SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)最新文献
Many data privacy models have been created in the last few years using the k-anonymization methodology including l-diversity, p-sensitive k-anonymity, and t-closeness. While these methods differ in their approaches and quality of the results, they all focus on ensuring the anonymization of the data while at the same time attempt to protect the quality of the data by minimizing the loss of the information contained in the original data set. In this paper, we propose an automated k-anonymity approach that uses clustering to maximize the utility of the data while ensuring that the data privacy is maintained. Our method employs data constraint rules, which are defined by the data research expert to represent especially informative distributions in categorical attributes or inflections points in a continuous attribute. The values of the data constraints are an integral component of our utility function, which is used to maximize the utility of the anonymized dataset. Finally, we present our experimental results that show that our approach meets or exceeds existing methods that do not incorporate data constraint rules.
{"title":"An automated data utility clustering methodology using data constraint rules","authors":"Stuart Morton, M. Mahoui, P. Gibson","doi":"10.1145/2389707.2389710","DOIUrl":"https://doi.org/10.1145/2389707.2389710","url":null,"abstract":"Many data privacy models have been created in the last few years using the k-anonymization methodology including l-diversity, p-sensitive k-anonymity, and t-closeness. While these methods differ in their approaches and quality of the results, they all focus on ensuring the anonymization of the data while at the same time attempt to protect the quality of the data by minimizing the loss of the information contained in the original data set. In this paper, we propose an automated k-anonymity approach that uses clustering to maximize the utility of the data while ensuring that the data privacy is maintained. Our method employs data constraint rules, which are defined by the data research expert to represent especially informative distributions in categorical attributes or inflections points in a continuous attribute. The values of the data constraints are an integral component of our utility function, which is used to maximize the utility of the anonymized dataset. Finally, we present our experimental results that show that our approach meets or exceeds existing methods that do not incorporate data constraint rules.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"3 1","pages":"9-16"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82113357","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}
Drug-related adverse events pose substantial risks to patients who consume post-market or Drug-related adverse events pose substantial risks to patients who consume post-market or investigational drugs. Early detection of adverse events benefits not only the drug regulators, but also the manufacturers for pharmacovigilance. Existing methods rely on patients' "spontaneous" self-reports that attest problems. The increasing popularity of social media platforms like the Twitter presents us a new information source for finding potential adverse events. Given the high frequency of user updates, mining Twitter messages can lead us to real-time pharmacovigilance. In this paper, we describe an approach to find drug users and potential adverse events by analyzing the content of twitter messages utilizing Natural Language Processing (NLP) and to build Support Vector Machine (SVM) classifiers. Due to the size nature of the dataset (i.e., 2 billion Tweets), the experiments were conducted on a High Performance Computing (HPC) platform using MapReduce, which exhibits the trend of big data analytics. The results suggest that daily-life social networking data could help early detection of important patient safety issues.
{"title":"Towards Large-scale Twitter Mining for Drug-related Adverse Events.","authors":"Jiang Bian, Umit Topaloglu, Fan Yu","doi":"10.1145/2389707.2389713","DOIUrl":"https://doi.org/10.1145/2389707.2389713","url":null,"abstract":"<p><p>Drug-related adverse events pose substantial risks to patients who consume post-market or Drug-related adverse events pose substantial risks to patients who consume post-market or investigational drugs. Early detection of adverse events benefits not only the drug regulators, but also the manufacturers for pharmacovigilance. Existing methods rely on patients' \"spontaneous\" self-reports that attest problems. The increasing popularity of social media platforms like the Twitter presents us a new information source for finding potential adverse events. Given the high frequency of user updates, mining Twitter messages can lead us to real-time pharmacovigilance. In this paper, we describe an approach to find drug users and potential adverse events by analyzing the content of twitter messages utilizing Natural Language Processing (NLP) and to build Support Vector Machine (SVM) classifiers. Due to the size nature of the dataset (i.e., 2 billion Tweets), the experiments were conducted on a High Performance Computing (HPC) platform using MapReduce, which exhibits the trend of big data analytics. The results suggest that daily-life social networking data could help early detection of important patient safety issues.</p>","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"2012 ","pages":"25-32"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2389707.2389713","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35459545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Subramaniam, P. Chundi, A. Muthuraj, E. Margalit, Sylvie Sim
Retinal prostheses are used to restore vision to individuals with vision impairments caused by the damaged photoreceptors in their retina. Despite the early successes, designing prostheses that can restore functional vision in general, continues to be a challenging problem due to the large number of design parameters that need to be customized for individual users. Gathering data using real patients in a timely and safe manner is also difficult. To address these problems, a virtual environment for realistically and safely simulating prosthetic vision is described. Besides supporting phosphenized rendering of images at different resolutions to normal users, and eye movement tracking, the environment also supports spatial distortions that are commonly perceived by prostheses users. A procedure to automatically generate such spatial distortions is developed. User corrections if any, are logged and compared with the original distortion values to evaluate distortion perception. Experimental results obtained in using this environment to perform various visual acuity tasks are described.
