@Article{info:doi/10.2196/66616,
author="Kapitan, Daniel
and Heddema, Femke
and Dekker, Andr{\'e}
and Sieswerda, Melle
and Verhoeff, Bart-Jan
and Berg, Matt",
title="Data Interoperability in Context: The Importance of Open-Source Implementations When Choosing Open Standards",
journal="J Med Internet Res",
year="2025",
month="Apr",
day="15",
volume="27",
pages="e66616",
keywords="FHIR",
keywords="OMOP",
keywords="openEHR",
keywords="health care informatics",
keywords="information standards",
keywords="secondary use",
keywords="digital platform",
keywords="data sharing",
keywords="data interoperability",
keywords="open source implementations",
keywords="open standards",
keywords="Fast Health Interoperability Resources",
keywords="Observational Medical Outcomes Partnership",
keywords="clinical care",
keywords="data exchange",
keywords="longitudinal analysis",
keywords="low income",
keywords="middle-income",
keywords="LMIC",
keywords="low and middle-income countries",
keywords="developing countries",
keywords="developing nations",
keywords="health information exchange",
doi="10.2196/66616",
url="https://www.jmir.org/2025/1/e66616",
url="http://www.ncbi.nlm.nih.gov/pubmed/40232773"
}


@Article{info:doi/10.2196/52119,
author="Tighe, Carlos
and Ngongalah, Lem
and Sent{\'i}s, Alexis
and Orchard, Francisco
and Pacurar, Gheorghe-Aurel
and Hayes, Conor
and Hayes, S. Jessica
and Toader, Adrian
and Connolly, A. M{\'a}ire",
title="Building and Developing a Tool (PANDEM-2 Dashboard) to Strengthen Pandemic Management: Participatory Design Study",
journal="JMIR Public Health Surveill",
year="2025",
month="Mar",
day="5",
volume="11",
pages="e52119",
keywords="pandemic preparedness and response",
keywords="COVID-19",
keywords="cross-border collaboration",
keywords="surveillance",
keywords="data collection",
keywords="data standardization",
keywords="data sharing",
keywords="dashboard",
keywords="IT system",
keywords="IT tools",
abstract="Background: The COVID-19 pandemic exposed challenges in pandemic management, particularly in real-time data sharing and effective decision-making. Data protection concerns and the lack of data interoperability and standardization hindered the collection, analysis, and interpretation of critical information. Effective data visualization and customization are essential to facilitate decision-making. Objective: This study describes the development of the PANDEM-2 dashboard, a system providing a standardized and interactive platform for decision-making in pandemic management. It outlines the participatory approaches used to involve expert end users in its development and addresses key considerations of privacy, data protection, and ethical and social issues. Methods: Development was informed by a review of 25 publicly available COVID-19 dashboards, leading to the creation of a visualization catalog. User requirements were gathered through workshops and consultations with 20 experts from various health care and public health professions in 13 European Union countries. These were further refined by mapping variables and indicators required to fulfill the identified needs. Through a participatory design process, end users interacted with a preprototype platform, explored potential interface designs, and provided feedback to refine the system's components. Potential privacy, data protection, and ethical and social risks associated with the technology, along with mitigation strategies, were identified through an iterative impact assessment. Results: Key variables incorporated into the PANDEM-2 dashboard included case rates, number of deaths, mortality rates, hospital resources, hospital admissions, testing, contact tracing, and vaccination uptake. Cases, deaths, and vaccination uptake were prioritized as the most relevant and readily available variables. However, data gaps, particularly in contact tracing and mortality rates, highlighted the need for better data collection and reporting mechanisms. User feedback emphasized the importance of diverse data visualization formats combining different data types, as well as analyzing data across various time frames. Users also expressed interest in generating custom visualizations and reports, especially on the impact of government interventions. Participants noted challenges in data reporting, such as inconsistencies in reporting levels, time intervals, the need for standardization between member states, and General Data Protection Regulation concerns for data sharing. Identified risks included ethical concerns (accessibility, user autonomy, responsible use, transparency, and accountability), privacy and data protection (security and access controls and data reidentification), and social issues (unintentional bias, data quality and accuracy, dependency on technology, and collaborative development). Mitigation measures focused on designing user-friendly interfaces, implementing robust security protocols, and promoting cross-member state collaboration. Conclusions: The PANDEM-2 dashboard provides an adaptable, user-friendly platform for pandemic preparedness and response. Our findings highlight the critical role of data interoperability, cross-border collaboration, and custom IT tools in strengthening future health crisis management. They also offer valuable insights into the challenges and opportunities in developing IT solutions to support pandemic preparedness. ",
doi="10.2196/52119",
url="https://publichealth.jmir.org/2025/1/e52119",
url="http://www.ncbi.nlm.nih.gov/pubmed/40053759"
}


