Personal Health Records or Patient Portals (electronic records tethered to healthcare systems and allowing patient access), are recognised as a promising mechanism to support greater patient engagement, yet questions remain open about the best way to encourage adoption of patient portals and what factors might contribute to sustained and meaningful use. A review of the literature is ongoing, with qualitative data collection planned.
{"title":"Personal Health Records: Understanding the Factors that Contribute to Creating Value and Practical use by Patients and Citizens","authors":"Irina Osovskaya","doi":"10.1145/3079452.3079484","DOIUrl":"https://doi.org/10.1145/3079452.3079484","url":null,"abstract":"Personal Health Records or Patient Portals (electronic records tethered to healthcare systems and allowing patient access), are recognised as a promising mechanism to support greater patient engagement, yet questions remain open about the best way to encourage adoption of patient portals and what factors might contribute to sustained and meaningful use. A review of the literature is ongoing, with qualitative data collection planned.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123046584","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}
Health data anonymization is a hot topic, on which both the medical and the computer science communities have made a great effort to provide a safer and trustful way of sharing data among research centers and hospitals.The main challenge in data anonymization is to provide a proper trade off between the utility of the resulting data/models and protecting individual privacy.In this paper we present a real anonymization case, with particular emphasis on choices that have to be made to carry it on, and difficulties experienced using a data set with many dimensions, and not well distinguishable features. We present our approach for evaluating disclosure risks and methods for anonymising high-dimensional medical survey data and measuring the utility of the transformed data.
{"title":"A Case Study of Anonymization of Medical Surveys","authors":"Michele Gentili, S. Hajian, Carlos Castillo","doi":"10.1145/3079452.3079490","DOIUrl":"https://doi.org/10.1145/3079452.3079490","url":null,"abstract":"Health data anonymization is a hot topic, on which both the medical and the computer science communities have made a great effort to provide a safer and trustful way of sharing data among research centers and hospitals.The main challenge in data anonymization is to provide a proper trade off between the utility of the resulting data/models and protecting individual privacy.In this paper we present a real anonymization case, with particular emphasis on choices that have to be made to carry it on, and difficulties experienced using a data set with many dimensions, and not well distinguishable features. We present our approach for evaluating disclosure risks and methods for anonymising high-dimensional medical survey data and measuring the utility of the transformed data.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134528464","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}
Jun Deng, N. Cummins, Maximilian Schmitt, Kun Qian, F. Ringeval, Björn Schuller
Machine learning paradigms based on child vocalisations show great promise as an objective marker of developmental disorders such as Autism. In conventional detection systems, hand-crafted acoustic features are usually fed into a discriminative classifier (e.g, Support Vector Machines); however it is well known that the accuracy and robustness of such a system is limited by the size of the associated training data. This paper explores, for the first time, the use of feature representations learnt using a deep Generative Adversarial Network (GAN) for classifying children's speech affected by developmental disorders. A comparative evaluation of our proposed system with different acoustic feature sets is performed on the Child Pathological and Emotional Speech database. Key experimental results presented demonstrate that GAN based methods exhibit competitive performance with the conventional paradigms in terms of the unweighted average recall metric.
{"title":"Speech-based Diagnosis of Autism Spectrum Condition by Generative Adversarial Network Representations","authors":"Jun Deng, N. Cummins, Maximilian Schmitt, Kun Qian, F. Ringeval, Björn Schuller","doi":"10.1145/3079452.3079492","DOIUrl":"https://doi.org/10.1145/3079452.3079492","url":null,"abstract":"Machine learning paradigms based on child vocalisations show great promise as an objective marker of developmental disorders such as Autism. In conventional detection systems, hand-crafted acoustic features are usually fed into a discriminative classifier (e.g, Support Vector Machines); however it is well known that the accuracy and robustness of such a system is limited by the size of the associated training data. This paper explores, for the first time, the use of feature representations learnt using a deep Generative Adversarial Network (GAN) for classifying children's speech affected by developmental disorders. A comparative evaluation of our proposed system with different acoustic feature sets is performed on the Child Pathological and Emotional Speech database. Key experimental results presented demonstrate that GAN based methods exhibit competitive performance with the conventional paradigms in terms of the unweighted average recall metric.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133518125","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 biomedical literature constitutes a rich source of evidence to support the discovery of biomarkers. However, locating evidence in huge volumes of text can be difficult, as typical keyword queries cannot account for the meaning and structure of text. Text mining (TM) methods carry out automated semantic analysis of documents, to facilitate structured searching that can more precisely match users' information needs. We describe our TM approach to the detection of sentence-level associations between genes and diseases, as a first step towards developing a sophisticated search system targeted at locating biomarker evidence in the literature. We vary the sophistication of our detection methodology according to sentence complexity, using either co-occurring mentions of genes and diseases, or linguistic patterns obtained using evidence from approximately 1 million biomedical abstracts. We demonstrate that this method can detect associations more successfully than applying a single technique, with an accuracy that compares highly favourably to related efforts. We also show that the identified relations can complement those detected using alternative approaches.
