Both microarray and next generation RNA sequencing methods have vastly improved our ability to detect transcript variation underlying organism development and disease. While many tools exist to assess gene and transcript variation, there is a paucity of methods to evaluate cell type identity relative to the hundreds of known adult and progenitor cell types. Such methods are sorely needed to understand which cell types are present within a biological sample, particularly during lineage restricted in vitro stem cell differentiation. We have developed LineageProfiler as a component of the AltAnalyze analysis package (http://www.altanalyze.org), to analyze and visualize transcriptome correlations to a large compendium of tissues, isolated cell types or progenitor states. Unlike related methods, LineageProfiler can utilize gene or exon expression profiles from either microarray or next generation sequencing data to derive correlations. Associated Z scores are automatically visualized along a comprehensive lineage network or as a clustered heatmap. Through integration with the tool GO-Elite (http://www.genmapp.org/go_elite), underlying biomarkers are used to evaluate enrichment of cell types between conditions and samples. This approach has been successful at accurately identifying known populations of differentiating cells in vitro from RNA-Seq, measuring the relative abundance of cell types from mixed tissue experiments and identifying contamination due to inconsistent tissue dissection.
{"title":"LineageProfiler: Automated Classification and Visualization of Cell Type Identity for Mammalian Transcriptomes","authors":"N. Salomonis","doi":"10.1109/HISB.2012.39","DOIUrl":"https://doi.org/10.1109/HISB.2012.39","url":null,"abstract":"Both microarray and next generation RNA sequencing methods have vastly improved our ability to detect transcript variation underlying organism development and disease. While many tools exist to assess gene and transcript variation, there is a paucity of methods to evaluate cell type identity relative to the hundreds of known adult and progenitor cell types. Such methods are sorely needed to understand which cell types are present within a biological sample, particularly during lineage restricted in vitro stem cell differentiation. We have developed LineageProfiler as a component of the AltAnalyze analysis package (http://www.altanalyze.org), to analyze and visualize transcriptome correlations to a large compendium of tissues, isolated cell types or progenitor states. Unlike related methods, LineageProfiler can utilize gene or exon expression profiles from either microarray or next generation sequencing data to derive correlations. Associated Z scores are automatically visualized along a comprehensive lineage network or as a clustered heatmap. Through integration with the tool GO-Elite (http://www.genmapp.org/go_elite), underlying biomarkers are used to evaluate enrichment of cell types between conditions and samples. This approach has been successful at accurately identifying known populations of differentiating cells in vitro from RNA-Seq, measuring the relative abundance of cell types from mixed tissue experiments and identifying contamination due to inconsistent tissue dissection.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131174751","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}
Zhuohui Gan, Jianwu Wang, N. Salomonis, I. Altintas, A. McCulloch, A. Zambon
In this paper, an extensible workflow, named MAAMD, is constructed to facilitate and standardize Affymetrix meta-analyses using Kepler, an open-source software that supports user-customized scientific workflows.
{"title":"MAAMD: A Workflow to Standardize Meta-Analyses of Affymetrix Microarray Data","authors":"Zhuohui Gan, Jianwu Wang, N. Salomonis, I. Altintas, A. McCulloch, A. Zambon","doi":"10.1109/HISB.2012.45","DOIUrl":"https://doi.org/10.1109/HISB.2012.45","url":null,"abstract":"In this paper, an extensible workflow, named MAAMD, is constructed to facilitate and standardize Affymetrix meta-analyses using Kepler, an open-source software that supports user-customized scientific workflows.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141124","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}
Mei Liu, M. Matheny, Yonghui Wu, E. M. Hinz, J. Denny, J. Schildcrout, R. Miller, Hua Xu
Introduction: Medication safety requires monitoring throughout a drug's market life. Early detection of adverse drug reactions (ADRs) can lead to alerts that prevent patient harm. Recently, electronic medical records (EMRs) have emerged as a valuable resource for pharmacovigilance. This study examines the use of retrospective medication orders and inpatient laboratory results in the EMR to identify ADRs. Methods: Using 12 years of EMR data, we designed a study to correlate abnormal laboratory results with specific drug orders by comparing outcomes of a drug-exposed group and a matched unexposed group. We assessed the relative merits of six pharmacovigilance methods used in spontaneous reporting systems (SRS), including proportional reporting ratio (PRR), reporting odds ratio (ROR), Yule's Q, the Chi-square test, Bayesian confidence propagation neural networks (BCPNN) and a gamma Poisson shrinker (GPS). The time of admission was set as "day zero" and all drug orders and laboratory results timings were represented as days elapsed since that time until discharge. Each patient in the exposed group was randomly matched to four unexposed patients by age group, gender, race, and major diagnoses based on ICD9 codes.