@Article{info:doi/10.2196/64069,
author="Liu, Yingxin
and Zhang, Jingyi
and Thabane, Lehana
and Bai, Xuerui
and Kang, Lili
and Lip, H. Gregory Y.
and Van Spall, C. Harriette G.
and Xia, Min
and Li, Guowei",
title="Data-Sharing Statements Requested from Clinical Trials by Public, Environmental, and Occupational Health Journals: Cross-Sectional Study",
journal="J Med Internet Res",
year="2025",
month="Feb",
day="7",
volume="27",
pages="e64069",
keywords="data sharing",
keywords="clinical trial",
keywords="public health",
keywords="International Committee of Medical Journal Editors",
keywords="ICMJE",
keywords="journal request",
keywords="clinical trials",
keywords="decision-making",
keywords="occupational health",
keywords="health informatics",
keywords="patient data",
abstract="Background: Data sharing plays a crucial role in health informatics, contributing to improving health information systems, enhancing operational efficiency, informing policy and decision-making, and advancing public health surveillance including disease tracking. Sharing individual participant data in public, environmental, and occupational health trials can help improve public trust and support by enhancing transparent reporting and reproducibility of research findings. The International Committee of Medical Journal Editors (ICMJE) requires all papers to include a data-sharing statement. However, it is unclear whether journals in the field of public, environmental, and occupational health adhere to this requirement. Objective: This study aims to investigate whether public, environmental, and occupational health journals requested data-sharing statements from clinical trials submitted for publication. Methods: In this bibliometric survey of ``Public, Environmental, and Occupational Health'' journals, defined by the Journal Citation Reports (as of June 2023), we included 202 journals with clinical trial reports published between 2019 and 2022. The primary outcome was a journal request for a data-sharing statement, as identified in the paper submission instructions. Multivariable logistic regression analysis was conducted to evaluate the relationship between journal characteristics and journal requests for data-sharing statements, with results presented as odds ratios (ORs) and corresponding 95\% CIs. We also investigated whether the journals included a data-sharing statement in their published trial reports. Results: Among the 202 public, environmental, and occupational health journals included, there were 68 (33.7\%) journals that did not request data-sharing statements. Factors significantly associated with journal requests for data-sharing statements included open access status (OR 0.43, 95\% CI 0.19-0.97), high journal impact factor (OR 2.31, 95\% CI 1.15-4.78), endorsement of Consolidated Standards of Reporting Trials (OR 2.43, 95\% CI 1.25-4.79), and publication in the United Kingdom (OR 7.18, 95\% CI 2.61-23.4). Among the 134 journals requesting data-sharing statements, 26.9\% (36/134) did not have statements in their published trial reports. Conclusions: Over one-third of the public, environmental, and occupational health journals did not request data-sharing statements in clinical trial reports. Among those journals that requested data-sharing statements in their submission guidance pages, more than one quarter published trial reports with no data-sharing statements. These results revealed an inadequate practice of requesting data-sharing statements by public, environmental, and occupational health journals, requiring more effort at the journal level to implement ICJME recommendations on data-sharing statements. ",
doi="10.2196/64069",
url="https://www.jmir.org/2025/1/e64069"
}


@Article{info:doi/10.2196/65658,
author="Ennis, Edel
and Bond, Raymond
and Mulvenna, Maurice
and Sweeney, Colm",
title="Understanding Individual Differences in Happiness Sources and Implications for Health Technology Design: Exploratory Analysis of an Open Dataset",
journal="JMIR Form Res",
year="2025",
month="Jan",
day="29",
volume="9",
pages="e65658",
keywords="happiness",
keywords="sexes",
keywords="age",
keywords="marital status",
keywords="parents",
keywords="affections",
keywords="achievements",
keywords="datasets",
keywords="digital health",
keywords="well-being",
keywords="mental health",
keywords="digital mental health interventions",
keywords="regression analyses",
keywords="evidence based",
abstract="Background: Psychologists have developed frameworks to understand many constructs, which have subsequently informed the design of digital mental health interventions (DMHIs) aimed at improving mental health outcomes. The science of happiness is one such domain that holds significant applied importance due to its links to well-being and evidence that happiness can be cultivated through interventions. However, as with many constructs, the unique ways in which individuals experience happiness present major challenges for designing personalized DMHIs. Objective: This paper aims to (1) present an analysis of how sex may interact with age, marital status, and parental status to predict individual differences in sources of happiness, and (2) to present a preliminary discussion of how open datasets may contribute to the process of designing health-related technology innovations. Methods: The HappyDB is an open database of 100,535 statements of what people consider to have made them happy, with some people asking to consider the past 24 hours (49,831 statements) and some considering the last 3 months (50,704 statements). Demographic information is also provided. Binary logistic regression analyses are used to determine whether various groups differed in their likelihood of selecting or not selecting a category as a source of their happiness. Results: Sex and age interacted to influence what was selected as sources of happiness, with patterns being less consistent among female individuals in comparison with male individuals. For marital status, differences in sources of happiness were predominantly between married individuals and those who are divorced or separated, but these were the same for both sexes. Married, single, and widowed individuals were all largely similar in their likelihood of selecting each of the categories as a source of their happiness. However, there were some anomalies, and sex appeared to be important in these anomalies. Sex and parental status also interacted to influence what was selected as sources of happiness. Conclusions: Sex interacts with age, marital status, and parental status in the likelihood of reporting affection, bonding, leisure, achievement, or enjoying the moment as sources of happiness. The contribution of an open dataset to understanding individual differences in sources of happiness is discussed in terms of its potential role in addressing the challenges of designing DMHIs that are ethical, responsible, evidence based, acceptable, engaging, inclusive, and effective for users. The discussion considers how the content design of DMHIs in general may benefit from exploring new methods informed by diverse data sources. It is proposed that examining the extent to which insights from nondigital settings can inform requirements gathering for DMHIs is warranted. ",
doi="10.2196/65658",
url="https://formative.jmir.org/2025/1/e65658"
}