{"title":"Extracting Gene-Disease Relations from Text to Support Biomarker Discovery","authors":"Paul Thompson, S. Ananiadou","doi":"10.1145/3079452.3079472","DOIUrl":"https://doi.org/10.1145/3079452.3079472","url":null,"abstract":"The biomedical literature constitutes a rich source of evidence to support the discovery of biomarkers. However, locating evidence in huge volumes of text can be difficult, as typical keyword queries cannot account for the meaning and structure of text. Text mining (TM) methods carry out automated semantic analysis of documents, to facilitate structured searching that can more precisely match users' information needs. We describe our TM approach to the detection of sentence-level associations between genes and diseases, as a first step towards developing a sophisticated search system targeted at locating biomarker evidence in the literature. We vary the sophistication of our detection methodology according to sentence complexity, using either co-occurring mentions of genes and diseases, or linguistic patterns obtained using evidence from approximately 1 million biomedical abstracts. We demonstrate that this method can detect associations more successfully than applying a single technique, with an accuracy that compares highly favourably to related efforts. We also show that the identified relations can complement those detected using alternative approaches.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"16 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114052260","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}
G. Ushaw, C. Sharp, Jess Hugill, Sheima Rafiq, C. Black, T. Casanova, K. Vancleef, J. Read, G. Morgan
Mass provision of healthcare through a digital medium can be greatly enhanced by the use of serious games. The accessibility and engagement provided by a serious game to the subject can significantly increase participation. The commercial games industry employs numerous techniques to analyse soft data collected from early users of an application to evolve the application itself and improve the experience of playing it. A game for mass stereoacuity testing of young children is used as a case study in this paper, to illustrate how soft feedback can be used to improve the effectiveness of a clinical trial. The key to the approach is identified as rapid incremental evolution of the application and trial protocol in a manner which increases the amount and usefulness of soft data collected, and reacts to issues identified in the soft data in a timely fashion. It is hoped that the approach can be adopted for a wide range of digital applications for mass health provision.
{"title":"Analysis of Soft Data for Mass Provision of Stereoacuity Testing Through a Serious Game for Health","authors":"G. Ushaw, C. Sharp, Jess Hugill, Sheima Rafiq, C. Black, T. Casanova, K. Vancleef, J. Read, G. Morgan","doi":"10.1145/3079452.3079496","DOIUrl":"https://doi.org/10.1145/3079452.3079496","url":null,"abstract":"Mass provision of healthcare through a digital medium can be greatly enhanced by the use of serious games. The accessibility and engagement provided by a serious game to the subject can significantly increase participation. The commercial games industry employs numerous techniques to analyse soft data collected from early users of an application to evolve the application itself and improve the experience of playing it. A game for mass stereoacuity testing of young children is used as a case study in this paper, to illustrate how soft feedback can be used to improve the effectiveness of a clinical trial. The key to the approach is identified as rapid incremental evolution of the application and trial protocol in a manner which increases the amount and usefulness of soft data collected, and reacts to issues identified in the soft data in a timely fashion. It is hoped that the approach can be adopted for a wide range of digital applications for mass health provision.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124655385","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}
Ashish Amresh, Annmarie A Lyles, L. Small, K. Gary
In this paper, we present the design and deployment of a mobile game titled "FitBit Garden" that encourages children to be physically active by representing the activity levels tracked via a FitBit pedometer in a garden ecosystem. The garden flourishes and grows as children and their parents take positive actions in the real world to improve the child's physical activity. These actions are then manifested into the virtual world via the mobile app. The paper presents the design of the intervention, the methods developed to collect and analyze data and the results of the usability study to determine form, function and acceptability of the intervention.
