Machine learning was employed to predict the risk of progression to active tuberculosis based on associated host genetic variation. Among the three adopted configurations, "TPOT Default", "TPOT spars", "TPOT N that were used,” “TPOT Default," and "TPOT sparse" produced the same best performance both reaching 0.816 Training CV score and 0.625 Testing Accuracy. Different genes variants identified using this approach were found to have distinctive contributions for TB infection, which represent the feature importance of the classifier. The feature importance of the random forest classifier pipeline in "TPOT sparse" was adopted. The top ten contributing genes were also submitted to Enrichr for gene pathway enrichment analysis. The identified enriched pathways have been shown to be key to TB infection.
{"title":"An AutoML Approach for Predicting Risk of Progression to Active Tuberculosis based on Its Association with Host Genetic Variations","authors":"Wanying Dou, Yihang Liu, Zehai Liu, D. Yerezhepov, U. Kozhamkulov, A. Akilzhanova, Omar Dib, Chee-Kai Chan","doi":"10.1145/3498731.3498743","DOIUrl":"https://doi.org/10.1145/3498731.3498743","url":null,"abstract":"Tuberculosis (TB) is a worldwide health challenge. Mycobacterium tuberculosis(M.tb) is capable of evading the host immune system which can lead to tuberculosis infection. Household contacts (HHCs) of TB cases have a higher risk of infection. Novel predictive techniques to identify high-risk TB susceptible groups are needed. Susceptibility to Tuberculosis is associated with host genetic variations. This research work uses the TPOT autoML tool to map genetic variations and TB infection status mathematically. Machine learning was employed to predict the risk of progression to active tuberculosis based on associated host genetic variation. Among the three adopted configurations, \"TPOT Default\", \"TPOT spars\", \"TPOT N that were used,” “TPOT Default,\" and \"TPOT sparse\" produced the same best performance both reaching 0.816 Training CV score and 0.625 Testing Accuracy. Different genes variants identified using this approach were found to have distinctive contributions for TB infection, which represent the feature importance of the classifier. The feature importance of the random forest classifier pipeline in \"TPOT sparse\" was adopted. The top ten contributing genes were also submitted to Enrichr for gene pathway enrichment analysis. The identified enriched pathways have been shown to be key to TB infection.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131444711","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}
Nucleus segmentation of fluorescence microscopy is a critical step in quantifying measurements in cell biology. Automatic and accurate nucleus segmentation has powerful applications in analyzing intrinsic characterization in nucleus morphology. However, existing methods have limited capacity to perform accurate segmentation in challenging samples, such as noisy images and clumped nuclei. In this paper, inspired by the idea of cascaded U-Net (or W-Net) and its remarkable performance improvement in medical image segmentation, we proposed a novel framework called Attention-enhanced Simplified W-Net (ASW-Net), in which a cascade-like structure with between-net connections was used. Results showed that this lightweight model could reach remarkable segmentation performance in the testing set (aggregated Jaccard index, 0.7981). In addition, our proposed framework performed better than the state-of-the-art methods in terms of segmentation performance. Moreover, we further explored the effectiveness of our designed network by visualizing the deep features from the network. Notably, our proposed framework is open-source.
{"title":"ASW-Net: A Deep Learning-based Tool for Cell Nucleus Segmentation of Fluorescence Microscopy","authors":"Weihao Pan, Zhe Liu, G. Lin","doi":"10.1145/3498731.3498734","DOIUrl":"https://doi.org/10.1145/3498731.3498734","url":null,"abstract":"Nucleus segmentation of fluorescence microscopy is a critical step in quantifying measurements in cell biology. Automatic and accurate nucleus segmentation has powerful applications in analyzing intrinsic characterization in nucleus morphology. However, existing methods have limited capacity to perform accurate segmentation in challenging samples, such as noisy images and clumped nuclei. In this paper, inspired by the idea of cascaded U-Net (or W-Net) and its remarkable performance improvement in medical image segmentation, we proposed a novel framework called Attention-enhanced Simplified W-Net (ASW-Net), in which a cascade-like structure with between-net connections was used. Results showed that this lightweight model could reach remarkable segmentation performance in the testing set (aggregated Jaccard index, 0.7981). In addition, our proposed framework performed better than the state-of-the-art methods in terms of segmentation performance. Moreover, we further explored the effectiveness of our designed network by visualizing the deep features from the network. Notably, our proposed framework is open-source.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121838960","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}
In this paper, the Support Vector Machine (SVM) was introduced into the pattern recognition of human lower limb movements, and a classification method based on multi-core Support Vector Machine was constructed. Through motion pattern recognition, a model representing the relationship between motion and surface EMG signals was established, which provided technical Support for the rehabilitation and diagnosis of patients with lower limb hemiplegia.
