Type 2 diabetes is one of the most serious chronic diseases which can be managed by medication and lifestyle changes. Regular physical activity is an example of lifestyle modification that can help in managing and preventing complications of the disease. However, a number of barriers to physical activity of different origin and type (e.g. health, personal, and psychological barriers) can prevent patients from achieving their goals. Various studies have attempted to categories the different barriers, but there is no unified model representing the different barriers and the possible interactions between them and the patient's activities. In this paper, we propose a conceptual model to identify and classify the barriers to physical activity for type 2 diabetes that is intended lay the foundations for the development of an ontology, i.e. a formal model of barriers and their relationships with diseases and patient's activities. The proposed model relies on identifying and classifying the barriers to physical activity according to their signs or factors, and reuses existing formal models of diabetes and other open source specialised resources.
{"title":"Towards an Ontology to Identify Barriers to Physical Activityfor Type 2 Diabetes","authors":"Yousef Alfaifi, F. Grasso, V. Tamma","doi":"10.1145/3079452.3079502","DOIUrl":"https://doi.org/10.1145/3079452.3079502","url":null,"abstract":"Type 2 diabetes is one of the most serious chronic diseases which can be managed by medication and lifestyle changes. Regular physical activity is an example of lifestyle modification that can help in managing and preventing complications of the disease. However, a number of barriers to physical activity of different origin and type (e.g. health, personal, and psychological barriers) can prevent patients from achieving their goals. Various studies have attempted to categories the different barriers, but there is no unified model representing the different barriers and the possible interactions between them and the patient's activities. In this paper, we propose a conceptual model to identify and classify the barriers to physical activity for type 2 diabetes that is intended lay the foundations for the development of an ontology, i.e. a formal model of barriers and their relationships with diseases and patient's activities. The proposed model relies on identifying and classifying the barriers to physical activity according to their signs or factors, and reuses existing formal models of diabetes and other open source specialised resources.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"295 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":"124280292","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}
Owen Noel Newton Fernando, Santosh Vijaykumar, R. W. Meurzec, T. Ngo, Karthikayen Jayasundar, Yohan Fernandopulle, V. Wanniarachchi
In 2008, an estimated 90,000 lives were lost to snake bites, with India being the most devastated [1]. Governments and health agencies spend time and money trying to curb this, but frequently fail because of the dynamic nature of snake threats. Snake Alert is a public health communication application, aiming to provide users assistance in reporting and being notified of snake sightings. First, prevention of snake encounters, by crowd pooling information on snake sightings based on geographical location. Next, the application allows users to upload photos of snakes upon each sighting, and with image recognition, and identifies the respective snake species. Lastly, the application provides onsite instructional self-treatment with specific advice based snake type. This application can be used to save lives, and provide accurate & dynamic information to people living in remote parts of the world.
{"title":"Snake Alert Application: A Snake Tracking & Reporting System","authors":"Owen Noel Newton Fernando, Santosh Vijaykumar, R. W. Meurzec, T. Ngo, Karthikayen Jayasundar, Yohan Fernandopulle, V. Wanniarachchi","doi":"10.1145/3079452.3079455","DOIUrl":"https://doi.org/10.1145/3079452.3079455","url":null,"abstract":"In 2008, an estimated 90,000 lives were lost to snake bites, with India being the most devastated [1]. Governments and health agencies spend time and money trying to curb this, but frequently fail because of the dynamic nature of snake threats. Snake Alert is a public health communication application, aiming to provide users assistance in reporting and being notified of snake sightings. First, prevention of snake encounters, by crowd pooling information on snake sightings based on geographical location. Next, the application allows users to upload photos of snakes upon each sighting, and with image recognition, and identifies the respective snake species. Lastly, the application provides onsite instructional self-treatment with specific advice based snake type. This application can be used to save lives, and provide accurate & dynamic information to people living in remote parts of the world.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"2 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":"116133625","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}
Assessing the impact of digital health projects and applications is a key challenge, especially in low resource settings. Full evaluative field studies are resource-intensive and time-consuming. Less demanding approaches that could provide rapid insights would be helpful. This paper presents some "short-cut" approaches for rapid assessments that can provide useful early indications of strengths and weaknesses and can ensure that evaluative efforts are focused on key uncertainties, are not wasted on unpromising interventions, and make the most of what is already known. Three rapid assessment approaches, all underpinned with logic modelling, are presented: Identification of "upstream" obstacles Utilisation of knowledge about "downstream" effects Fermi estimation Their application is illustrated by examples, mainly considering assessment of mobile phone healthcare information applications for citizens and healthcare workers in medium and low-resource settings.