{"title":"FitBit Garden: A Mobile Game Designed to Increase Physical Activity in Children","authors":"Ashish Amresh, Annmarie A Lyles, L. Small, K. Gary","doi":"10.1145/3079452.3079457","DOIUrl":"https://doi.org/10.1145/3079452.3079457","url":null,"abstract":"In this paper, we present the design and deployment of a mobile game titled \"FitBit Garden\" that encourages children to be physically active by representing the activity levels tracked via a FitBit pedometer in a garden ecosystem. The garden flourishes and grows as children and their parents take positive actions in the real world to improve the child's physical activity. These actions are then manifested into the virtual world via the mobile app. The paper presents the design of the intervention, the methods developed to collect and analyze data and the results of the usability study to determine form, function and acceptability of the intervention.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114477788","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}
R. Fossion, Christopher R. Stephens, Karla P. García-Pelagio, Lorena García-Iglesias
Obesity is becoming a pandemic worldwide but the mechanisms that cause obesity are not well understood. One possibility are metabolic differences between lean and obese people, for which body temperature may offer a proxy which is relatively easy to measure. In the present contribution, we present results from two complementary methodological approaches to measure skin temperature as a function of body weight: in the first study temperature at the axilla and anthropometric measures were collected at a single time point in 1,073 male and female employees of all ages of the Universidad Nacional Autónoma de México (UNAM), whereas in the second study a 1-week continuous monitoring was realized of the skin temperature of the non-dominant wrist of 22 male young adults. In spite of the methodological differences, both studies indicate a higher mean temperature of the obese with respect to the lean subjects, possibly reflecting how obese people offset excess calorie intake by a higher heat transfer to the environment. On the other hand, with respect to the variance of the temperature over groups of underweight, normal weight, overweight and obese subjects, the first study that was realized in controlled circumstances did not detect any differences between groups, whereas the differences that were detected in the second study probably indicate behavioural differences between groups such as the level of physical activity.
肥胖正在成为一种世界性的流行病，但导致肥胖的机制还没有得到很好的理解。一种可能是瘦人和肥胖者之间的代谢差异，体温可能是一个相对容易测量的替代指标。在目前的贡献中，我们介绍了两种互补的方法方法来测量皮肤温度作为体重的函数的结果:在第一项研究中，研究人员在一个时间点收集了1073名不同年龄的国立大学Autónoma de msamxico (UNAM)的男女雇员的腋下温度和人体测量数据，而在第二项研究中，对22名年轻男性的非主手腕皮肤温度进行了为期一周的连续监测。尽管研究方法不同，但两项研究都表明，肥胖者的平均体温高于瘦子，这可能反映了肥胖者是如何通过向环境传递更高的热量来抵消多余的卡路里摄入的。另一方面，关于体重过轻、正常体重、超重和肥胖受试者组之间的温度差异，第一项研究是在受控环境下进行的，并没有发现组间的任何差异，而第二项研究中发现的差异可能表明了组间的行为差异，比如身体活动水平。
{"title":"Data Mining and Time-Series Analysis as Two Complementary Approaches to Study Body Temperature in Obesity","authors":"R. Fossion, Christopher R. Stephens, Karla P. García-Pelagio, Lorena García-Iglesias","doi":"10.1145/3079452.3079504","DOIUrl":"https://doi.org/10.1145/3079452.3079504","url":null,"abstract":"Obesity is becoming a pandemic worldwide but the mechanisms that cause obesity are not well understood. One possibility are metabolic differences between lean and obese people, for which body temperature may offer a proxy which is relatively easy to measure. In the present contribution, we present results from two complementary methodological approaches to measure skin temperature as a function of body weight: in the first study temperature at the axilla and anthropometric measures were collected at a single time point in 1,073 male and female employees of all ages of the Universidad Nacional Autónoma de México (UNAM), whereas in the second study a 1-week continuous monitoring was realized of the skin temperature of the non-dominant wrist of 22 male young adults. In spite of the methodological differences, both studies indicate a higher mean temperature of the obese with respect to the lean subjects, possibly reflecting how obese people offset excess calorie intake by a higher heat transfer to the environment. On the other hand, with respect to the variance of the temperature over groups of underweight, normal weight, overweight and obese subjects, the first study that was realized in controlled circumstances did not detect any differences between groups, whereas the differences that were detected in the second study probably indicate behavioural differences between groups such as the level of physical activity.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128416561","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}
In 2011 the term "Big Data" was introduced by Gartner [5], and since then its use in literature has ever increased, also in the (bio)medical research field [1]. Although the term Big Data is widely used, studies show that its meaning is much debated and many different definitions exist [10]. This variety of definitions may lead to different understandings and therefore difficulties in communication. For example, a researcher that is looking for "Big Data" solutions might miss an interesting method that is not tagged as such. In previous work we studied major topics that appear in Big Data literature using a Topic Modelling approach [8]. However, from that study it was not possible to know whether those topics are exclusive to publications self-identified as Big Data (BD), or not. Therefore, here we investigate the research question: What are the differences between topics in BD and non-Big Data (NBD) corpora?
