Proceedings of the 2018 International Conference on Digital Health最新文献

{"title":"Talking to Ana: A Mobile Self-Anamnesis Application with Conversational User Interface","authors":"K. Denecke, S. Hochreutener, A. Pöpel, R. May","doi":"10.1145/3194658.3194670","DOIUrl":"https://doi.org/10.1145/3194658.3194670","url":null,"abstract":"Normally, a physician is collecting a patient's medical history under time pressure during the initial patient interview. This leads to incomplete, erroneous data with negative effects on treatment and patient safety. The objective of this work is to introduce a concept for a self-anamnesis realized as a mobile application for patients. We implement the concept for the concrete example of self-anamnesis in music therapy. For this purpose, requirements are collected in discussions with music therapists. A conversational user interface is chosen to simulate the patient-therapist conversation. The self-anamnesis application is equipped with 63 questions that are asked subsequently to the user. We have chosen a rule-based approach for realizing the chat conversation and used the Artificial Intelligence Markup Language (AIML) for encapsulating the questions and responses of the chatbot. In contrast to digital questionnaires, the application of a conversational user interface in the context of collecting information regarding a patient's medical history, provides several benefits: the user can be encouraged to complete all queries and can ask clarifying questions in case something is unclear.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133786089","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":"Eat & Tell: A Randomized Trial of Random-Loss Incentive to Increase Dietary Self-Tracking Compliance","authors":"Palakorn Achananuparp, Ee-Peng Lim, Vibhanshu Abhishek, Tianjiao Yun","doi":"10.1145/3194658.3194662","DOIUrl":"https://doi.org/10.1145/3194658.3194662","url":null,"abstract":"A growing body of evidence has shown that incorporating behavioral economics principles into the design of financial incentive programs helps improve their cost-effectiveness, promote individuals» short-term engagement, and increase compliance in health behavior interventions. Yet, their effects on long-term engagement have not been fully examined. In study designs where repeated administration of incentives is required to ensure the regularity of behaviors, the effectiveness of subsequent incentives may decrease as a result of the law of diminishing marginal utility. In this paper, we introduce random-loss incentive -- a new financial incentive based on loss aversion and unpredictability principles -- to address the problem of individuals» growing insensitivity to repeated interventions over time. We evaluate the new incentive design by conducting a randomized controlled trial to measure the influences of random losses on participants» dietary self-tracking and self-reporting compliance using a mobile web application called Eat & Tell. The results show that random losses are significantly more effective than fixed losses in encouraging long-term engagement.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132689245","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":"Inferring Visual Behaviour from User Interaction Data on a Medical Dashboard","authors":"Ainhoa Yera, J. Muguerza, O. Arbelaitz, I. Perona, R. Keers, D. Ashcroft, Richard Williams, N. Peek, C. Jay, Markel Vigo","doi":"10.1145/3194658.3194676","DOIUrl":"https://doi.org/10.1145/3194658.3194676","url":null,"abstract":"(its size and complexity) and its context of use. This results in user interfaces with a high-density of data that do not support optimal decision-making by clinicians. Anecdotal evidence indicates that clinicians demand the right amount of information to carry out their tasks. This suggests that adaptive user interfaces could be employed in order to cater for the information needs of the users and tackle information overload. Yet, since these information needs may vary, it is necessary first to identify and prioritise them, before implementing adaptations to the user interface. As gaze has long been known to be an indicator of interest, eye tracking allows us to unobtrusively observe where the users are looking, but it is not practical to use in a deployed system. Here, we address the question of whether we can infer visual behaviour on a medication safety dashboard through user interaction data. Our findings suggest that, there is indeed a relationship between the use of the mouse (in terms of clickstreams and mouse hovers) and visual behaviour in terms of cognitive load. We discuss the implications of this finding for the design of adaptive medical dashboards.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127639724","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":"MAVIE-Lab Sports: A mHealth for Injury Prevention and Risk Management in Sport","authors":"Madelyn Yiseth Rojas Castro, Marina Travanca, Marta Avalos Fernandez, D. Conesa, L. Orriols, E. Lagarde","doi":"10.1145/3194658.3194694","DOIUrl":"https://doi.org/10.1145/3194658.3194694","url":null,"abstract":"Smart-phones technology and the development of mHealth (Mobile Health) applications offer an opportunity to design intervention tools to influence health behavior changes. The MAVIE-Lab is a mHealth application including a DSS (Desicion Support System) to assist in the personalized evaluation of HLIs (Home, Leisure and Sport Injuries) risk and to promote the adoption of prevention measures. MAVIE-Lab Sports will be the first module of the mobile application. The purpose of this PhD project is to improve a particular module of MAVIE-Lab, devoted to sports (MAVIE-Lab Sports), in different aspects: statistical modeling, design and ergonomics. It also aims to evaluate system usability, acceptability, safety and efficacy. The development structure proposed and executed in this thesis will be replicated for the development of future modules for different types of HLIs. This document develops the argument, objectives and advances in the development of the MAVIE-Lab Sports and the future work.