@Article{info:doi/10.2196/50235,
author="Jefferson, Emily
and Milligan, Gordon
and Johnston, Jenny
and Mumtaz, Shahzad
and Cole, Christian
and Best, Joseph
and Giles, Charles Thomas
and Cox, Samuel
and Masood, Erum
and Horban, Scott
and Urwin, Esmond
and Beggs, Jillian
and Chuter, Antony
and Reilly, Gerry
and Morris, Andrew
and Seymour, David
and Hopkins, Susan
and Sheikh, Aziz
and Quinlan, Philip",
title="The Challenges and Lessons Learned Building a New UK Infrastructure for Finding and Accessing Population-Wide COVID-19 Data for Research and Public Health Analysis: The CO-CONNECT Project",
journal="J Med Internet Res",
year="2024",
month="Nov",
day="20",
volume="26",
pages="e50235",
keywords="COVID-19",
keywords="infrastructure",
keywords="trusted research environments",
keywords="safe havens",
keywords="feasibility analysis",
keywords="cohort discovery",
keywords="federated analytics",
keywords="federated discovery",
keywords="lessons learned",
keywords="population wide",
keywords="data",
keywords="public health",
keywords="analysis",
keywords="CO-CONNECT",
keywords="challenges",
keywords="data transformation",
doi="10.2196/50235",
url="https://www.jmir.org/2024/1/e50235"
}


@Article{info:doi/10.2196/57754,
author="Liu, Shuimei
and Guo, Raymond L.",
title="Data Ownership in the AI-Powered Integrative Health Care Landscape",
journal="JMIR Med Inform",
year="2024",
month="Nov",
day="19",
volume="12",
pages="e57754",
keywords="data ownership",
keywords="integrative healthcare",
keywords="artificial intelligence",
keywords="AI",
keywords="ownership",
keywords="data science",
keywords="governance",
keywords="consent",
keywords="privacy",
keywords="security",
keywords="access",
keywords="model",
keywords="framework",
keywords="transparency",
doi="10.2196/57754",
url="https://medinform.jmir.org/2024/1/e57754"
}


@Article{info:doi/10.2196/58116,
author="Mayito, Jonathan
and Tumwine, Conrad
and Galiwango, Ronald
and Nuwamanya, Elly
and Nakasendwa, Suzan
and Hope, Mackline
and Kiggundu, Reuben
and Byonanebye, M. Dathan
and Dhikusooka, Flavia
and Twemanye, Vivian
and Kambugu, Andrew
and Kakooza, Francis",
title="Combating Antimicrobial Resistance Through a Data-Driven Approach to Optimize Antibiotic Use and Improve Patient Outcomes: Protocol for a Mixed Methods Study",
journal="JMIR Res Protoc",
year="2024",
month="Nov",
day="8",
volume="13",
pages="e58116",
keywords="antimicrobial resistance",
keywords="AMR database",
keywords="AMR",
keywords="machine learning",
keywords="antimicrobial use",
keywords="artificial intelligence",
keywords="antimicrobial",
keywords="data-driven",
keywords="mixed-method",
keywords="patient outcome",
keywords="drug-resistant infections",
keywords="drug resistant",
keywords="surveillance data",
keywords="economic",
keywords="antibiotic",
abstract="Background: It is projected that drug-resistant infections will lead to 10 million deaths annually by 2050 if left unabated. Despite this threat, surveillance data from resource-limited settings are scarce and often lack antimicrobial resistance (AMR)--related clinical outcomes and economic burden. We aim to build an AMR and antimicrobial use (AMU) data warehouse, describe the trends of resistance and antibiotic use, determine the economic burden of AMR in Uganda, and develop a machine learning algorithm to predict AMR-related clinical outcomes. Objective: The overall objective of the study is to use data-driven approaches to optimize antibiotic use and combat antimicrobial-resistant infections in Uganda. We aim to (1) build a dynamic AMR and antimicrobial use and consumption (AMUC) data warehouse to support research in AMR and AMUC to inform AMR-related interventions and public health policy, (2) evaluate the trends in AMR and antibiotic use based on annual antibiotic and point prevalence survey data collected at 9 regional referral hospitals over a 5-year period, (3) develop a machine learning model to predict the clinical outcomes of patients with bacterial infectious syndromes due to drug-resistant pathogens, and (4) estimate the annual economic burden of AMR in Uganda using the cost-of-illness approach. Methods: We will conduct a study involving data curation, machine learning--based modeling, and cost-of-illness analysis using AMR and AMU data abstracted from procurement, human resources, and clinical records of patients with bacterial infectious syndromes at 9 regional referral hospitals in Uganda collected between 2018 and 2026. We will use data curation procedures, FLAIR (Findable, Linkable, Accessible, Interactable and Repeatable) principles, and role-based access control to build a robust and dynamic AMR and AMU data warehouse. We will also apply machine learning algorithms to model AMR-related clinical outcomes, advanced statistical analysis to study AMR and AMU trends, and cost-of-illness analysis to determine the AMR-related economic burden. Results: The study received funding from the Wellcome Trust through the Centers for Antimicrobial Optimisation Network (CAMO-Net) in April 2023. As of October 28, 2024, we completed data warehouse development, which is now under testing; completed data curation of the historical Fleming Fund surveillance data (2020-2023); and collected retrospective AMR records for 599 patients that contained clinical outcomes and cost-of-illness economic burden data across 9 surveillance sites for objectives 3 and 4, respectively. Conclusions: The data warehouse will promote access to rich and interlinked AMR and AMU data sets to answer AMR program and research questions using a wide evidence base. The AMR-related clinical outcomes model and cost data will facilitate improvement in the clinical management of AMR patients and guide resource allocation to support AMR surveillance and interventions. International Registered Report Identifier (IRRID): PRR1-10.2196/58116 ",
doi="10.2196/58116",
url="https://www.researchprotocols.org/2024/1/e58116"
}