{"title":"Research on Key Techniques of Lower Limb Rehabilitation Training Based on Human Surface EMG Signal","authors":"Liye Ren, Chen Wang, Ping Feng","doi":"10.1145/3498731.3498745","DOIUrl":"https://doi.org/10.1145/3498731.3498745","url":null,"abstract":"In this paper, the Support Vector Machine (SVM) was introduced into the pattern recognition of human lower limb movements, and a classification method based on multi-core Support Vector Machine was constructed. Through motion pattern recognition, a model representing the relationship between motion and surface EMG signals was established, which provided technical Support for the rehabilitation and diagnosis of patients with lower limb hemiplegia.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124748769","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}
E. Montella, Teresa Angela Trunfio, Umberto Armonia, Clotilde De Marco, Martina Profeta, M. Triassi, P. Gargiulo
The prevention of healthcare–associated infections (HAIs) is one of the most important parameters to evaluate healthcare service quality. In this work, we report on the application of the Firth's penalized maximum likelihood logistic regression to find some patients characteristics that can be related to HAIs and used as predictor factors. Data of 344 patients who have been hospitalized in the Adult Intensive Care of the “Federico II” University Hospital of Naples who underwent a wide range of surgical procedures between January 2018 and December 2019 were acquired using the departmental information system. This procedure allowed the identification of variables that influenced the risk of HAIs. Data distributions were evaluated to demonstrate their non-normality and then statistical analyses were performed such as Firth's penalized maximum likelihood logistic regression. Results show a correlation among the vascular catheterization days and the possibility to contract HAIs. This information, together with other tools for reducing the risk of infection such as surveillance, epidemiological guidelines, and training of healthcare personnel, could be of great help to re-design the healthcare processes and improve the quality of the health care system.
{"title":"A study of healthcare associated infections in the Intensive Care Unit of “Federico II” University Hospital through Logistic Regression","authors":"E. Montella, Teresa Angela Trunfio, Umberto Armonia, Clotilde De Marco, Martina Profeta, M. Triassi, P. Gargiulo","doi":"10.1145/3498731.3498750","DOIUrl":"https://doi.org/10.1145/3498731.3498750","url":null,"abstract":"The prevention of healthcare–associated infections (HAIs) is one of the most important parameters to evaluate healthcare service quality. In this work, we report on the application of the Firth's penalized maximum likelihood logistic regression to find some patients characteristics that can be related to HAIs and used as predictor factors. Data of 344 patients who have been hospitalized in the Adult Intensive Care of the “Federico II” University Hospital of Naples who underwent a wide range of surgical procedures between January 2018 and December 2019 were acquired using the departmental information system. This procedure allowed the identification of variables that influenced the risk of HAIs. Data distributions were evaluated to demonstrate their non-normality and then statistical analyses were performed such as Firth's penalized maximum likelihood logistic regression. Results show a correlation among the vascular catheterization days and the possibility to contract HAIs. This information, together with other tools for reducing the risk of infection such as surveillance, epidemiological guidelines, and training of healthcare personnel, could be of great help to re-design the healthcare processes and improve the quality of the health care system.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115956254","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}
Obstructive sleep apnea (OSA) is a common upper respiratory tract disease, which is related to autonomic nervous system (ANS) dysfunction and associated with reduced heart rate variability (HRV). Fuzzy approximate entropy of extrema based on multiple moving averages (Emma-fApEn) can effectively analyze the physiological sympathetic tone in a short period of time during sleep. In this study, we compared fApEn-minima and fApEn-maxima obtained with Emma-fApEn with classic time-frequency domain indices using electrocardiogram(ECG) recordings from the PhysioNet database. The empirical results showed that Mean and LH could significantly differentiate OSA recordings from healthy recordings. Compared with support vector machine (SVM) and k-nearest neighbor classification (KNN), random forest (RF) provided the highest accuracy in OSA detection. Therefore, Emma-fApEn could analyze the decrease in the complexity of sympathetic tone in OSA patients during sleep.
{"title":"Obstructive Sleep Apnea Detection using Fuzzy Approximate Entropy of Extrema based on Multiple Moving Averages","authors":"Keming Wei, Guanzheng Liu","doi":"10.1145/3498731.3498747","DOIUrl":"https://doi.org/10.1145/3498731.3498747","url":null,"abstract":"Obstructive sleep apnea (OSA) is a common upper respiratory tract disease, which is related to autonomic nervous system (ANS) dysfunction and associated with reduced heart rate variability (HRV). Fuzzy approximate entropy of extrema based on multiple moving averages (Emma-fApEn) can effectively analyze the physiological sympathetic tone in a short period of time during sleep. In this study, we compared fApEn-minima and fApEn-maxima obtained with Emma-fApEn with classic time-frequency domain indices using electrocardiogram(ECG) recordings from the PhysioNet database. The empirical results showed that Mean and LH could significantly differentiate OSA recordings from healthy recordings. Compared with support vector machine (SVM) and k-nearest neighbor classification (KNN), random forest (RF) provided the highest accuracy in OSA detection. Therefore, Emma-fApEn could analyze the decrease in the complexity of sympathetic tone in OSA patients during sleep.","PeriodicalId":166893,"journal":{"name":"Proceedings of the 2021 10th International Conference on Bioinformatics and Biomedical Science","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122645644","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：