{"title":"Detecting Adverse Drug Reactions Using Inpatient Medication Orders and Laboratory Tests Data","authors":"Mei Liu, M. Matheny, Yonghui Wu, E. M. Hinz, J. Denny, J. Schildcrout, R. Miller, Hua Xu","doi":"10.1109/HISB.2012.56","DOIUrl":"https://doi.org/10.1109/HISB.2012.56","url":null,"abstract":"Introduction: Medication safety requires monitoring throughout a drug's market life. Early detection of adverse drug reactions (ADRs) can lead to alerts that prevent patient harm. Recently, electronic medical records (EMRs) have emerged as a valuable resource for pharmacovigilance. This study examines the use of retrospective medication orders and inpatient laboratory results in the EMR to identify ADRs. Methods: Using 12 years of EMR data, we designed a study to correlate abnormal laboratory results with specific drug orders by comparing outcomes of a drug-exposed group and a matched unexposed group. We assessed the relative merits of six pharmacovigilance methods used in spontaneous reporting systems (SRS), including proportional reporting ratio (PRR), reporting odds ratio (ROR), Yule's Q, the Chi-square test, Bayesian confidence propagation neural networks (BCPNN) and a gamma Poisson shrinker (GPS). The time of admission was set as \"day zero\" and all drug orders and laboratory results timings were represented as days elapsed since that time until discharge. Each patient in the exposed group was randomly matched to four unexposed patients by age group, gender, race, and major diagnoses based on ICD9 codes.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446899","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}
Seemeen Karimi, Xiaoqian Jiang, P. Cosman, H. Martz
We developed a method to evaluate the accuracy of segmentation algorithms. Oversegmentation, undersegmentation, missing and spurious labels may all appear concurrently in machine segmented images. Segmentation algorithms make systematic errors and have different optimal operating ranges. Existing methods of segmentation evaluation do not evaluate these details. Our method, based on multiple feature recovery, reports systematic errors and indicates optimal operating ranges of features, besides measuring overall errors. A knowledge of the magnitude and type of errors can be used for tuning or selecting segmentation algorithms. Although our method was developed for CT scanning for security, it is applicable to other fields, including medical imaging, where multi-object feature recovery, non-uniform costs and a knowledge of optimal operating ranges are helpful.
{"title":"Evaluation of Segmentation Algorithms in CT Scanning","authors":"Seemeen Karimi, Xiaoqian Jiang, P. Cosman, H. Martz","doi":"10.1109/HISB.2012.64","DOIUrl":"https://doi.org/10.1109/HISB.2012.64","url":null,"abstract":"We developed a method to evaluate the accuracy of segmentation algorithms. Oversegmentation, undersegmentation, missing and spurious labels may all appear concurrently in machine segmented images. Segmentation algorithms make systematic errors and have different optimal operating ranges. Existing methods of segmentation evaluation do not evaluate these details. Our method, based on multiple feature recovery, reports systematic errors and indicates optimal operating ranges of features, besides measuring overall errors. A knowledge of the magnitude and type of errors can be used for tuning or selecting segmentation algorithms. Although our method was developed for CT scanning for security, it is applicable to other fields, including medical imaging, where multi-object feature recovery, non-uniform costs and a knowledge of optimal operating ranges are helpful.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128227532","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}
Shuang Wang, Xiaoqian Jiang, L. Ohno-Machado, Lijuan Cui, Samuel Cheng, H. Xiong
Privacy is an important concern when biometrics are used in authentication systems for accessing Electronic Health Records (EHR) or other biomedical research data repositories involving human subjects. Biometrics of individuals deserve careful protection because they contain sensitive information closely related to personal privacy (e.g., personal health, ethnic group, etc.) and the leakage of such information can be used to re-identify individuals. More importantly, biometrics are unique and they are not easily revocable. Existing secure biometric systems prevent attackers from collecting unprotected biometrics in databases, however, they cannot guarantee confidentiality in probing and transmitting biometrics.