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131678688","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":"Towards Consistent Data Representation in the IoT Healthcare Landscape","authors":"Roberto Reda, F. Piccinini, A. Carbonaro","doi":"10.1145/3194658.3194668","DOIUrl":"https://doi.org/10.1145/3194658.3194668","url":null,"abstract":"Nowadays, the enormous volume of health and fitness data gathered from IoT wearable devices offers favourable opportunities to the research community. For instance, it can be exploited using sophisticated data analysis techniques, such as automatic reasoning, to find patterns and, extract information and new knowledge in order to enhance decision-making and deliver better healthcare. However, due to the high heterogeneity of data representation formats, the IoT healthcare landscape is characterised by an ubiquitous presence of data silos which prevents users and clinicians from obtaining a consistent representation of the whole knowledge. Semantic web technologies, such as ontologies and inference rules, have been shown as a promising way for the integration and exploitation of data from heterogeneous sources. In this paper, we present a semantic data model useful to: (1) consistently represent health and fitness data from heterogeneous IoT sources; (2) integrate and exchange them; and (3) enable automatic reasoning by inference engines.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114434742","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":"ML Approach for Early Detection of Sleep Apnea Treatment Abandonment: A Case Study","authors":"Matheus Araújo, Rahul Bhojwani, J. Srivastava, L. Kazaglis, C. Iber","doi":"10.1145/3194658.3194681","DOIUrl":"https://doi.org/10.1145/3194658.3194681","url":null,"abstract":"Sleep apnea is a growing problem in the country, with over 200,000 new cases being identified each year. Continuous positive airway pressure (CPAP) is the best treatment for obstructive sleep apnea (OSA), but is limited by low adherence to treatment. Fairview's Sleep program actively tracks CPAP usage and outcomes and employs tele-health coaching to improve adherence. This labor-intensive protocol is applied to those who are failing to meet early adherence targets. However, the implementation of this is based on heuristic rules which may not be matched to actual outcomes, contacting some patients too late and others unnecessarily. Machine learning can facilitate efficient contact strategies through early and accurate identification of therapy trajectories based on patient history, including EHR data, health information, questionnaires, and daily PAP metrics. Prediction models for classification of patients regarding CPAP adherence at a clinically-important time of 6 months of regular use were built. Using data from the first 30 days of CPAP usage, and a more aggressive decision scenario from the first 13 days of usage, the proposed approach results in an improvement in prediction significantly better than the current approach used by the hospital. Further, it is shown that a hospital can utilize this precise and earlier prediction by implementing appropriate actions based on the patient»s predicted risk level.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129306727","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":"ZIKA: A New System to Empower Health Workers and Local Communities to Improve Surveillance Protocols by E-learning and to Forecast Zika Virus in Real Time in Brazil","authors":"Juan D. Beltrán, A. Boscor, W. Santos, T. Massoni, P. Kostkova","doi":"10.1145/3194658.3194683","DOIUrl":"https://doi.org/10.1145/3194658.3194683","url":null,"abstract":"The devastating consequences of neonates infected with the Zika virus makes it necessary to fight and stop the spread of this virus and its vectors (Aedes mosquitoes). An essential part of the fight against mosquitoes is the use of mobile technology to support routine surveillance and risk assessment by community health workers (health agents). In addition, to improve early warning systems, the public health authorities need to forecast more accurately where an outbreak of the virus and its vector is likely to occur. The ZIKΛ system aims to develop a novel comprehensive framework that combines e-learning to empower health agents, community-based participatory surveillance, and forecasting of occurrences and distribution of the Zika virus and its vectors in real time. This system is currently being implemented in Brazil, in the cities of Campina Grande, Recife, Jaboatão dos Guararapes, and Olinda, the State of Pernambuco and Paraiba with the highest prevalence of the Zika virus disease. In this paper, we present the ZIKA system which helps health agents to learn new techniques and good practices to improve the surveillance of the virus and offer a real time distribution forecast of the virus and the vector. The forecast model is recalibrated in real time with information coming from health agents, governmental institutions, and weather stations to predict the areas with higher risk of a Zika virus outbreak in an interactive map. This mapping and alert system will help governmental institutions to make fast decisions and use their resources more efficiently to stop the spread of the Zika virus. The ZIKA app was developed and built in Ionic which allows for easy cross-platform rendering for both iOS and Android. The system presented in the current paper is one of the first systems combining public health surveillance, citizen-driven participatory reporting and weather data-based prediction. The implementation of the ZIKA system will reduce the devastating consequences of Zika virus in neonates and improve the life quality of vulnerable people in Brazil.