@Article{info:doi/10.2196/44492,
author="Kumar, Ashutosh
and Asghar, Adil
and Raza, Khursheed
and Narayan, K. Ravi
and Jha, K. Rakesh
and Satyam, Abhigyan
and Kumar, Gopichand
and Dwivedi, Prakhar
and Sahni, Chetan
and Kumari, Chiman
and Kulandhasamy, Maheswari
and Motwani, Rohini
and Kaur, Gurjot
and Krishna, Hare
and Kumar, Sujeet
and Sesham, Kishore
and Pandey, N. Sada
and Parashar, Rakesh
and Kant, Kamla",
title="Shift in Demographic Involvement and Clinical Characteristics of COVID-19 From Wild-Type SARS-CoV-2 to the Delta Variant in the Indian Population: In Silico Analysis",
journal="Interact J Med Res",
year="2024",
month="Oct",
day="8",
volume="13",
pages="e44492",
keywords="SARS-CoV-2",
keywords="COVID-19",
keywords="epidemiology",
keywords="demographic shift",
keywords="severity of illness",
keywords="variant",
keywords="virus",
keywords="pandemic",
keywords="population studies",
keywords="genomic analysis",
abstract="Background: The Delta variant (B.1.617.2) was considered the most dangerous SARS-CoV-2 strain; however, in-depth studies on its impact based on demographic and clinical characteristics of COVID-19 are scarce. Objective: We aimed to investigate the shift in demographic and clinical characteristics of the COVID-19 pandemic with the emergence of the SARS-CoV-2 Delta variant compared with the wild-type (WT) strain (B.1). Methods: A cross-sectional study of COVID-19 cases in the Indian population caused by the WT strain (B.1) and Delta variant of SARS-CoV-2 was performed. The viral genomic sequence metadata containing demographic, vaccination, and patient status details (N=9500, NDelta=6238, NWT=3262) were statistically analyzed. Results: With the Delta variant, in comparison with the WT strain, a higher proportion of young individuals (<20 years) were infected (0-9 years: Delta: 281/6238, 4.5\% vs B.1: 75/3262, 2.3\%; 10-19 years: Delta: 562/6238, 9\% vs B.1: 229/3262, 7\%; P<.001). The proportion of women contracting infection increased (Delta: 2557/6238, 41\% vs B.1: 1174/3262, 36\%; P<.001). However, it decreased for men (Delta: 3681/6238, 59\% vs B.1: 2088/3262, 64\%; P<.001). An increased proportion of the young population developed symptomatic illness and were hospitalized (Delta: 27/262, 10.3\% vs B.1: 5/130, 3.8\%; P=.02). Moreover, an increased proportion of the women (albeit not men) from the young (Delta: 37/262, 14.1\% vs B.1: 4/130, 3.1\%; P<.001) and adult (Delta: 197/262, 75.2\% vs B.1: 72/130, 55.4\%; P<.001) groups developed symptomatic illness and were hospitalized. The mean age of men and women who contracted infection (Delta: men=37.9, SD 17.2 years; women=36.6, SD 17.6 years; P<.001; B.1: men=39.6, SD 16.9 years; women=40.1, SD 17.4 years; P<.001) as well as developing symptoms or being hospitalized (Delta: men=39.6, SD 17.4 years; women=35.6, SD 16.9 years, P<.001; B.1: men=47, SD 18 years; women=49.5, SD 20.9 years, P<.001) were considerably lower with the Delta variant than the B.1 strain. The total mortality was about 1.8 times higher with the Delta variant than with the WT strain. With the Delta variant, compared with B.1, mortality decreased for men (Delta: 58/85, 68\% vs B.1: 15/20, 75\%; P<.001); in contrast, it increased for women (Delta: 27/85, 32\% vs B.1: 5/20, 25\%; P<.001). The odds of death increased with age, irrespective of sex (odds ratio 3.034, 95\% CI 1.7-5.2, P<.001). Frequent postvaccination infections (24/6238) occurred with the Delta variant following complete doses. Conclusions: The increased involvement of young people and women, the lower mean age for illness, higher mortality, and frequent postvaccination infections were significant epidemiological concerns with the Delta variant. ",
doi="10.2196/44492",
url="https://www.i-jmr.org/2024/1/e44492"
}