{"title":"(Bio)medical Publications in the Age of Big Data: Yes, They Are Different","authors":"A. V. Altena, S. Olabarriaga","doi":"10.1145/3079452.3079474","DOIUrl":"https://doi.org/10.1145/3079452.3079474","url":null,"abstract":"In 2011 the term \"Big Data\" was introduced by Gartner [5], and since then its use in literature has ever increased, also in the (bio)medical research field [1]. Although the term Big Data is widely used, studies show that its meaning is much debated and many different definitions exist [10]. This variety of definitions may lead to different understandings and therefore difficulties in communication. For example, a researcher that is looking for \"Big Data\" solutions might miss an interesting method that is not tagged as such. In previous work we studied major topics that appear in Big Data literature using a Topic Modelling approach [8]. However, from that study it was not possible to know whether those topics are exclusive to publications self-identified as Big Data (BD), or not. Therefore, here we investigate the research question: What are the differences between topics in BD and non-Big Data (NBD) corpora?","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121400202","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}
In this work we present a portable system for nutrition logging that integrates multiple devices and modalities in order to facilitate food and drink tracking. The system consists of a smartphone, a smartwatch and a smartscale that can be combined flexibly by users depending on the current situation and their personal needs. Based on a requirement analysis, we present the rationale behind the design and implementation of our food and drink logger. We also report the preliminary results of an in-situ study we conducted in order to explore the potential benefits and challenges of a multi-device approach to nutrition tracking in daily life settings.
{"title":"Development of a Multi-Device Nutrition Logging Prototype Including a Smartscale","authors":"A. Seiderer, E. André","doi":"10.1145/3079452.3079486","DOIUrl":"https://doi.org/10.1145/3079452.3079486","url":null,"abstract":"In this work we present a portable system for nutrition logging that integrates multiple devices and modalities in order to facilitate food and drink tracking. The system consists of a smartphone, a smartwatch and a smartscale that can be combined flexibly by users depending on the current situation and their personal needs. Based on a requirement analysis, we present the rationale behind the design and implementation of our food and drink logger. We also report the preliminary results of an in-situ study we conducted in order to explore the potential benefits and challenges of a multi-device approach to nutrition tracking in daily life settings.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123475501","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}
K. Gary, R. Stoll, Pooja Rallabhandi, M. Patwardhan, Derek B. Hamel, Ashish Amresh, A. Pina, Kevin Cleary, Z. Quezado
Games may be employed for delivery of a clinical protocol, or as an incentive for protocol tasks. We focus on serious games in mHealth apps for pediatric patients with a chronic disease as an incentive for behavior modification. A patient is rewarded with enhanced gameplay in proportion to her/his compliance with a clinical protocol. The game-as-reward prevents fatigue and sustains patient engagement as the mHealth apps are used on a frequent basis when the affliction is a chronic disease. However, our experience shows a fine line between games that encourage engagement and ones that distract patients from protocol tasks.
{"title":"MHealth Games as Rewards: Incentive or Distraction?","authors":"K. Gary, R. Stoll, Pooja Rallabhandi, M. Patwardhan, Derek B. Hamel, Ashish Amresh, A. Pina, Kevin Cleary, Z. Quezado","doi":"10.1145/3079452.3079459","DOIUrl":"https://doi.org/10.1145/3079452.3079459","url":null,"abstract":"Games may be employed for delivery of a clinical protocol, or as an incentive for protocol tasks. We focus on serious games in mHealth apps for pediatric patients with a chronic disease as an incentive for behavior modification. A patient is rewarded with enhanced gameplay in proportion to her/his compliance with a clinical protocol. The game-as-reward prevents fatigue and sustains patient engagement as the mHealth apps are used on a frequent basis when the affliction is a chronic disease. However, our experience shows a fine line between games that encourage engagement and ones that distract patients from protocol tasks.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132556110","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：