{"title":"Privacy-Preserving Biometric System for Secure Fingerprint Authentication","authors":"Shuang Wang, Xiaoqian Jiang, L. Ohno-Machado, Lijuan Cui, Samuel Cheng, H. Xiong","doi":"10.1109/HISB.2012.53","DOIUrl":"https://doi.org/10.1109/HISB.2012.53","url":null,"abstract":"Privacy is an important concern when biometrics are used in authentication systems for accessing Electronic Health Records (EHR) or other biomedical research data repositories involving human subjects. Biometrics of individuals deserve careful protection because they contain sensitive information closely related to personal privacy (e.g., personal health, ethnic group, etc.) and the leakage of such information can be used to re-identify individuals. More importantly, biometrics are unique and they are not easily revocable. Existing secure biometric systems prevent attackers from collecting unprotected biometrics in databases, however, they cannot guarantee confidentiality in probing and transmitting biometrics.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"679 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116107607","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}
Shuang Wang, Xiaoqian Jiang, L. Ohno-Machado, Lijuan Cui, Samuel Cheng
The privacy and security of biomedical data are important. Ideally, biomedical data should be kept in a secure manner (i.e. encrypted). With the increasing deployment of the electronic health records, it is critical to make protected health information (PHI) available securely to private and public healthcare providers through the National Health Information Network (NHIN). Efficient transmission and storage of these large encrypted biomedical data becomes an important concern. An intuitive way is to compress the encrypted biomedical data directly. Unfortunately, traditional compression algorithms (removing redundancy through exploiting the structure of data) fail to handle encrypted data. The reason is that encrypted data appear to be random and lack the structure in the original data. The "best" practice has been compressing the data before encryption, however, this is not appropriate for privacy related scenarios (e.g., biomedical application), where one wants to process data while keeping them encrypted and safe. In this paper, we develop a Secure Privacy-presERving Medical Image CompRessiOn (SUPERMICRO) framework based on distributed source coding (DSC), which makes the compression of the encrypted data possible without compromising security and compression efficiency. Our approach guarantees the data transmission and storage in a privacy-preserving manner. We tested our proposed framework on two CT image sequences and compared it with the state-of-the-art JPEG 2000 lossless compression. Experimental results demonstrated that the SUPERMICRO framework provides enhanced security and privacy protection, as well as high compression performance.
{"title":"SecUre Privacy-presERving Medical Image CompRessiOn (SUPERMICRO)","authors":"Shuang Wang, Xiaoqian Jiang, L. Ohno-Machado, Lijuan Cui, Samuel Cheng","doi":"10.1109/HISB.2012.55","DOIUrl":"https://doi.org/10.1109/HISB.2012.55","url":null,"abstract":"The privacy and security of biomedical data are important. Ideally, biomedical data should be kept in a secure manner (i.e. encrypted). With the increasing deployment of the electronic health records, it is critical to make protected health information (PHI) available securely to private and public healthcare providers through the National Health Information Network (NHIN). Efficient transmission and storage of these large encrypted biomedical data becomes an important concern. An intuitive way is to compress the encrypted biomedical data directly. Unfortunately, traditional compression algorithms (removing redundancy through exploiting the structure of data) fail to handle encrypted data. The reason is that encrypted data appear to be random and lack the structure in the original data. The \"best\" practice has been compressing the data before encryption, however, this is not appropriate for privacy related scenarios (e.g., biomedical application), where one wants to process data while keeping them encrypted and safe. In this paper, we develop a Secure Privacy-presERving Medical Image CompRessiOn (SUPERMICRO) framework based on distributed source coding (DSC), which makes the compression of the encrypted data possible without compromising security and compression efficiency. Our approach guarantees the data transmission and storage in a privacy-preserving manner. We tested our proposed framework on two CT image sequences and compared it with the state-of-the-art JPEG 2000 lossless compression. Experimental results demonstrated that the SUPERMICRO framework provides enhanced security and privacy protection, as well as high compression performance.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121278146","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}
The deep sequencing of transcriptomes has revolutionized our ability to detect known and novel RNA variants at a never before observed resolution. To capitalize on these ever improving technologies, we require functionally rich methods of annotation to predict and evaluate the consequences of RNA isoform variation at the level of proteins, domains and microRNA binding sites. We introduce a new version of the popular open-source application AltAnalyze, capable of analyzing RNA-Sequencing (RNA-Seq) datasets as well as splicing-sensitive or conventional arrays. This software can be run through an intuitive graphical user interface or command-line. Over 60 species and data from various RNA-Seq alignment workflows are immediately supported without any specialized configuration. AltAnalyze provides multiple options for gene expression quantification, filtering, quality control and biological interpretation. Hierarchical clustering heatmaps, principal component analysis plots, lineage correlation diagrams and visualization of enriched pathways are automatically produced for differentially expressed genes. For detection of alternative splicing, promoter or polyadenylation events, AltAnalyze combines both reciprocal-junction and alternative-exon expression approaches to identify annotated and novel RNA variation. By connecting these regulated splicing-events with optimal inclusion and exclusion isoforms, AltAnalyze is able to evaluate the impact of alternative RNA expression on protein domains, annotated motifs and binding sites for microRNAs. From a broader perspective, AltAnalyze examines the enrichment of effected domains and microRNA binding sites, to highlight the global impact of alternative splicing. Together, AltAnalyze provides an efficient, streamlined and comprehensive set of analysis results, to determine the biological impact of transcriptome regulation.