{"title":"Simulating prosthetic vision with disortions for retinal prosthesis design","authors":"M. Subramaniam, P. Chundi, A. Muthuraj, E. Margalit, Sylvie Sim","doi":"10.1145/2389707.2389719","DOIUrl":"https://doi.org/10.1145/2389707.2389719","url":null,"abstract":"Retinal prostheses are used to restore vision to individuals with vision impairments caused by the damaged photoreceptors in their retina. Despite the early successes, designing prostheses that can restore functional vision in general, continues to be a challenging problem due to the large number of design parameters that need to be customized for individual users. Gathering data using real patients in a timely and safe manner is also difficult. To address these problems, a virtual environment for realistically and safely simulating prosthetic vision is described. Besides supporting phosphenized rendering of images at different resolutions to normal users, and eye movement tracking, the environment also supports spatial distortions that are commonly perceived by prostheses users. A procedure to automatically generate such spatial distortions is developed. User corrections if any, are logged and compared with the original distortion values to evaluate distortion perception. Experimental results obtained in using this environment to perform various visual acuity tasks are described.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"23 1","pages":"57-64"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76528536","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 increasing prevalence of electronic health records containing rich information about a patient's health and physical condition has the potential to transform research in health and medicine. In this work, we present a health record search system for finding patients matching certain inclusion criteria (specified as keyword queries) for clinical studies. In particular, our system aggregates multi-level evidence and combines proven statistical IR models, both in an innovative way, and achieves a 20% MAP (mean average precision) improvement over a strong baseline. Moreover, our cross-validation results show that the overall performance of our system is comparable to other top-performing systems on the same task.
{"title":"Combining multi-level evidence for medical record retrieval","authors":"Dongqing Zhu, Ben Carterette","doi":"10.1145/2389707.2389717","DOIUrl":"https://doi.org/10.1145/2389707.2389717","url":null,"abstract":"The increasing prevalence of electronic health records containing rich information about a patient's health and physical condition has the potential to transform research in health and medicine. In this work, we present a health record search system for finding patients matching certain inclusion criteria (specified as keyword queries) for clinical studies. In particular, our system aggregates multi-level evidence and combines proven statistical IR models, both in an innovative way, and achieves a 20% MAP (mean average precision) improvement over a strong baseline. Moreover, our cross-validation results show that the overall performance of our system is comparable to other top-performing systems on the same task.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"15 1","pages":"49-56"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91217491","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}
With the rapid proliferation of the Internet, traditional Information Retrieval (IR) techniques need to address challenges that stem from information overload by filtering web documents and ranking them in an order that can be perceived to be more relevant and credible to the end-user. In the domain of health care, an increasing number of people turn to the Internet for their health and wellness concerns. The results returned by traditional search engines can therefore be overwhelming and, even worse, inaccurate. As a consequence there is a need to design more "intelligent" web services that pre-process and alter information on the user's behalf. Specifically, this paper describes the design of a personalized search engine that utilizes patient data (either stored in user-managed personal health records or in provider-managed electronic medical records) and couples this with a selective crawling of credible medical information to eliminate search results that appear irrelevant to the user (given the user's "health profile") and rank the remaining results in order of relevance based on the health conditions of users performing the searches. Toward this end, a new ranking algorithm that combines a user's search query and the user's health profile is introduced. Finally, comparisons of the search results for users with different health profiles and diverse queries are presented using this architecture.