@Article{info:doi/10.2196/51563,
author="Gundler, Christopher
and Gottfried, Karl
and Wiederhold, Johannes Alexander
and Ataian, Maximilian
and Wurlitzer, Marcus
and Gewehr, Erik Jan
and {\"U}ckert, Frank",
title="Unlocking the Potential of Secondary Data for Public Health Research: Retrospective Study With a Novel Clinical Platform",
journal="Interact J Med Res",
year="2024",
month="Oct",
day="1",
volume="13",
pages="e51563",
keywords="secondary use",
keywords="hypothesis testing",
keywords="research platform",
keywords="clinical data",
keywords="Parkinson disease",
keywords="data",
keywords="health-related research",
keywords="health data",
keywords="electronic health record",
keywords="EHR",
keywords="tremor",
abstract="Background: Clinical routine data derived from university hospitals hold immense value for health-related research on large cohorts. However, using secondary data for hypothesis testing necessitates adherence to scientific, legal (such as the General Data Protection Regulation, federal and state protection legislations), technical, and administrative requirements. This process is intricate, time-consuming, and susceptible to errors. Objective: This study aims to develop a platform that enables clinicians to use current real-world data for testing research and evaluate advantages and limitations at a large university medical center (542,944 patients in 2022). Methods: We identified requirements from clinical practitioners, conceptualized and implemented a platform based on the existing components, and assessed its applicability in clinical reality quantitatively and qualitatively. Results: The proposed platform was established at the University Medical Center Hamburg-Eppendorf and made 639 forms encompassing 10,629 data elements accessible to all resident scientists and clinicians. Every day, the number of patients rises, and parts of their electronic health records are made accessible through the platform. Qualitatively, we were able to conduct a retrospective analysis of Parkinson disease over 777 patients, where we provide additional evidence for a significantly higher proportion of action tremors in patients with rest tremors (340/777, 43.8\%) compared with those without rest tremors (255/777, 32.8\%), as determined by a chi-square test (P<.001). Quantitatively, our findings demonstrate increased user engagement within the last 90 days, underscoring clinicians' increasing adoption of the platform in their regular research activities. Notably, the platform facilitated the retrieval of clinical data from 600,000 patients, emphasizing its substantial added value. Conclusions: This study demonstrates the feasibility of simplifying the use of clinical data to enhance exploration and sustainability in scientific research. The proposed platform emerges as a potential technological and legal framework for other medical centers, providing them with the means to unlock untapped potential within their routine data. ",
doi="10.2196/51563",
url="https://www.i-jmr.org/2024/1/e51563"
}


@Article{info:doi/10.2196/52120,
author="Victoria-Castro, Maria Angela
and Arora, Tanima
and Simonov, Michael
and Biswas, Aditya
and Alausa, Jameel
and Subair, Labeebah
and Gerber, Brett
and Nguyen, Andrew
and Hsiao, Allen
and Hintz, Richard
and Yamamoto, Yu
and Soufer, Robert
and Desir, Gary
and Wilson, Perry Francis
and Villanueva, Merceditas",
title="Promoting Collaborative Scholarship During the COVID-19 Pandemic Through an Innovative COVID-19 Data Explorer and Repository at Yale School of Medicine: Development and Usability Study",
journal="JMIR Form Res",
year="2024",
month="Sep",
day="3",
volume="8",
pages="e52120",
keywords="COVID-19",
keywords="database",
keywords="data access",
keywords="interdepartmental communication",
keywords="collaborative scholarship",
keywords="clinical data",
keywords="repository",
keywords="researchers",
keywords="large-scale database",
keywords="innovation",
abstract="Background: The COVID-19 pandemic sparked a surge of research publications spanning epidemiology, basic science, and clinical science. Thanks to the digital revolution, large data sets are now accessible, which also enables real-time epidemic tracking. However, despite this, academic faculty and their trainees have been struggling to access comprehensive clinical data. To tackle this issue, we have devised a clinical data repository that streamlines research processes and promotes interdisciplinary collaboration. Objective: This study aimed to present an easily accessible up-to-date database that promotes access to local COVID-19 clinical data, thereby increasing efficiency, streamlining, and democratizing the research enterprise. By providing a robust database, a broad range of researchers (faculty and trainees) and clinicians from different areas of medicine are encouraged to explore and collaborate on novel clinically relevant research questions. Methods: A research platform, called the Yale Department of Medicine COVID-19 Explorer and Repository (DOM-CovX), was constructed to house cleaned, highly granular, deidentified, and continually updated data from over 18,000 patients hospitalized with COVID-19 from January 2020 to January 2023, across the Yale New Haven Health System. Data across several key domains were extracted including demographics, past medical history, laboratory values during hospitalization, vital signs, medications, imaging, procedures, and outcomes. Given the time-varying nature of several data domains, summary statistics were constructed to limit the computational size of the database and provide a reasonable data file that the broader research community could use for basic statistical analyses. The initiative also included a front-end user interface, the DOM-CovX Explorer, for simple data visualization of aggregate data. The detailed clinical data sets were made available for researchers after a review board process. Results: As of January 2023, the DOM-CovX Explorer has received 38 requests from different groups of scientists at Yale and the repository has expanded research capability to a diverse group of stakeholders including clinical and research-based faculty and trainees within 15 different surgical and nonsurgical specialties. A dedicated DOM-CovX team guides access and use of the database, which has enhanced interdepartmental collaborations, resulting in the publication of 16 peer-reviewed papers, 2 projects available in preprint servers, and 8 presentations in scientific conferences. Currently, the DOM-CovX Explorer continues to expand and improve its interface. The repository includes up to 3997 variables across 7 different clinical domains, with continued growth in response to researchers' requests and data availability. Conclusions: The DOM-CovX Data Explorer and Repository is a user-friendly tool for analyzing data and accessing a consistently updated, standardized, and large-scale database. Its innovative approach fosters collaboration, diversity of scholarly pursuits, and expands medical education. In addition, it can be applied to other diseases beyond COVID-19. ",
doi="10.2196/52120",
url="https://formative.jmir.org/2024/1/e52120"
}


