Proceedings of the 1st International Conference on Medical and Health Informatics 2017最新文献

{"title":"Unsupervised Feature Learning for Gene Selection in Microarray Data Analysis","authors":"Xiucai Ye, T. Sakurai","doi":"10.1145/3107514.3107527","DOIUrl":"https://doi.org/10.1145/3107514.3107527","url":null,"abstract":"Feature selection has become one of the most important computational techniques in processing the analysis of high dimensional microarray data. In this paper, we propose a novel unsupervised feature selection method, which utilizes discriminant analysis and local regression to microarray data learning. During the learning of cluster labels, gene selection is performed simultaneously. By imposing row sparsity on the weight matrix, the proposed method optimizes for selecting the discriminative genes which are more informative and better capture the interesting natural clusters of samples. We evaluate the proposed method on real microarray gene expression datasets. The experimental results demonstrate that the proposed method not only achieves good performance, but also outperforms other state-of-the-art unsupervised feature selection methods.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131761170","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}

{"title":"Hearing Performance Testing Application","authors":"T. Wongsirichot, N. Elz, Napaporn Suwanmanee, Hassana Hmad-a-dam, Suthira Plansangket, Sukgamon Sukpisit","doi":"10.1145/3107514.3107516","DOIUrl":"https://doi.org/10.1145/3107514.3107516","url":null,"abstract":"To have a hearing test using an audiometer, patients have to go to a hospital to be examined and be tested by an audiologist in a soundproof room. In some cases, a test with an audiometer may not be convenient or cannot be performed because not all hospitals have an audiometer or an audiologist available. Recently, mobile devices such smartphones and tablets are widely used. Users are able to exchange information or install mobile applications via the Internet. Moreover, with the HTML5 cross-platform technology, developers can build cross-platform mobile applications that are able to operate on both iOS and Android operating systems using the same code. With the power of the Internet and the mentioned technology, this paper proposes a Hearing Performance Testing Application which is a cross-platform mobile application. This application is able to perform hearing tests for patients in the similar manner as an audiometer and provide testing results to a doctor or an audiologist via the Internet.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130861124","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}

{"title":"A Study of Implementing Artificial Neural Networks and Cluster Analysis to Distinguish Fatigue Type and Level in Graduate Students","authors":"Chen-Yuan Huang, Fang-Jung Chang, Yi-Chieh Lin, Cheng-Chih Huang, Chwen-Tzeng Su","doi":"10.1145/3107514.3107522","DOIUrl":"https://doi.org/10.1145/3107514.3107522","url":null,"abstract":"There are many causes of fatigue and the prevalence rate and key factors of fatigue differ according to population groups. Masters students in Taiwan are a high risk group for fatigue, and their lifestyle data was collected as the subject of the present study. Physiological parameters are measured using mobile devices, and the checklist individual strength (CIS) questionnaire and fatigue type checklist are utilized to explore the prevalence rate and type of fatigue in masters students. Cluster analysis was used to establish fatigue levels, and Pearson's correlation analysis was used to explore the correlation between different fatigue types and fatigue level. The results obtained from the CIS questionnaire showed a fatigue prevalence rate of 50%, with a Cronbach's alpha value of 0.885, indicating good internal consistency. Fatigue type was established using the fatigue type checklist and a neural network. Masters students who are fatigued with an active sympathetic nervous system accounted for 28.75% of the subjects, while 21.75% of the subjects were fatigued with an active parasympathetic nervous system, where the key factors are the number of exercise days and the number of steps taken. Cluster analysis was then used to separate the degree of fatigue into four levels. Fatigue scores between 111 and 140 are classified as extremely fatigued; between 77 and 110 as generally fatigued; between 48 and 76 as borderline fatigued; and between 20 and 47 as removed from fatigue. Different fatigue levels were found to have different key factors, and the results of the present study can help provide differentiated solutions for different levels of fatigue.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130872064","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}

{"title":"Reporting Verbs in Medical Research Articles","authors":"Richard H. Davis","doi":"10.1145/3107514.3107526","DOIUrl":"https://doi.org/10.1145/3107514.3107526","url":null,"abstract":"This study of reporting verbs in medical writing is based on a corpus of medical research articles published between 2001-2011, comprising 1,051,368 words (Davis 2015), The corpus holds 250 randomly selected medical articles, all peer-reviewed, located in PubMed, and open sourced. Analysis using WordSmith (Scott 2005) was conducted on all four of the Introduction-Methods-Results-Discussion (IMRD) sections, omitting title, abstract, figures, headings, captions, legends, acknowledgments, references, tables, and appendices. While important features, they were unlikely to include reporting verbs.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114343748","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}

{"title":"Usage Patterns and Data Quality: A Case Study of a National Type-1 Diabetes Study","authors":"Jinrong Wu, R. Sinnott, Jemie Effendy, S. Glöckner, William Hu, Jiajie Li","doi":"10.1145/3107514.3107518","DOIUrl":"https://doi.org/10.1145/3107514.3107518","url":null,"abstract":"The Environmental Determinants of Islet Auto- immunity (ENDIA) project is Australia's largest study into the causes of Type-1 Diabetes (T1D). The ENDIA study is supported by a Cloud-based software platform including a clinical registry comprising extensive longitudinal information on families at risk of having a child that might go on to develop T1D. This registry includes both demographic and clinical information on families and children as well as the environmental factors that might influence the onset of T1D. A multitude of samples are obtained through the study and used to support a diverse portfolio of bioinformatics data analytics. The quality of the data in the registry is essential to the overall success of the project. This paper presents a Cloud-based log-analytics platform that supports the detailed analysis of patterns of usage of the registry by the clinical centres and collaborators involved. We explore the impact that the usage patterns have on the overall data quality. We also consider ways of improving data quality by mothers entering their own data through targeted mobile applications that have been developed for dietary data collection.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126824403","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}