{"title":"AltAnalyze - An Optimized Platform for RNA-Seq Splicing and Domain-Level Analyses","authors":"N. Salomonis","doi":"10.1109/HISB.2012.38","DOIUrl":"https://doi.org/10.1109/HISB.2012.38","url":null,"abstract":"The deep sequencing of transcriptomes has revolutionized our ability to detect known and novel RNA variants at a never before observed resolution. To capitalize on these ever improving technologies, we require functionally rich methods of annotation to predict and evaluate the consequences of RNA isoform variation at the level of proteins, domains and microRNA binding sites. We introduce a new version of the popular open-source application AltAnalyze, capable of analyzing RNA-Sequencing (RNA-Seq) datasets as well as splicing-sensitive or conventional arrays. This software can be run through an intuitive graphical user interface or command-line. Over 60 species and data from various RNA-Seq alignment workflows are immediately supported without any specialized configuration. AltAnalyze provides multiple options for gene expression quantification, filtering, quality control and biological interpretation. Hierarchical clustering heatmaps, principal component analysis plots, lineage correlation diagrams and visualization of enriched pathways are automatically produced for differentially expressed genes. For detection of alternative splicing, promoter or polyadenylation events, AltAnalyze combines both reciprocal-junction and alternative-exon expression approaches to identify annotated and novel RNA variation. By connecting these regulated splicing-events with optimal inclusion and exclusion isoforms, AltAnalyze is able to evaluate the impact of alternative RNA expression on protein domains, annotated motifs and binding sites for microRNAs. From a broader perspective, AltAnalyze examines the enrichment of effected domains and microRNA binding sites, to highlight the global impact of alternative splicing. Together, AltAnalyze provides an efficient, streamlined and comprehensive set of analysis results, to determine the biological impact of transcriptome regulation.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121314106","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}
M. Kahn, L. Schilling, Bethany M. Kwan, Aidan Bunting, Christopher A. Uhrich, C. Singleton
The growing availability of electronic clinical data is enabling new opportunities for large-scale distributed data-sharing networks that support comparative effectiveness research (CER). Data stored in electronic health records (EHRs) require substantial processing to be usable in distributed research networks (DRNs). We describe the functional features of ROSITA (Reusable OMOP and SAFTINet Interface Adaptor), a virtual machine package that performs many required functions to transform EHR data for use in distributed CER networks. ROSITA is a "middleware" component of SAFTINet, a multi-institutional DRN focused on CER studies to inform the care of safety net populations.