@Article{info:doi/10.2196/59924,
author="Jia, Si Si
and Luo, Xinwei
and Gibson, Anne Alice
and Partridge, Ruth Stephanie",
title="Developing the DIGIFOOD Dashboard to Monitor the Digitalization of Local Food Environments: Interdisciplinary Approach",
journal="JMIR Public Health Surveill",
year="2024",
month="Aug",
day="13",
volume="10",
pages="e59924",
keywords="online food delivery",
keywords="food environment",
keywords="dashboard",
keywords="web scraping",
keywords="big data",
keywords="surveillance",
keywords="monitoring",
keywords="prevention",
keywords="food",
keywords="food delivery",
keywords="development study",
keywords="development",
keywords="accessibility",
keywords="Australia",
keywords="monitoring tool",
keywords="tool",
keywords="tools",
abstract="Background: Online food delivery services (OFDS) enable individuals to conveniently access foods from any deliverable location. The increased accessibility to foods may have implications on the consumption of healthful or unhealthful foods. Concerningly, previous research suggests that OFDS offer an abundance of energy-dense and nutrient-poor foods, which are heavily promoted through deals or discounts. Objective: In this paper, we describe the development of the DIGIFOOD dashboard to monitor the digitalization of local food environments in New South Wales, Australia, resulting from the proliferation of OFDS. Methods: Together with a team of data scientists, we designed a purpose-built dashboard using Microsoft Power BI. The development process involved three main stages: (1) data acquisition of food outlets via web scraping, (2) data cleaning and processing, and (3) visualization of food outlets on the dashboard. We also describe the categorization process of food outlets to characterize the healthfulness of local, online, and hybrid food environments. These categories included takeaway franchises, independent takeaways, independent restaurants and cafes, supermarkets or groceries, bakeries, alcohol retailers, convenience stores, and sandwich or salad shops. Results: To date, the DIGIFOOD dashboard has mapped 36,967 unique local food outlets (locally accessible and scraped from Google Maps) and 16,158 unique online food outlets (accessible online and scraped from Uber Eats) across New South Wales, Australia. In 2023, the market-leading OFDS operated in 1061 unique suburbs or localities in New South Wales. The Sydney-Parramatta region, a major urban area in New South Wales accounting for 28 postcodes, recorded the highest number of online food outlets (n=4221). In contrast, the Far West and Orana region, a rural area in New South Wales with only 2 postcodes, recorded the lowest number of food outlets accessible online (n=7). Urban areas appeared to have the greatest increase in total food outlets accessible via online food delivery. In both local and online food environments, it was evident that independent restaurants and cafes comprised the largest proportion of food outlets at 47.2\% (17,437/36,967) and 51.8\% (8369/16,158), respectively. However, compared to local food environments, the online food environment has relatively more takeaway franchises (2734/16,158, 16.9\% compared to 3273/36,967, 8.9\%) and independent takeaway outlets (2416/16,158, 14.9\% compared to 4026/36,967, 10.9\%). Conclusions: The DIGIFOOD dashboard leverages the current rich data landscape to display and contrast the availability and healthfulness of food outlets that are locally accessible versus accessible online. The DIGIFOOD dashboard can be a useful monitoring tool for the evolving digital food environment at a regional scale and has the potential to be scaled up at a national level. Future iterations of the dashboard, including data from additional prominent OFDS, can be used by policy makers to identify high-priority areas with limited access to healthful foods both online and locally. ",
doi="10.2196/59924",
url="https://publichealth.jmir.org/2024/1/e59924"
}


