Objective:To determine the most influential data features and to develop machine learning approaches that best predict hospital readmissions among patients with diabetes.Methods:In this retrospective cohort study,we s...Objective:To determine the most influential data features and to develop machine learning approaches that best predict hospital readmissions among patients with diabetes.Methods:In this retrospective cohort study,we surveyed patient statistics and performed feature analysis to identify the most influential data features associated with readmissions.Classification of all-cause,30-day readmission outcomes were modeled using logistic regression,artificial neural network,and Easy Ensemble.F1 statistic,sensitivity,and positive predictive value were used to evaluate the model performance.Results:We identified 14 most influential data features(4 numeric features and 10 categorical features)and evaluated 3 machine learning models with numerous sampling methods(oversampling,undersampling,and hybrid techniques).The deep learning model offered no improvement over traditional models(logistic regression and Easy Ensemble)for predicting readmission,whereas the other two algorithms led to much smaller differences between the training and testing datasets.Conclusions:Machine learning approaches to record electronic health data offer a promising method for improving readmission prediction in patients with diabetes.But more work is needed to construct datasets with more clinical variables beyond the standard risk factors and to fine-tune and optimize machine learning models.展开更多
This paper attempts to estimate diagnostically relevant measure,i.e.,Arteriovenous Ratio with an improved retinal vessel classification using feature ranking strategies and multiple classifiers decision-combination sc...This paper attempts to estimate diagnostically relevant measure,i.e.,Arteriovenous Ratio with an improved retinal vessel classification using feature ranking strategies and multiple classifiers decision-combination scheme.The features exploited for retinal vessel characterization are based on statistical measures of histogram,different filter responses of images and local gradient in-formation.The feature selection process is based on two feature ranking approaches(Pearson Correlation Coefficient technique and Relief-F method)to rank the features followed by use of maximum classification accuracy of three supervised classifiers(κ-Nearest Neighbor,Support Vector Machine and Naïve Bayes)as a threshold for feature subset selection.Retinal vessels are labeled using the selected feature subset and proposed hybrid classification scheme,i.e.,decision fusion of multiple classifiers.The comparative analysis shows an increase in vessel classification accuracy as well as Arteriovenous Ratio calculation performance.The system is tested on three databases,a local dataset of 44 images and two publically available databases,INSPIRE-AVR containing 40 images and VICAVR containing 58 images.The local database also contains images with pathologically diseased structures.The performance of the proposed system is assessed by comparing the experimental results with the gold standard estimations as well as with the results of previous methodologies.Overall,an accuracy of 90.45%,93.90%and 87.82%is achieved in retinal blood vessel separation with 0.0565,0.0650 and 0.0849 mean error in Arte-riovenous Ratio calculation for Local,INSPIRE-AVR and VICAVR dataset,respectively.展开更多
Magnetic resonance imaging(MRI)has been a prevalence technique for breast cancer diagnosis.Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis.There are...Magnetic resonance imaging(MRI)has been a prevalence technique for breast cancer diagnosis.Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis.There are two main issues of the existing breast lesion segmentation techniques:requir ing manual delineation of Regions of Interests(ROIs)as a step of initialization;and requiring a large amount of labeled images for model construction or parameter lear ning,while in real clinical or experimental settings,it is highly challenging to get suficient labeled MRIs.To resolve these issues,this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies.After image segmentation with advanced cluster techniques,we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI To obtain the opt imal performance of tumor extraction,we take extensive experiments to learn par ameters for tumor segmentation and dassification,and design 225 classifiers corresponding to diferent parameter settings.We call the proposed method as Semi supervised Tumor Segmentation(SSTS),and apply it to both mass and nonmass lesions.Experimental results show better performance of SsTS compared with five state of-the art methods.展开更多