{"title":"Preparing Electronic Health Records Data for Comparative Effectiveness Studies","authors":"M. Kahn, L. Schilling, Bethany M. Kwan, Aidan Bunting, Christopher A. Uhrich, C. Singleton","doi":"10.1109/HISB.2012.9","DOIUrl":"https://doi.org/10.1109/HISB.2012.9","url":null,"abstract":"The growing availability of electronic clinical data is enabling new opportunities for large-scale distributed data-sharing networks that support comparative effectiveness research (CER). Data stored in electronic health records (EHRs) require substantial processing to be usable in distributed research networks (DRNs). We describe the functional features of ROSITA (Reusable OMOP and SAFTINet Interface Adaptor), a virtual machine package that performs many required functions to transform EHR data for use in distributed CER networks. ROSITA is a \"middleware\" component of SAFTINet, a multi-institutional DRN focused on CER studies to inform the care of safety net populations.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130407120","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}
C. Tao, Guoqian Jiang, T. Oniki, R. Freimuth, Jyotishman Pathak, Qian Zhu, Deepak K. Sharma, S. Huff, C. Chute
Healthcare system interoperability is one of the most important goals for Meaningful Use of the Electronic Health Records (EHR). It is essential to facilitate IT support for workflow management, decision support systems, and evidence-based healthcare, as well as secondary use of EHR across healthcare organizations. The Clinical Element Model (CEM) was designed to provide a consistent architecture for representing clinical information in EHR systems. The CEM has been adopted in the Strategic Health IT Advanced Research Project, secondary use of EHR (SHARPn) as the common unified information model for unambiguous data representation, interpretation, and exchange within and across heterogeneous sources and applications.
{"title":"A Semantic-Web Oriented Representation of Clinical Element Model for Secondary Use of Electronic Healthcare Data","authors":"C. Tao, Guoqian Jiang, T. Oniki, R. Freimuth, Jyotishman Pathak, Qian Zhu, Deepak K. Sharma, S. Huff, C. Chute","doi":"10.1109/HISB.2012.58","DOIUrl":"https://doi.org/10.1109/HISB.2012.58","url":null,"abstract":"Healthcare system interoperability is one of the most important goals for Meaningful Use of the Electronic Health Records (EHR). It is essential to facilitate IT support for workflow management, decision support systems, and evidence-based healthcare, as well as secondary use of EHR across healthcare organizations. The Clinical Element Model (CEM) was designed to provide a consistent architecture for representing clinical information in EHR systems. The CEM has been adopted in the Strategic Health IT Advanced Research Project, secondary use of EHR (SHARPn) as the common unified information model for unambiguous data representation, interpretation, and exchange within and across heterogeneous sources and applications.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129610832","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}
Increased amounts of data contained in electronic health records (EHRs) has led to inefficiencies for clinicians trying to locate relevant patient information. Automated summarization tools that create condition-specific data displays rather than current displays by data type have the potential to greatly improve clinician efficiency. These tools require new kinds of clinical knowledge (e.g., problem-medication relationships) that is difficult to obtain. We compared association rule mining and crowdsourcing as automated methods for generating a knowledge base of problem-medication pairs using a single source of clinical data from a commercially available EHR. The association rule mining and crowdsourcing approaches identified 19,586 and 31,440 pairs respectively. When comparing the top 500 pairs from each approach, only 186 overlapped. Manual inspection of the pairs indicated that crowdsourcing identified mostly common relationships, while association rule mining identified a combination of common and rare relationships. These findings indicate that the approaches are complementary, and further research is necessary to combine the approaches and better evaluate the approaches to generate an all-inclusive, highly accurate problem-medication knowledge base.
{"title":"Comparison of Association Rule Mining and Crowdsourcing for Automated Generation of a Problem-Medication Knowledge Base","authors":"A. McCoy, Dean F. Sittig, A. Wright","doi":"10.1109/HISB.2012.50","DOIUrl":"https://doi.org/10.1109/HISB.2012.50","url":null,"abstract":"Increased amounts of data contained in electronic health records (EHRs) has led to inefficiencies for clinicians trying to locate relevant patient information. Automated summarization tools that create condition-specific data displays rather than current displays by data type have the potential to greatly improve clinician efficiency. These tools require new kinds of clinical knowledge (e.g., problem-medication relationships) that is difficult to obtain. We compared association rule mining and crowdsourcing as automated methods for generating a knowledge base of problem-medication pairs using a single source of clinical data from a commercially available EHR. The association rule mining and crowdsourcing approaches identified 19,586 and 31,440 pairs respectively. When comparing the top 500 pairs from each approach, only 186 overlapped. Manual inspection of the pairs indicated that crowdsourcing identified mostly common relationships, while association rule mining identified a combination of common and rare relationships. These findings indicate that the approaches are complementary, and further research is necessary to combine the approaches and better evaluate the approaches to generate an all-inclusive, highly accurate problem-medication knowledge base.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129495048","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：