{"title":"An architecture for personalized health information retrieval","authors":"N. Yadav, C. Poellabauer","doi":"10.1145/2389707.2389716","DOIUrl":"https://doi.org/10.1145/2389707.2389716","url":null,"abstract":"With the rapid proliferation of the Internet, traditional Information Retrieval (IR) techniques need to address challenges that stem from information overload by filtering web documents and ranking them in an order that can be perceived to be more relevant and credible to the end-user. In the domain of health care, an increasing number of people turn to the Internet for their health and wellness concerns. The results returned by traditional search engines can therefore be overwhelming and, even worse, inaccurate. As a consequence there is a need to design more \"intelligent\" web services that pre-process and alter information on the user's behalf. Specifically, this paper describes the design of a personalized search engine that utilizes patient data (either stored in user-managed personal health records or in provider-managed electronic medical records) and couples this with a selective crawling of credible medical information to eliminate search results that appear irrelevant to the user (given the user's \"health profile\") and rank the remaining results in order of relevance based on the health conditions of users performing the searches. Toward this end, a new ranking algorithm that combines a user's search query and the user's health profile is introduced. Finally, comparisons of the search results for users with different health profiles and diverse queries are presented using this architecture.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"17 1","pages":"41-48"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79249320","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}
Riccardo Lora, Alberto Sabaini, Combi Carlo, U. Moretti
Pharmacovigilance is the activity related to the collection, analysis, and prevention of adverse reactions induced by drugs. The spontaneous reporting of adverse drug reactions is a system for identifying and sending reports about unexpected reactions to the regulatory authority. In Italy the information needed for properly carrying out the pharmacovigilance activities is scattered in different databases, which often contain the same information but encoded in different and temporally evolving ways. The data contained in the mentioned archives need to be integrated with information contained in other databases. In this paper we describe the construction of a data warehousing system, called VigiSegn, for the national center of pharmacovigilance; in particular, we focus on the data sources analysis and the design of the reconciled database. The (temporal) schema of reconciled data has been designed by using the TimeER conceptual data model.
{"title":"Designing the reconciled schema for a pharmacovigilance data warehouse through a temporally-enhanced ER model","authors":"Riccardo Lora, Alberto Sabaini, Combi Carlo, U. Moretti","doi":"10.1145/2389707.2389711","DOIUrl":"https://doi.org/10.1145/2389707.2389711","url":null,"abstract":"Pharmacovigilance is the activity related to the collection, analysis, and prevention of adverse reactions induced by drugs. The spontaneous reporting of adverse drug reactions is a system for identifying and sending reports about unexpected reactions to the regulatory authority. In Italy the information needed for properly carrying out the pharmacovigilance activities is scattered in different databases, which often contain the same information but encoded in different and temporally evolving ways. The data contained in the mentioned archives need to be integrated with information contained in other databases. In this paper we describe the construction of a data warehousing system, called VigiSegn, for the national center of pharmacovigilance; in particular, we focus on the data sources analysis and the design of the reconciled database. The (temporal) schema of reconciled data has been designed by using the TimeER conceptual data model.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"5 1","pages":"17-24"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87379846","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 knowledge management community has introduced a multitude of methods for knowledge discovery on large datasets. In the context of public health intelligence, we integrated and incorporated some of these methods into an analyst's workflow that proceeds from the data-centric descriptive level of analysis to the model-centric causal level of reasoning. We show several case studies of the proposed analyst's workflow as applied to the US Health Indicators Warehouse (HIW), which is a medium scale, public dataset regarding community health information as collected by the US federal government. In our case studies, we demonstrate a series of visual analytics efforts targeted at the HIW, including visual analysis according to correlation matrices, multivariate outlier analysis, multiple linear regression of Medicare costs, confirmatory factor analysis, and hybrid scatterplot and heatmap visualization for distributions of a group of health indicators. We conclude by sketching a preliminary framework for examining causal dependence hypotheses for future data science research in public health.