{"title":"Rapid Methods to Assess the Potential Impact of Digital Health Interventions, and their Application to Low Resource Settings","authors":"G. Royston","doi":"10.1145/3079452.3079466","DOIUrl":"https://doi.org/10.1145/3079452.3079466","url":null,"abstract":"Assessing the impact of digital health projects and applications is a key challenge, especially in low resource settings. Full evaluative field studies are resource-intensive and time-consuming. Less demanding approaches that could provide rapid insights would be helpful. This paper presents some \"short-cut\" approaches for rapid assessments that can provide useful early indications of strengths and weaknesses and can ensure that evaluative efforts are focused on key uncertainties, are not wasted on unpromising interventions, and make the most of what is already known. Three rapid assessment approaches, all underpinned with logic modelling, are presented: Identification of \"upstream\" obstacles Utilisation of knowledge about \"downstream\" effects Fermi estimation Their application is illustrated by examples, mainly considering assessment of mobile phone healthcare information applications for citizens and healthcare workers in medium and low-resource settings.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"1 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":"123722665","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}
Mobile technology has become an increasingly popular source for female teenagers to seek sexual health information. However, it is not known what design features teenagers want in sexual health apps. Therefore, this research aimed to explore whether internet-based sexual health resources via websites and mobiles apps are meeting teenagers' sexual health needs and to explore for the first time teenagers' perceptions of the design features of sexual health mobile apps. Twenty-three female participants aged 13-16 years (M = 14.3, SD = 0.91) viewed either six existing sexual health websites or three existing sexual health mobile apps chosen to be representative of the range and variety currently available. Participants then took part in focus groups evaluating each of the websites and mobile apps. The findings indicate that teenagers currently use their phones to access sexual health information due to ease of access and privacy. However, teenagers were not aware of sexual health apps. Participants believed that apps should have similar design features to websites but apps should contain an interactive element paired with accurate sexual health information. At present, female teenagers are not using sexual health mobile apps, yet they believe they are more convenient and private compared to websites. Professionals' designing mobile apps should consider how best to market this resource appropriately to teenagers whilst ensuring that they contain both interactive features and accurate information.
{"title":"Exploring the Preferences of Female Teenagers when Seeking Sexual Health Information using Websites and Apps","authors":"K. McKellar, Elizabeth Sillence, Michaela A Smith","doi":"10.1145/3079452.3079497","DOIUrl":"https://doi.org/10.1145/3079452.3079497","url":null,"abstract":"Mobile technology has become an increasingly popular source for female teenagers to seek sexual health information. However, it is not known what design features teenagers want in sexual health apps. Therefore, this research aimed to explore whether internet-based sexual health resources via websites and mobiles apps are meeting teenagers' sexual health needs and to explore for the first time teenagers' perceptions of the design features of sexual health mobile apps. Twenty-three female participants aged 13-16 years (M = 14.3, SD = 0.91) viewed either six existing sexual health websites or three existing sexual health mobile apps chosen to be representative of the range and variety currently available. Participants then took part in focus groups evaluating each of the websites and mobile apps. The findings indicate that teenagers currently use their phones to access sexual health information due to ease of access and privacy. However, teenagers were not aware of sexual health apps. Participants believed that apps should have similar design features to websites but apps should contain an interactive element paired with accurate sexual health information. At present, female teenagers are not using sexual health mobile apps, yet they believe they are more convenient and private compared to websites. Professionals' designing mobile apps should consider how best to market this resource appropriately to teenagers whilst ensuring that they contain both interactive features and accurate information.","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":"131071739","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. Tsoi, Max W. Y. Lam, Felix C. H. Chan, H. W. Hirai, Baker K. K. Bat, Samuel Y. S. Wong, H. Meng