@Article{info:doi/10.2196/45242,
author="Bostan, Sarah
and Johnson, A. Owen
and Jaspersen, J. Lena
and Randell, Rebecca",
title="Contextual Barriers to Implementing Open-Source Electronic Health Record Systems for Low- and Lower-Middle-Income Countries: Scoping Review",
journal="J Med Internet Res",
year="2024",
month="Aug",
day="1",
volume="26",
pages="e45242",
keywords="implementation",
keywords="open source",
keywords="electronic health records",
keywords="digital health",
keywords="low- and lower-middle-income countries",
keywords="barriers",
keywords="global health care",
keywords="scoping",
keywords="review",
abstract="Background: Low- and lower-middle-income countries account for a higher percentage of global epidemics and chronic diseases. In most low- and lower-middle-income countries, there is limited access to health care. The implementation of open-source electronic health records (EHRs) can be understood as a powerful enabler for low- and lower-middle-income countries because it can transform the way health care technology is delivered. Open-source EHRs can enhance health care delivery in low- and lower-middle-income countries by improving the collection, management, and analysis of health data needed to inform health care delivery, policy, and planning. While open-source EHR systems are cost-effective and adaptable, they have not proliferated rapidly in low- and lower-middle-income countries. Implementation barriers slow adoption, with existing research focusing predominantly on technical issues preventing successful implementation. Objective: This interdisciplinary scoping review aims to provide an overview of contextual barriers affecting the adaptation and implementation of open-source EHR systems in low- and lower-middle-income countries and to identify areas for future research. Methods: We conducted a scoping literature review following a systematic methodological framework. A total of 7 databases were selected from 3 disciplines: medicine and health sciences, computing, and social sciences. The findings were reported in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist. The Mixed Methods Appraisal Tool and the Critical Appraisal Skills Programme checklists were used to assess the quality of relevant studies. Data were collated and summarized, and results were reported qualitatively, adopting a narrative synthesis approach. Results: This review included 13 studies that examined open-source EHRs' adaptation and implementation in low- and lower-middle-income countries from 3 interrelated perspectives: socioenvironmental, technological, and organizational barriers. The studies identified key issues such as limited funding, sustainability, organizational and management challenges, infrastructure, data privacy and protection, and ownership. Data protection, confidentiality, ownership, and ethics emerged as important issues, often overshadowed by technical processes. Conclusions: While open-source EHRs have the potential to enhance health care delivery in low- and lower-middle-income-country settings, implementation is fraught with difficulty. This scoping review shows that depending on the adopted perspective to implementation, different implementation barriers come into view. A dominant focus on technology distracts from socioenvironmental and organizational barriers impacting the proliferation of open-source EHRs. The role of local implementing organizations in addressing implementation barriers in low- and lower-middle-income countries remains unclear. A holistic understanding of implementers' experiences of implementation processes is needed. This could help characterize and solve implementation problems, including those related to ethics and the management of data protection. Nevertheless, this scoping review provides a meaningful contribution to the global health informatics discipline. ",
doi="10.2196/45242",
url="https://www.jmir.org/2024/1/e45242"
}


@Article{info:doi/10.2196/56406,
author="Chang, Annie
and O'Hagan, Ross
and Young, N. Jade
and Wei, Nancy
and Gulati, Nicholas",
title="Geographic Disparities in Online Searches for Psoriasis Biologics in the United States: Google Trends Analysis",
journal="JMIR Dermatol",
year="2024",
month="Jul",
day="31",
volume="7",
pages="e56406",
keywords="psoriasis",
keywords="biologics",
keywords="health disparities",
keywords="Google Trends",
keywords="online search",
keywords="web-based search",
keywords="USA",
keywords="United States",
keywords="Google",
keywords="awareness",
keywords="skin",
keywords="patient awareness",
keywords="psoriasis treatment",
keywords="US",
keywords="psoriasis medication",
keywords="patient education",
doi="10.2196/56406",
url="https://derma.jmir.org/2024/1/e56406"
}


@Article{info:doi/10.2196/54281,
author="G{\'o}mez, Gustavo
and Hufstedler, Heather
and Montenegro Morales, Carlos
and Roell, Yannik
and Lozano-Parra, Anyela
and Tami, Adriana
and Magalhaes, Tereza
and Marques, A. Ernesto T.
and Balmaseda, Angel
and Calvet, Guilherme
and Harris, Eva
and Brasil, Patricia
and Herrera, Victor
and Villar, Luis
and Maxwell, Lauren
and Jaenisch, Thomas
and ",
title="Pooled Cohort Profile: ReCoDID Consortium's Harmonized Acute Febrile Illness Arbovirus Meta-Cohort",
journal="JMIR Public Health Surveill",
year="2024",
month="Jul",
day="23",
volume="10",
pages="e54281",
keywords="infectious disease",
keywords="harmonized meta-cohort",
keywords="IPD-MA",
keywords="arbovirus",
keywords="dengue",
keywords="zika",
keywords="chikungunya",
keywords="surveillance",
keywords="public health",
keywords="open access data",
keywords="FAIR principles",
keywords="febrile illness",
keywords="clinical-epidemiological data",
keywords="cross-disease interaction",
keywords="epidemiology",
keywords="consortium",
keywords="innovation",
keywords="statistical tool",
keywords="Latin America",
keywords="Maelstrom's",
keywords="methodology",
keywords="CDISC",
keywords="immunological interaction",
keywords="flavivirus",
keywords="infection",
keywords="arboviral disease",
doi="10.2196/54281",
url="https://publichealth.jmir.org/2024/1/e54281",
url="http://www.ncbi.nlm.nih.gov/pubmed/39042429"
}