Heterogeneous information network (HIN)-structured data provide an effective model for practical purposes in real world. Network embedding is fundamental for supporting the network-based analysis and prediction tasks....Heterogeneous information network (HIN)-structured data provide an effective model for practical purposes in real world. Network embedding is fundamental for supporting the network-based analysis and prediction tasks. Methods of network embedding that are currently popular normally fail to effectively preserve the semantics of HIN. In this study, we propose AGA2Vec, a generative adversarial model for HIN embedding that uses attention mechanisms and meta-paths. To capture the semantic information from multi-typed entities and relations in HIN, we develop a weighted meta-path strategy to preserve the proximity of HIN. We then use an autoencoder and a generative adversarial model to obtain robust representations of HIN. The results of experiments on several real-world datasets show that the proposed approach outperforms state-of-the-art approaches for HIN embedding.展开更多
Objectives:To analyze the satisfaction of patients with community health service(CHS)and the changes of the CHS delivered before and after the new health reform in different regions of China,and to put forward relevan...Objectives:To analyze the satisfaction of patients with community health service(CHS)and the changes of the CHS delivered before and after the new health reform in different regions of China,and to put forward relevant policy recommendations for CHS development.Methods:Twelve community health centers were selected by random sampling in each of the eight typical cities in the east,middle and west regions of China.Questionnaire survey was conducted among patients visiting these institutions during daily work hours.Results:The proportions of the participants who stated that the medical environment,service attitude and medical skills of the doctors were improved were higher in the west region than those of the east and middle regions;but the percentage of patients who held that the drug price had lowered was higher in the east region than those of the middle and west region,the differences were of statistical significance(P<0.0125).The patients’satisfaction rates with medical environment,service attitude,and technical skills of the medical staff in the west region were 88.9%,91.5%and 81.6%respectively,which were higher than those in the east and middle regions.In the east region,the satisfaction rate with the reimbursement for this visit was 58.5%,which was highest among the three regions;in the west region,patients’satisfaction rates with drug types and preventive care were 51.5%and 65.9%,respectively,which was significantly higher than those in the east and middle regions(P<0.0125).As recommended by the participants,the top three aspects of health services that need to be improved were drug type and quality(25.3%),drug prices(21.8%)and technical skills(18.2%)in the east region;infrastructure(28.2%),drug prices(21.8%)and drug types and quality(21.2%)in the middle region;infrastructure(30.8%),drug types and quality(28.1%)and reimbursement(27.9%)in the west region.Conclusions:The comprehensive CHS reform should take the opinions of patients into account;essential drug system should be consolidated continually;and the reform of the payment system should be promoted by actively cooperating with the health insurance organizations.展开更多
This paper addresses an advanced analysis system for the identification of alcoholic brain states from electroencephalogram(EEG) data in an automatic way. This study introduces an optimum allocation based sampling(OAS...This paper addresses an advanced analysis system for the identification of alcoholic brain states from electroencephalogram(EEG) data in an automatic way. This study introduces an optimum allocation based sampling(OAS) scheme to discover the most favourable representative data points from every single time-window of each EEG signal considering the minimal variability of the observations. Combining all representative samples of each time-window in a set, some statistical features are extracted from every set of each class. The Mann-Whitney U test is used to assess whether each of the features is significant between the two classes(e.g., alcoholic and control). In order to evaluate the effectiveness of the OAS-based features, four well-known machine learning methods(decision table,support vector machine(SVM), k-nearest neighbor(k-NN) and logistic regression) are considered for identification of alcoholic brain state. The experimental results on the UCI KDD(i.e., UCI knowledge discovery in databases) database demonstrate that the OAS based decision table algorithm yields the highest accuracy of 99.58% with a low false alarm rate 0.40%, which is an improvement of up to9.58% over the existing algorithms. A proposed analysis system can be used to detect alcoholism and also to determine the level of alcoholism-related changes in EEG signals.展开更多
Summary What is already known about this topic?Campylobacter genus bacteria are recognized as some of the leading causes of the bacterial diarrheal illness in both developing and developed countries.Recent pilot surve...Summary What is already known about this topic?Campylobacter genus bacteria are recognized as some of the leading causes of the bacterial diarrheal illness in both developing and developed countries.Recent pilot surveillance study revealed Campylobacter is the most common pathogen in the diarrheal cases using the enhanced filtration methods in Beijing.One outbreak caused by multi-drug resistant Campylobacter coli(C.coli)was identified in 2018.展开更多