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134103717","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":"Hearts and Politics: Metrics for Tracking Biorhythm Changes during Brexit and Trump","authors":"L. Aiello, D. Quercia, E. Roitmann","doi":"10.1145/3194658.3194678","DOIUrl":"https://doi.org/10.1145/3194658.3194678","url":null,"abstract":"Our internal experience of time reflects what is going in the world around us. Our body»s natural rhythms get disrupted for a variety of external factors, including exposure to collective events. We collect readings of steps, sleep, and heart rates from 11K users of health tracking devices in London and San Francisco. We introduce measures to quantify changes in not only volume of these three bio-signals (as previous research has done) but also synchronicity and periodicity, and we empirically assess how strong those variations are, compared to random expectation, during four major events: Christmas, New Year»s Eve, Brexit, and the US presidential election of 2016 (Donald Trump»s election). While Christmas and New Year»s eve are associated with short-term effects, Brexit and Trump»s election are associated with longer-term disruptions. Our results promise to inform the design of new ways of monitoring population health at scale.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122055062","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":"Information Sources and Needs in the Obesity and Diabetes Twitter Discourse","authors":"Yelena Mejova","doi":"10.1145/3194658.3194664","DOIUrl":"https://doi.org/10.1145/3194658.3194664","url":null,"abstract":"Obesity and diabetes epidemics are affecting about a third and tenth of US population, respectively, capturing the attention of the nation and its institutions. Social media provides an open forum for communication between individuals and health organizations, a forum which is easily joined by parties seeking to gain profit from it. In this paper we examine 1.5 million tweets mentioning obesity and diabetes in order to assess (1) the quality of information circulating in this conversation, as well as (2) the behavior and information needs of the users engaged in it. The analysis of top cited domains shows a strong presence of health information sources which are not affiliated with a governmental or academic institution at 41% in obesity and 50% diabetes samples, and that tweets containing these domains are retweeted more than those containing domains of reputable sources. On the user side, we estimate over a quarter of non-informational obesity discourse to contain fat-shaming -- a practice of humiliating and criticizing overweight individuals -- with some self-directed toward the writers themselves. We also find a great diversity in questions asked in these datasets, spanning definition of obesity as a disease, social norms, and governmental policies. Our results indicate a need for addressing the quality control of health information on social media, as well as a need to engage in a topically diverse, psychologically charged discourse around these diseases.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126105523","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":"Predicting Antimicrobial Drug Consumption using Web Search Data","authors":"N. Hansen, K. Mølbak, I. Cox, C. Lioma","doi":"10.1145/3194658.3194667","DOIUrl":"https://doi.org/10.1145/3194658.3194667","url":null,"abstract":"Consumption of antimicrobial drugs, such as antibiotics, is linked with antimicrobial resistance. Surveillance of antimicrobial drug consumption is therefore an important element in dealing with antimicrobial resistance. Many countries lack sufficient surveillance systems. Usage of web mined data therefore has the potential to improve current surveillance methods. To this end, we study how well antimicrobial drug consumption can be predicted based on web search queries, compared to historical purchase data of antimicrobial drugs. We present two prediction models (linear Elastic Net, and non-linear Gaussian Processes), which we train and evaluate on almost 6 years of weekly antimicrobial drug consumption data from Denmark and web search data from Google Health Trends. We present a novel method of selecting web search queries by considering diseases and drugs linked to antimicrobials, as well as professional and layman descriptions of antimicrobial drugs, all of which we mine from the open web. We find that predictions based on web search data are marginally more erroneous but overall on a par with predictions based on purchases of antimicrobial drugs. This marginal difference corresponds to ∠1% point mean absolute error in weekly usage. Best predictions are reported when combining both web search and purchase data. This study contributes a novel alternative solution to the real-life problem of predicting (and hence monitoring) antimicrobial drug consumption, which is particularly valuable in countries/states lacking centralised and timely surveillance systems.","PeriodicalId":216658,"journal":{"name":"Proceedings of the 2018 International Conference on Digital Health","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133612979","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}