Background: Blood pressure variability (BPV) is associated with the cardiovascular disease. However, there is no standard risk stratification method to evaluate BPV. Our study aims to cluster BPV into three levels, namely, low, medium and high levels, by a machine learning approach. Methods: The Systolic Blood Pressure Intervention Trial (SPRINT) dataset, which includes patients with hypertension or at risk of cardiovascular diseases, was obtained from a clinical data sharing platform. In the clinical trial, participants with systolic blood pressure (SBP) of at least 130 mmHg and an increased cardiovascular risk were randomized to receive intensive treatment (targeting SBP below 120 mmHg) or standard treatment (targeting SBP below 140 mmHg), and blood pressure (BP) were measured and recorded during the follow-up periods. Visit-to-visit BPV was measured by the deviation between the observed records and the personalized BP trends, and two-dimensional clustering on SBP and diastolic BP were applied. Different curve fitting techniques (linear regression and cubic regression) and clustering methods (K-means and Agglomerative Clustering) were attempted and compared with each other. Results: With 8,092 participants and a median follow-up of 3.26 years, linear regression was a simple and reliable method to capture the BP trend. K-means model showed stable data clustering results. Intensive treatment showed to be effective for participants with a high level of BPV. Conclusion: Machine learning can be used for data clustering on BPV.
{"title":"Classification of Visit-to-Visit Blood Pressure Variability: A Machine Learning Approach for Data Clustering on Systolic Blood Pressure Intervention Trial (SPRINT)","authors":"K. Tsoi, Max W. Y. Lam, Felix C. H. Chan, H. W. Hirai, Baker K. K. Bat, Samuel Y. S. Wong, H. Meng","doi":"10.1145/3079452.3079454","DOIUrl":"https://doi.org/10.1145/3079452.3079454","url":null,"abstract":"Background: Blood pressure variability (BPV) is associated with the cardiovascular disease. However, there is no standard risk stratification method to evaluate BPV. Our study aims to cluster BPV into three levels, namely, low, medium and high levels, by a machine learning approach. Methods: The Systolic Blood Pressure Intervention Trial (SPRINT) dataset, which includes patients with hypertension or at risk of cardiovascular diseases, was obtained from a clinical data sharing platform. In the clinical trial, participants with systolic blood pressure (SBP) of at least 130 mmHg and an increased cardiovascular risk were randomized to receive intensive treatment (targeting SBP below 120 mmHg) or standard treatment (targeting SBP below 140 mmHg), and blood pressure (BP) were measured and recorded during the follow-up periods. Visit-to-visit BPV was measured by the deviation between the observed records and the personalized BP trends, and two-dimensional clustering on SBP and diastolic BP were applied. Different curve fitting techniques (linear regression and cubic regression) and clustering methods (K-means and Agglomerative Clustering) were attempted and compared with each other. Results: With 8,092 participants and a median follow-up of 3.26 years, linear regression was a simple and reliable method to capture the BP trend. K-means model showed stable data clustering results. Intensive treatment showed to be effective for participants with a high level of BPV. Conclusion: Machine learning can be used for data clustering on BPV.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"20 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":"132316716","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}
I consider my PhD as having 2 distinctive parts: A) to ascertain the quality of physical activity (PA) applications (apps) on the market in terms of safety, effectiveness, and user experience (Studies 1, 2); B) to assessthe efficacy of selected PA apps with potential, physically inactive, users (Studies 3, 4). I am finalising part A of the PhD and I am writing the protocols for part B. It would be valuable to gain the views of experts to make sure I am considering the topic from both behaviour change discipline and user experience research.