Many location-based services need to query objects existing in a specific space,such as location-based tourism resource recommendation.Both a large number of spatial objects and the real-time object access requirement...Many location-based services need to query objects existing in a specific space,such as location-based tourism resource recommendation.Both a large number of spatial objects and the real-time object access requirements of location-based services pose a big challenge for spatial object storage and query management.In this paper,we propose HGeoHashBase,an improved storage model by integrating GeoHash with key-value structure,to organize spatial objects for efficient range queries.GeoHash is responsible for spatial encoding and key-value structure as underlying data storage.Both the similarity of the encodings for objects in the close geographical locations and the multi-version data mechanism are blended into the proposed model well.Considering the tradeoff between encoding precision and query performance,a theoretical proof is presented.Extensive experiments are designed and conducted,whose results show that the proposed model can gain significant performance improvement.展开更多
Objective:Changes in supplying community health services,degree of satisfaction,and pol-icy suggestions are presented from the perspectives of health professionals in different regions of China with the purpose of fur...Objective:Changes in supplying community health services,degree of satisfaction,and pol-icy suggestions are presented from the perspectives of health professionals in different regions of China with the purpose of further facilitating comprehensive reform of community health services.Methods:Based on geographic location and economic level of development,eight cities were selected and 12 community health service institutions were chosen by random sampling from each city.A questionnaire survey was conducted by the health professionals.Results:With respect to working enthusiasm,reduction in antibiotic drug use,social image and trust of patients,more health professionals in middle and western China showed positive feed-backs than those in eastern China.With respect to preliminary results of the reform,performance and salary,and health care insurance policies,health professionals’satisfaction levels in middle and western China were higher than in eastern China.The health professionals in middle and western China were more concerned about equipment,infrastructure and increasing training op-portunities.The health professionals in both eastern and middle China accentuated improving the variety of essential drugs covered by health insurance,while health professionals in eastern China suggested performance-related payment reform.Conclusions:The performance of health professionals in middle and western China was improved more signifi cantly through comprehensive reform than that of health professionals in eastern China.For health professionals in middle and western China,it is essential to strengthen infrastructure and increase professional training,while health professionals in middle and eastern China would like to see an increase in the variety of essential drugs,and those in eastern China require strengthening performance-related payment reform.展开更多
Objective:This research aims to develop a more scientific and reasonable performance evaluation indicator system for the implementation of an essential drug system in community health service institutions.Methods:The ...Objective:This research aims to develop a more scientific and reasonable performance evaluation indicator system for the implementation of an essential drug system in community health service institutions.Methods:The Delphi method was used to establish an indicator system based on three rounds of expert consultations,and the fuzzy comprehensive evaluation method was used to determine the weights of the indicators.Results:The participation in the three rounds of consultations were 100%(10/10),90%(18/20),and 85%(17/20),which showed that the experts had real enthusiasm for participating in this research.The authority coefficients of the first-,second-,and third-level indicators were 0.75,0.76,and 0.76,respectively,which showed that the consultation results were dependable.The concordance coefficients of the second and third rounds were 0.489 and 0.487,respectively(P<0.001),indicating that the expert opinions were highly consistent.The performance evaluation indicator system consisted of three first-level indicators(supporting,implementation,and effect indicators),nine second-level indicators,and 21 third-level indicators.Conclusion:In this new performance evaluation indicator system,the selected experts were representative,the consultation results were dependable,the constructed evaluation indicator system was reasonable,and the setting of weights was scientific.展开更多
