2017 IEEE International Conference on Healthcare Informatics (ICHI)最新文献

{"title":"Catching Zika Fever: Application of Crowdsourcing and Machine Learning for Tracking Health Misinformation on Twitter","authors":"Amira Ghenai, Yelena Mejova","doi":"10.1109/ICHI.2017.58","DOIUrl":"https://doi.org/10.1109/ICHI.2017.58","url":null,"abstract":"In February 2016, World Health Organization declared the Zika outbreak a Public Health Emergency of International Concern. With developing evidence it can cause birth defects, and the Summer Olympics coming up in the worst affected country, Brazil, the virus caught fire on social media. In this work, we use Zika as a case study in building a tool for tracking the misinformation around health concerns on Twitter. We collect more than 13 million tweets regarding the Zika outbreak and track rumors outlined by the World Health Organization and Snopes fact checking website. The tool pipeline, which incorporates health professionals, crowdsourcing, and machine learning, allows us to capture health-related rumors around the world, as well as clarification campaigns by reputable health organizations. We discover an extremely bursty behavior of rumor-related topics, and show that, once the questionable topic is detected, it is possible to identify rumor-bearing tweets using automated techniques.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128186268","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":"Construction of Discharge Summaries Classifier","authors":"S. Tsumoto, Tomohiro Kimura, H. Iwata, S. Hirano","doi":"10.1109/ICCI-CC.2017.8109797","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2017.8109797","url":null,"abstract":"This paper proposes a method for construction of classifiers for discharge summaries. First, morphological analysis is applied to a set of summaries and a term matrix is generated. Second, correspond analysis is applied to the classification labels and the term matrixand generates two dimensional coordinates. By measuring thedistance between categories and the assigned points, ranking of key wordswill be generated. Then, keywords are selected as attributes according to the rank, andtraining example for classifiers will be generated. Finally learning methodsare applied to the training examples. Experimental validation shows that random forest achieved the best performance and the second best was the deep learner with a small difference, but decision tree methods with many keywords performed only a little worse than neural network or deep learning methods.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131082011","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":"Physiology-Aware Rural Ambulance Routing","authors":"Mohammad Hosseini, Richard B. Berlin, L. Sha","doi":"10.1109/ICHI.2017.27","DOIUrl":"https://doi.org/10.1109/ICHI.2017.27","url":null,"abstract":"The ultimate objective of medical cyber-physical systems is to enhance the effectiveness of patient care. During emergency patient transport from rural medical facility to center tertiary hospital, real-time monitoring of the patient in the ambulance by a physician expert at the tertiary center is crucial. The physician experts can provide vital assistance to the ambulance EMT personnel. While telemetry healthcare services using mobile networks may enable remote real-time monitoring of transported patients, physiologic measures and tracking are at least as important and requires the existence of high-fidelity communication coverage. However, the wireless networks along the roads especially in rural areas can range from 4G to low-speed 2G, some parts with communication breakage. From a patient care perspective, transport during critical illness can make route selection patient state dependent. Prompt decisions with the relative advantage of a longer more secure bandwidth route versus a shorter, more rapid transport route but with less secure bandwidth must be made. The trade-off between route selection and the quality of wireless communication is an important optimization problem which unfortunately has remained unaddressed by prior work.In this paper, we propose a novel physiology-aware route scheduling approach for emergency ambulance transport of rural patients with acute, high risk diseases in need of continuous remote monitoring. We mathematically model the problem into an NP-hard graph theory problem, and approximate a solution based on a trade-off between communication coverage and shortest path. We profile communication along two major routes in a large rural hospital settings in Illinois, and use the traces to manifest the concept. Further, we design our algorithms and run preliminary experiments for scalability analysis. We believe that our scheduling techniques can become a compelling aid that enables an always-connected remote monitoring system in emergency patient transfer scenarios aimed to prevent morbidity and mortality with early diagnosis and effective treatment.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"257 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115794118","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 Large-Scale Exploration of Factors Affecting Hand Hygiene Compliance Using Linear Predictive Models","authors":"Michael T. Lash, Jason Slater, P. Polgreen, Alberto Maria Segre","doi":"10.1109/ICHI.2017.12","DOIUrl":"https://doi.org/10.1109/ICHI.2017.12","url":null,"abstract":"This large-scale study, consisting of 24.5 million hand hygiene opportunities spanning 19 distinct facilities in 10 different states, uses linear predictive models to expose factors that may affect hand hygiene compliance. We examine the use of features such as temperature, relative humidity, influenza severity, day/night shift, federal holidays and the presence of new residents in predicting daily hand hygiene compliance. The results suggest that colder temperatures and federal holidays have an adverse effect on hand hygiene compliance rates, and that individual cultures and attitudes regarding hand hygiene exist among facilities.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121068646","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":"On Consolidated Predictive Model of the Natural History of Breast Cancer Considering Primary Tumor and Primary Distant Metastases Growth","authors":"E. Tyuryumina, A. Neznanov","doi":"10.1109/ICHI.2017.14","DOIUrl":"https://doi.org/10.1109/ICHI.2017.14","url":null,"abstract":"We propose a new mathematical growth model of primary tumor and primary metastases which may help to improve predicting accuracy of breast cancer process using an original mathematical model referred to CoM-IV and corresponding software. The CoM-IV model and predictive software: a) detect different growth periods of primary tumor and primary metastases; b) make forecast of patient survival; c) have higher average prediction accuracy than the other tools; d) can improve forecasts on survival of BC and facilitate optimisation of diagnostic tests. The CoM-IV enables us, for the first time, to predict the whole natural history of primary tumor and primary metastases growth on each stage (pT1, pT2, pT3, pT4) relying only on primary tumor sizes. Summarising: CoM-IV a) describes correctly primary tumor and primary distant metastases growth of IV (T1-4N0-3M1) stage with (N1-3) or without regional metastases in lymph nodes (N0); b) facilitates the understanding of the appearance period and manifestation of primary metastases.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129562336","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":"[Tutorials - 3 summaries]","authors":"Jianlin Shi, D. Mowery","doi":"10.1109/ichi.2017.104","DOIUrl":"https://doi.org/10.1109/ichi.2017.104","url":null,"abstract":"Summary form only given. The complete presentations were not made available for publication as part of the conference proceedings. Describes three tutorials associated with the conference meeting.","PeriodicalId":263611,"journal":{"name":"2017 IEEE International Conference on Healthcare Informatics (ICHI)","volume":"33 16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114055166","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}