{"title":"The Public Health Potential of the Current Health Apps for Increasing Physical Activity","authors":"P. Bondaronek, E. Murray, F. Hamilton","doi":"10.1145/3079452.3079480","DOIUrl":"https://doi.org/10.1145/3079452.3079480","url":null,"abstract":"I consider my PhD as having 2 distinctive parts: A) to ascertain the quality of physical activity (PA) applications (apps) on the market in terms of safety, effectiveness, and user experience (Studies 1, 2); B) to assessthe efficacy of selected PA apps with potential, physically inactive, users (Studies 3, 4). I am finalising part A of the PhD and I am writing the protocols for part B. It would be valuable to gain the views of experts to make sure I am considering the topic from both behaviour change discipline and user experience research.","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":"125372738","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}
Hanna Schäfer, Santiago Hors-Fraile, Raghav Pavan Karumur, André Calero Valdez, A. Said, Helma Torkamaan, Tom Ulmer, C. Trattner
People increasingly use the Internet for obtaining information regarding diseases, diagnoses and available treatments. Currently, many online health portals already provide non-personalized health information in the form of articles. However, it can be challenging to find information relevant to one's condition, interpret this in context, and understand the medical terms and relationships. Recommender Systems (RS) already help these systems perform precise information filtering. In this short paper, we look one step ahead and show the progress made towards RS helping users find personalized, complex medical interventions or support them with preventive healthcare measures. We identify key challenges that need to be addressed for RS to offer the kind of decision support needed in high-risk domains like healthcare.
{"title":"Towards Health (Aware) Recommender Systems","authors":"Hanna Schäfer, Santiago Hors-Fraile, Raghav Pavan Karumur, André Calero Valdez, A. Said, Helma Torkamaan, Tom Ulmer, C. Trattner","doi":"10.1145/3079452.3079499","DOIUrl":"https://doi.org/10.1145/3079452.3079499","url":null,"abstract":"People increasingly use the Internet for obtaining information regarding diseases, diagnoses and available treatments. Currently, many online health portals already provide non-personalized health information in the form of articles. However, it can be challenging to find information relevant to one's condition, interpret this in context, and understand the medical terms and relationships. Recommender Systems (RS) already help these systems perform precise information filtering. In this short paper, we look one step ahead and show the progress made towards RS helping users find personalized, complex medical interventions or support them with preventive healthcare measures. We identify key challenges that need to be addressed for RS to offer the kind of decision support needed in high-risk domains like healthcare.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"18 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":"114139945","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 paper, we describe how people negotiate and communicate with healthcare professionals (HCPs) about information they have found online for the purposes of making health decisions. Drawing on 55 interviews with people using the Internet as part of their health decision-making we show how online information can be successfully integrated into decision-making leading to decision satisfaction and perceived positive outcomes. We describe what successful integration looks like as well as detail the ways in which integration of information can be disguised during negotiations with HCPs. Finally, we document what happens when integration fails, potentially valuable information resources are lost or the patient decides to bypass the HCP altogether. By exploring successful and unsuccessful integration examples we make three suggestions about how integration of online health information into HCP discussions around decision-making could be improved via (1) improved digital curation tools (2) providing communication scaffolding for the doctor-patient consultation and (3) harnessing the power of collective resources.
{"title":"(How) do People Negotiate Online Information into their Decision Making with Healthcare Professionals?","authors":"Lauren Bussey, Elizabeth Sillence","doi":"10.1145/3079452.3079495","DOIUrl":"https://doi.org/10.1145/3079452.3079495","url":null,"abstract":"In this paper, we describe how people negotiate and communicate with healthcare professionals (HCPs) about information they have found online for the purposes of making health decisions. Drawing on 55 interviews with people using the Internet as part of their health decision-making we show how online information can be successfully integrated into decision-making leading to decision satisfaction and perceived positive outcomes. We describe what successful integration looks like as well as detail the ways in which integration of information can be disguised during negotiations with HCPs. Finally, we document what happens when integration fails, potentially valuable information resources are lost or the patient decides to bypass the HCP altogether. By exploring successful and unsuccessful integration examples we make three suggestions about how integration of online health information into HCP discussions around decision-making could be improved via (1) improved digital curation tools (2) providing communication scaffolding for the doctor-patient consultation and (3) harnessing the power of collective resources.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"32 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":"125803338","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 outcomes in modern society are often shaped by peer interactions. Increasingly, a significant fraction of such interactions happen online and can have an impact on various mental health and behavioral health outcomes. Guided by appropriate social and psychological research, we conduct an observational study to understand the interactions between clinically depressed users and their ego-network when contrasted with a differential control group of normal users and their ego-network. Specifically, we examine if one can identify relevant linguistic and emotional signals from social media exchanges to detect symptomatic cues of depression. We observe significant deviations in the behavior of depressed users from the control group. Reduced and nocturnal online activity patterns, reduced active and passive network participation, increase in negative sentiment or emotion, distinct linguistic styles (e.g. self-focused pronoun usage), highly clustered and tightly-knit neighborhood structure, and little to no exchange of influence between depressed users and their ego-network over time are some of the observed characteristics. Based on our observations, we then describe an approach to extract relevant features and show that building a classifier to predict depression based on such features can achieve an F-score of 90%.