{"title":"Comparison of antioxidant activity of exopolysaccharides between Lactobacillus acidophilus La and Bifidobacterium adolescentis Ba in vitro","authors":"T. Lin, Yuh‐Shuen Chen","doi":"10.1145/3107514.3107531","DOIUrl":"https://doi.org/10.1145/3107514.3107531","url":null,"abstract":"In order to identify the relationship between antioxidant property of exopolysaccharide (EPS) and composition as well as concentration, the study compared the antioxidant activity of EPS between L. acidophilus La and B. adolescentis Ba in vitro. Firstly, the carbohydrate composition of LaP and BaP were quantified by high performance liquid chromatography (HPLC) equipped with a RI detector. The antioxidant activities of EPS estimated included DPPH radical-scavenging activity, linoleic acid peroxidation, ferrous ion chelating effects, and reducing power. The results revealed all the indications of antioxidant property of BaP were significantly stronger than that of LaP (P< 0.05). Moreover, the antioxidant property of BaP was positively correlated with the composition concentration including phenolic content of powerful antioxidant. Therefore, the comparison of composition and concentration of EPS not only could distinguish the antioxidant activity between LaP and BaP, but also made EPS acquire different functionality from composition and concentration. Thus, BaP with more antioxidant potential may merit the potential application of food additives and supplements to the health-promoting food industry.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126841457","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}

{"title":"Potentially Inappropriate Medication Prescription in Elderly Outpatients","authors":"Tzu-Chueh Wang, Hai-Lin Lu, D. Trezise, Fung Hung, J. Shieh, Kung-Chuan Hsu","doi":"10.1145/3107514.3107525","DOIUrl":"https://doi.org/10.1145/3107514.3107525","url":null,"abstract":"Potentially inappropriate medication (PIM) is defined as medication which may result in higher than expected risk when used by elderly patients. Its risk of occurrence may be increased through the effects of drug interactions, adverse drug reactions (ADR), adverse drug effects (ADE), and so on. At the commencement of this study, we hypothesized that: 1. After the release of a revised version of the Beers Criteria, the number of medications prescribed that are inappropriate under these guidelines would decline. 2. Polypharmacy would lead to increased potentially inappropriate use of medication. 3. More PIM would be prescribed at hospitals than at local clinics. To test these hypotheses, we analyzed prescriptions that had been issued by physicians at local hospitals and clinics and dispensed at a community pharmacy in Kaohsiung City, from 2009 to 2015. We found that the overall rate of prescription of PIM for elderly patients was 50.8% from 2009-2012, compared with 37.6% from 2013-2015. The largest number of prescriptions filled at the pharmacy was for the 'young-old', while the smallest number was for the 'oldest-old'. Prior to the introduction of the guidelines, the incidence of PIM was highest among the 'oldest-old', while after their introduction, PIM was highest among the 'aged'. In terms of prescribing institutions, physicians in hospitals were more likely to prescribe PIM than those in clinics. In terms of polypharmacy, inappropriate medications were most likely to be prescribed when ten or more medications were being used simultaneously. After the release of the guidelines, the rate of PIM among patients using ten kinds of medication or more exceeded that of those using one to four medications by a factor of six. This study involved only a retro-analysis of prescriptions dispensed at a community pharmacy. In the future, if pharmacists can discuss the appropriateness of prescriptions with physicians after medications have been prescribed, it is likely that the rate of PIM can be reduced, thus contributing to an improved quality of life for elderly patients.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134328807","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}

{"title":"Statins Use in Diabetes Patients as Primary Prevention and Low-Density Lipoprotein Cholesterol Levels","authors":"C. Sun","doi":"10.1145/3107514.3107520","DOIUrl":"https://doi.org/10.1145/3107514.3107520","url":null,"abstract":"Few data are available on the use of statins among the type 2 diabetes patients for primary prevention after publication of the American Diabetes Association guidelines in 2008. The American Diabetes Association (ADA) standards of care for diabetes state that statin therapy should be initiated in individuals with diabetes and other cardiovascular risk factors with a target LDL cholesterol of 100 mg/dl. This paper is to determine statin use in diabetes patients as primary prevention and its impact on low-density lipoprotein cholesterol (LDL-C) control among US individuals in year 2011-2012. In the research, diabetes patients were first identified among participants of the National Health and Nutrition Examination Survey (NHANES) 2011-2012. Patients were excluded if they had any cardiovascular events including congestive heart failure, heart failure, and stroke before as statin usually recommend for secondary prevention among these patients. Statin use was obtained from review of participants' drug containers. LDL-C control (yes) were defined was defined as <100 mg/dl. A logistic regression was conducted first to understand the characteristics associated with statin use as primary prevention among diabetes patients. A secondary logistic regression was done to examine the effect of statin on LDL-C control. Finally a linear regression model was used to look at the impact of statin on LDL-C as a continuous variable. Full Sample 2 Year Interview Weight (WTINT2YR) was applied for all the analysis. A total of 598 patients were identified and the weighted sample size was 17,387,156 for the data analysis. The conclusion comes out to be that statin use was associated with substantial improvements in LDL-C control in this study. Nevertheless, suboptimal statin use, especially among women and individuals with lower family income, prevented the maximal public health benefit from statin as a primary prevention among diabetes population.","PeriodicalId":214313,"journal":{"name":"Proceedings of the 1st International Conference on Medical and Health Informatics 2017","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132965433","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}