基金supported in part by the Key Research and Development Program for Guangdong Province(No.2019B010136001)in part by Hainan Major Science and Technology Projects(No.ZDKJ2019010)+3 种基金in part by the National Key Research and Development Program of China(No.2016YFB0800803 and No.2018YFB1004005)in part by National Natural Science Foundation of China(No.81960565,No.81260139,No.81060073,No.81560275,No.61562021,No.30560161 and No.61872110)in part by Hainan Special Projects of Social Development(No.ZDYF2018103 and No.2015SF 39)in part by Hainan Association for Academic Excellence Youth Science and Technology Innovation Program(No.201515)
文摘Objective:To determine the most influential data features and to develop machine learning approaches that best predict hospital readmissions among patients with diabetes.Methods:In this retrospective cohort study,we surveyed patient statistics and performed feature analysis to identify the most influential data features associated with readmissions.Classification of all-cause,30-day readmission outcomes were modeled using logistic regression,artificial neural network,and Easy Ensemble.F1 statistic,sensitivity,and positive predictive value were used to evaluate the model performance.Results:We identified 14 most influential data features(4 numeric features and 10 categorical features)and evaluated 3 machine learning models with numerous sampling methods(oversampling,undersampling,and hybrid techniques).The deep learning model offered no improvement over traditional models(logistic regression and Easy Ensemble)for predicting readmission,whereas the other two algorithms led to much smaller differences between the training and testing datasets.Conclusions:Machine learning approaches to record electronic health data offer a promising method for improving readmission prediction in patients with diabetes.But more work is needed to construct datasets with more clinical variables beyond the standard risk factors and to fine-tune and optimize machine learning models.
文摘This paper attempts to estimate diagnostically relevant measure,i.e.,Arteriovenous Ratio with an improved retinal vessel classification using feature ranking strategies and multiple classifiers decision-combination scheme.The features exploited for retinal vessel characterization are based on statistical measures of histogram,different filter responses of images and local gradient in-formation.The feature selection process is based on two feature ranking approaches(Pearson Correlation Coefficient technique and Relief-F method)to rank the features followed by use of maximum classification accuracy of three supervised classifiers(κ-Nearest Neighbor,Support Vector Machine and Naïve Bayes)as a threshold for feature subset selection.Retinal vessels are labeled using the selected feature subset and proposed hybrid classification scheme,i.e.,decision fusion of multiple classifiers.The comparative analysis shows an increase in vessel classification accuracy as well as Arteriovenous Ratio calculation performance.The system is tested on three databases,a local dataset of 44 images and two publically available databases,INSPIRE-AVR containing 40 images and VICAVR containing 58 images.The local database also contains images with pathologically diseased structures.The performance of the proposed system is assessed by comparing the experimental results with the gold standard estimations as well as with the results of previous methodologies.Overall,an accuracy of 90.45%,93.90%and 87.82%is achieved in retinal blood vessel separation with 0.0565,0.0650 and 0.0849 mean error in Arte-riovenous Ratio calculation for Local,INSPIRE-AVR and VICAVR dataset,respectively.
基金the National Natural Science Foundation of China(Grants No 61702274)the Natural Science Foundation of Jiangsu Province(Grants No BK20170958).
文摘Magnetic resonance imaging(MRI)has been a prevalence technique for breast cancer diagnosis.Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis.There are two main issues of the existing breast lesion segmentation techniques:requir ing manual delineation of Regions of Interests(ROIs)as a step of initialization;and requiring a large amount of labeled images for model construction or parameter lear ning,while in real clinical or experimental settings,it is highly challenging to get suficient labeled MRIs.To resolve these issues,this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies.After image segmentation with advanced cluster techniques,we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI To obtain the opt imal performance of tumor extraction,we take extensive experiments to learn par ameters for tumor segmentation and dassification,and design 225 classifiers corresponding to diferent parameter settings.We call the proposed method as Semi supervised Tumor Segmentation(SSTS),and apply it to both mass and nonmass lesions.Experimental results show better performance of SsTS compared with five state of-the art methods.