{"title":"Moving from descriptive to causal analytics: case study of discovering knowledge from us health indicators warehouse","authors":"J. Schryver, M. Shankar, Songhua Xu","doi":"10.1145/2389707.2389709","DOIUrl":"https://doi.org/10.1145/2389707.2389709","url":null,"abstract":"The knowledge management community has introduced a multitude of methods for knowledge discovery on large datasets. In the context of public health intelligence, we integrated and incorporated some of these methods into an analyst's workflow that proceeds from the data-centric descriptive level of analysis to the model-centric causal level of reasoning. We show several case studies of the proposed analyst's workflow as applied to the US Health Indicators Warehouse (HIW), which is a medium scale, public dataset regarding community health information as collected by the US federal government. In our case studies, we demonstrate a series of visual analytics efforts targeted at the HIW, including visual analysis according to correlation matrices, multivariate outlier analysis, multiple linear regression of Medicare costs, confirmatory factor analysis, and hybrid scatterplot and heatmap visualization for distributions of a group of health indicators. We conclude by sketching a preliminary framework for examining causal dependence hypotheses for future data science research in public health.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"8 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79091511","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}
Christopher C. Yang, Haodong Yang, Ling Jiang, Mi Zhang
Adverse Drug Reactions (ADRs) represent a serious problem all over the world. They may complicate a patient's medical conditions and increase the morbidity, even mortality. Drug safety currently depends heavily on post-marketing surveillance, because pre-marketing review process cannot identify all possible adverse drug reactions in that it is limited by scale and time span. However, current post-marketing surveillance is conducted through centralized volunteering reporting systems, and the reporting rate is low. Consequently, it is difficult to detect the adverse drug reactions signals in a timely manner. To solve this problem, many researchers have explored methods to detect ADRs in electronic health records. Nevertheless, we only have access to electronic health records form particular health units. Aggregating and integrating electronic health records from multiple sources is rather challenging. With the advance of Web 2.0 technologies and the popularity of social media, many health consumers are discussing and exchanging health-related information with their peers. Many of this online discussion involve adverse drug reactions. In this work, we propose to use association mining and Proportional Reporting Ratios to mine the associations between drugs and adverse reactions from the user contributed content in social media. We have conducted an experiment using ten drugs and five adverse drug reactions. The FDA alerts are used as the gold standard to test the performance of the proposed techniques. The result shows that the metrics leverage, lift, and PRR are all promising to detect the adverse drug reactions reported by FDA. However, PRR outperformed the other two metrics.
{"title":"Social media mining for drug safety signal detection","authors":"Christopher C. Yang, Haodong Yang, Ling Jiang, Mi Zhang","doi":"10.1145/2389707.2389714","DOIUrl":"https://doi.org/10.1145/2389707.2389714","url":null,"abstract":"Adverse Drug Reactions (ADRs) represent a serious problem all over the world. They may complicate a patient's medical conditions and increase the morbidity, even mortality. Drug safety currently depends heavily on post-marketing surveillance, because pre-marketing review process cannot identify all possible adverse drug reactions in that it is limited by scale and time span. However, current post-marketing surveillance is conducted through centralized volunteering reporting systems, and the reporting rate is low. Consequently, it is difficult to detect the adverse drug reactions signals in a timely manner. To solve this problem, many researchers have explored methods to detect ADRs in electronic health records. Nevertheless, we only have access to electronic health records form particular health units. Aggregating and integrating electronic health records from multiple sources is rather challenging. With the advance of Web 2.0 technologies and the popularity of social media, many health consumers are discussing and exchanging health-related information with their peers. Many of this online discussion involve adverse drug reactions. In this work, we propose to use association mining and Proportional Reporting Ratios to mine the associations between drugs and adverse reactions from the user contributed content in social media. We have conducted an experiment using ten drugs and five adverse drug reactions. The FDA alerts are used as the gold standard to test the performance of the proposed techniques. The result shows that the metrics leverage, lift, and PRR are all promising to detect the adverse drug reactions reported by FDA. However, PRR outperformed the other two metrics.","PeriodicalId":92138,"journal":{"name":"SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)","volume":"4 1","pages":"33-40"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74499237","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}
SHB'12 : proceedings of the 2012 ACM International Workshop on Smart Health and Wellbeing : October 29, 2012, Maui, Hawaii, USA. International Workshop on Smart Health and Wellbeing (2012 : Maui, Hawaii)
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：