{"title":"Emotional and Linguistic Cues of Depression from Social Media","authors":"Nikhita Vedula, S. Parthasarathy","doi":"10.1145/3079452.3079465","DOIUrl":"https://doi.org/10.1145/3079452.3079465","url":null,"abstract":"Health outcomes in modern society are often shaped by peer interactions. Increasingly, a significant fraction of such interactions happen online and can have an impact on various mental health and behavioral health outcomes. Guided by appropriate social and psychological research, we conduct an observational study to understand the interactions between clinically depressed users and their ego-network when contrasted with a differential control group of normal users and their ego-network. Specifically, we examine if one can identify relevant linguistic and emotional signals from social media exchanges to detect symptomatic cues of depression. We observe significant deviations in the behavior of depressed users from the control group. Reduced and nocturnal online activity patterns, reduced active and passive network participation, increase in negative sentiment or emotion, distinct linguistic styles (e.g. self-focused pronoun usage), highly clustered and tightly-knit neighborhood structure, and little to no exchange of influence between depressed users and their ego-network over time are some of the observed characteristics. Based on our observations, we then describe an approach to extract relevant features and show that building a classifier to predict depression based on such features can achieve an F-score of 90%.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"12 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":"131278496","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}
Today, cancer patients and their caregivers often prefer to share the decision making process with their physicians and may be highly involved in the process of locating and choosing clinical trials for treatment. One issue is that treatments received on one trial may preclude participation in other trials because of eligibility requirements in the study design. We are developing a system to help patients and caregivers locate clinical trials, focusing on pediatric cancer where clinical trial participation is very high. We present a method by which conflicts - that is, the possibility that one or more interventions in one trial may cause a patient to not be eligible for another trial - can be determined in a group of clinical trials for Wilm's Tumor. More specifically, a conflict occurs when a drug or treatment mentioned in an intervention of one trial is also present in an eligibility criterion in another trial. We present results based on generating the conflicts in this group of trials, including the types of trials are most likely to cause conflicts. We also look at the specific treatments and drugs that cause conflicts, using the UMLS Metathesaurus concepts. The conflict generating algorithm will be used as part of the clinical trial search system, allowing patients to determine if a given trial will preclude him or her from other trials in the future.
{"title":"Conflict Discovery and Analysis for Clinical Trials","authors":"Bonnie K. MacKellar, Christina Schweikert","doi":"10.1145/3079452.3079494","DOIUrl":"https://doi.org/10.1145/3079452.3079494","url":null,"abstract":"Today, cancer patients and their caregivers often prefer to share the decision making process with their physicians and may be highly involved in the process of locating and choosing clinical trials for treatment. One issue is that treatments received on one trial may preclude participation in other trials because of eligibility requirements in the study design. We are developing a system to help patients and caregivers locate clinical trials, focusing on pediatric cancer where clinical trial participation is very high. We present a method by which conflicts - that is, the possibility that one or more interventions in one trial may cause a patient to not be eligible for another trial - can be determined in a group of clinical trials for Wilm's Tumor. More specifically, a conflict occurs when a drug or treatment mentioned in an intervention of one trial is also present in an eligibility criterion in another trial. We present results based on generating the conflicts in this group of trials, including the types of trials are most likely to cause conflicts. We also look at the specific treatments and drugs that cause conflicts, using the UMLS Metathesaurus concepts. The conflict generating algorithm will be used as part of the clinical trial search system, allowing patients to determine if a given trial will preclude him or her from other trials in the future.","PeriodicalId":245682,"journal":{"name":"Proceedings of the 2017 International Conference on Digital Health","volume":"14 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":"132189810","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：