基金This work was supported by the National Natural Science Foundation of China under Grant No.61672161the Youth Research Fund of Shanghai Municipal Health and Family Planning Commission of China under Grant No.2015Y0195。
文摘Heterogeneous information network (HIN)-structured data provide an effective model for practical purposes in real world. Network embedding is fundamental for supporting the network-based analysis and prediction tasks. Methods of network embedding that are currently popular normally fail to effectively preserve the semantics of HIN. In this study, we propose AGA2Vec, a generative adversarial model for HIN embedding that uses attention mechanisms and meta-paths. To capture the semantic information from multi-typed entities and relations in HIN, we develop a weighted meta-path strategy to preserve the proximity of HIN. We then use an autoencoder and a generative adversarial model to obtain robust representations of HIN. The results of experiments on several real-world datasets show that the proposed approach outperforms state-of-the-art approaches for HIN embedding.
基金Supported by the CAHHF project(AuSAID):FA55 HSS409。
文摘Objectives:To analyze the satisfaction of patients with community health service(CHS)and the changes of the CHS delivered before and after the new health reform in different regions of China,and to put forward relevant policy recommendations for CHS development.Methods:Twelve community health centers were selected by random sampling in each of the eight typical cities in the east,middle and west regions of China.Questionnaire survey was conducted among patients visiting these institutions during daily work hours.Results:The proportions of the participants who stated that the medical environment,service attitude and medical skills of the doctors were improved were higher in the west region than those of the east and middle regions;but the percentage of patients who held that the drug price had lowered was higher in the east region than those of the middle and west region,the differences were of statistical significance(P<0.0125).The patients’satisfaction rates with medical environment,service attitude,and technical skills of the medical staff in the west region were 88.9%,91.5%and 81.6%respectively,which were higher than those in the east and middle regions.In the east region,the satisfaction rate with the reimbursement for this visit was 58.5%,which was highest among the three regions;in the west region,patients’satisfaction rates with drug types and preventive care were 51.5%and 65.9%,respectively,which was significantly higher than those in the east and middle regions(P<0.0125).As recommended by the participants,the top three aspects of health services that need to be improved were drug type and quality(25.3%),drug prices(21.8%)and technical skills(18.2%)in the east region;infrastructure(28.2%),drug prices(21.8%)and drug types and quality(21.2%)in the middle region;infrastructure(30.8%),drug types and quality(28.1%)and reimbursement(27.9%)in the west region.Conclusions:The comprehensive CHS reform should take the opinions of patients into account;essential drug system should be consolidated continually;and the reform of the payment system should be promoted by actively cooperating with the health insurance organizations.
基金supported by National Natural Science Foundation of China (No. 61332013)the Australian Research Council (ARC) Linkage Project (No. LP100200682)Discovery Project (No. DP140100841)
文摘This paper addresses an advanced analysis system for the identification of alcoholic brain states from electroencephalogram(EEG) data in an automatic way. This study introduces an optimum allocation based sampling(OAS) scheme to discover the most favourable representative data points from every single time-window of each EEG signal considering the minimal variability of the observations. Combining all representative samples of each time-window in a set, some statistical features are extracted from every set of each class. The Mann-Whitney U test is used to assess whether each of the features is significant between the two classes(e.g., alcoholic and control). In order to evaluate the effectiveness of the OAS-based features, four well-known machine learning methods(decision table,support vector machine(SVM), k-nearest neighbor(k-NN) and logistic regression) are considered for identification of alcoholic brain state. The experimental results on the UCI KDD(i.e., UCI knowledge discovery in databases) database demonstrate that the OAS based decision table algorithm yields the highest accuracy of 99.58% with a low false alarm rate 0.40%, which is an improvement of up to9.58% over the existing algorithms. A proposed analysis system can be used to detect alcoholism and also to determine the level of alcoholism-related changes in EEG signals.
基金This work was supported by National Key Scientific and Technology Project(2018ZX 10305409 and 2018ZX10712-001).
文摘Summary What is already known about this topic?Campylobacter genus bacteria are recognized as some of the leading causes of the bacterial diarrheal illness in both developing and developed countries.Recent pilot surveillance study revealed Campylobacter is the most common pathogen in the diarrheal cases using the enhanced filtration methods in Beijing.One outbreak caused by multi-drug resistant Campylobacter coli(C.coli)was identified in 2018.
基金This study was supported by the National Natural Sci-ence Foundation of China(Grant Nos.61462017,61363005,U1501252,61662013)Guangxi Natural Science Foundation of China(2017GXNS-FAA 198035,2014GXNSFAA118353,2014GXNSFAA118390)+1 种基金Guangxi Key Laboratory of Automatic Detection Technology and Instrument Foun-dation(YQ15110)Guangxi Cooperative Innovation Center of Cloud Computing and Big Data,and the High Level Innovation Team of Colleges and Universities in Guangxi and Outstanding Scholars Program Funding.
文摘Many location-based services need to query objects existing in a specific space,such as location-based tourism resource recommendation.Both a large number of spatial objects and the real-time object access requirements of location-based services pose a big challenge for spatial object storage and query management.In this paper,we propose HGeoHashBase,an improved storage model by integrating GeoHash with key-value structure,to organize spatial objects for efficient range queries.GeoHash is responsible for spatial encoding and key-value structure as underlying data storage.Both the similarity of the encodings for objects in the close geographical locations and the multi-version data mechanism are blended into the proposed model well.Considering the tradeoff between encoding precision and query performance,a theoretical proof is presented.Extensive experiments are designed and conducted,whose results show that the proposed model can gain significant performance improvement.
基金Sino-Australia Health and HIV/AIDS fund project[Project No:FA55 HSS409].
文摘Objective:Changes in supplying community health services,degree of satisfaction,and pol-icy suggestions are presented from the perspectives of health professionals in different regions of China with the purpose of further facilitating comprehensive reform of community health services.Methods:Based on geographic location and economic level of development,eight cities were selected and 12 community health service institutions were chosen by random sampling from each city.A questionnaire survey was conducted by the health professionals.Results:With respect to working enthusiasm,reduction in antibiotic drug use,social image and trust of patients,more health professionals in middle and western China showed positive feed-backs than those in eastern China.With respect to preliminary results of the reform,performance and salary,and health care insurance policies,health professionals’satisfaction levels in middle and western China were higher than in eastern China.The health professionals in middle and western China were more concerned about equipment,infrastructure and increasing training op-portunities.The health professionals in both eastern and middle China accentuated improving the variety of essential drugs covered by health insurance,while health professionals in eastern China suggested performance-related payment reform.Conclusions:The performance of health professionals in middle and western China was improved more signifi cantly through comprehensive reform than that of health professionals in eastern China.For health professionals in middle and western China,it is essential to strengthen infrastructure and increase professional training,while health professionals in middle and eastern China would like to see an increase in the variety of essential drugs,and those in eastern China require strengthening performance-related payment reform.
基金the“Research on Performance Evaluation of Chinese Community Health Service Institutions’Implementation of Essential Medicine System”supported by National Natural Science Foundation[71103130]。
文摘Objective:This research aims to develop a more scientific and reasonable performance evaluation indicator system for the implementation of an essential drug system in community health service institutions.Methods:The Delphi method was used to establish an indicator system based on three rounds of expert consultations,and the fuzzy comprehensive evaluation method was used to determine the weights of the indicators.Results:The participation in the three rounds of consultations were 100%(10/10),90%(18/20),and 85%(17/20),which showed that the experts had real enthusiasm for participating in this research.The authority coefficients of the first-,second-,and third-level indicators were 0.75,0.76,and 0.76,respectively,which showed that the consultation results were dependable.The concordance coefficients of the second and third rounds were 0.489 and 0.487,respectively(P<0.001),indicating that the expert opinions were highly consistent.The performance evaluation indicator system consisted of three first-level indicators(supporting,implementation,and effect indicators),nine second-level indicators,and 21 third-level indicators.Conclusion:In this new performance evaluation indicator system,the selected experts were representative,the consultation results were dependable,the constructed evaluation indicator system was reasonable,and the setting of weights was scientific.