@Article{info:doi/10.2196/53790,
author="Sanchez, Jasmin
and Trofholz, Amanda
and Berge, M. Jerica",
title="Best Practices and Recommendations for Research Using Virtual Real-Time Data Collection: Protocol for Virtual Data Collection Studies",
journal="JMIR Res Protoc",
year="2024",
month="May",
day="14",
volume="13",
pages="e53790",
keywords="real-time data collection",
keywords="remote research",
keywords="virtual data collection",
keywords="virtual research protocol",
keywords="virtual research visits",
abstract="Background: The COVID-19 pandemic and the subsequent need for social distancing required the immediate pivoting of research modalities. Research that had previously been conducted in person had to pivot to remote data collection. Researchers had to develop data collection protocols that could be conducted remotely with limited or no evidence to guide the process. Therefore, the use of web-based platforms to conduct real-time research visits surged despite the lack of evidence backing these novel approaches. Objective: This paper aims to review the remote or virtual research protocols that have been used in the past 10 years, gather existing best practices, and propose recommendations for continuing to use virtual real-time methods when appropriate. Methods: Articles (n=22) published from 2013 to June 2023 were reviewed and analyzed to understand how researchers conducted virtual research that implemented real-time protocols. ``Real-time'' was defined as data collection with a participant through a live medium where a participant and research staff could talk to each other back and forth in the moment. We excluded studies for the following reasons: (1) studies that collected participant or patient measures for the sole purpose of engaging in a clinical encounter; (2) studies that solely conducted qualitative interview data collection; (3) studies that conducted virtual data collection such as surveys or self-report measures that had no interaction with research staff; (4) studies that described research interventions but did not involve the collection of data through a web-based platform; (5) studies that were reviews or not original research; (6) studies that described research protocols and did not include actual data collection; and (7) studies that did not collect data in real time, focused on telehealth or telemedicine, and were exclusively intended for medical and not research purposes. Results: Findings from studies conducted both before and during the COVID-19 pandemic suggest that many types of data can be collected virtually in real time. Results and best practice recommendations from the current protocol review will be used in the design and implementation of a substudy to provide more evidence for virtual real-time data collection over the next year. Conclusions: Our findings suggest that virtual real-time visits are doable across a range of participant populations and can answer a range of research questions. Recommended best practices for virtual real-time data collection include (1) providing adequate equipment for real-time data collection, (2) creating protocols and materials for research staff to facilitate or guide participants through data collection, (3) piloting data collection, (4) iteratively accepting feedback, and (5) providing instructions in multiple forms. The implementation of these best practices and recommendations for future research are further discussed in the paper. International Registered Report Identifier (IRRID): DERR1-10.2196/53790 ",
doi="10.2196/53790",
url="https://www.researchprotocols.org/2024/1/e53790",
url="http://www.ncbi.nlm.nih.gov/pubmed/38743477"
}


@Article{info:doi/10.2196/49433,
author="Lee, Mi-Sun
and Lee, Hooyeon",
title="Chronic Disease Patterns and Their Relationship With Health-Related Quality of Life in South Korean Older Adults With the 2021 Korean National Health and Nutrition Examination Survey: Latent Class Analysis",
journal="JMIR Public Health Surveill",
year="2024",
month="Apr",
day="10",
volume="10",
pages="e49433",
keywords="chronic disease",
keywords="latent class analysis",
keywords="multimorbidity",
keywords="older adults",
keywords="quality of life",
abstract="Background: Improved life expectancy has increased the prevalence of older adults living with multimorbidities, which likely deteriorates their health-related quality of life (HRQoL). Understanding which chronic conditions frequently co-occur can facilitate person-centered care tailored to the needs of individuals with specific multimorbidity profiles. Objective: The study objectives were to (1) examine the prevalence of multimorbidity among Korean older adults (ie, those aged 65 years and older), (2) investigate chronic disease patterns using latent class analysis, and (3) assess which chronic disease patterns are more strongly associated with HRQoL. Methods: A sample of 1806 individuals aged 65 years and older from the 2021 Korean National Health and Nutrition Examination Survey was analyzed. Latent class analysis was conducted to identify the clustering pattern of chronic diseases. HRQoL was assessed by an 8-item health-related quality of life scale (HINT-8). Multiple linear regression was used to analyze the association with the total score of the HINT-8. Logistic regression analysis was performed to evaluate the odds ratio of having problems according to the HINT-8 items. Results: The prevalence of multimorbidity in the sample was 54.8\%. Three chronic disease patterns were identified: relatively healthy, cardiometabolic condition, arthritis, allergy, or asthma. The total scores of the HINT-8 were the highest in participants characterized as arthritis, allergy, or asthma group, indicating the lowest quality of life. Conclusions: Current health care models are disease-oriented, meaning that the management of chronic conditions applies to a single condition and may not be relevant to those with multimorbidities. Identifying chronic disease patterns and their impact on overall health and well-being is critical for guiding integrated care. ",
doi="10.2196/49433",
url="https://publichealth.jmir.org/2024/1/e49433",
url="http://www.ncbi.nlm.nih.gov/pubmed/38598275"
}


@Article{info:doi/10.2196/45943,
author="He, Qiyu
and Mok, Tsz-Ngai
and Sin, Tat-Hang
and Yin, Jiaying
and Li, Sicun
and Yin, Yiyue
and Ming, Wai-Kit
and Feng, Bin",
title="Global, Regional, and National Prevalence of Gout From 1990 to 2019: Age-Period-Cohort Analysis With Future Burden Prediction",
journal="JMIR Public Health Surveill",
year="2023",
month="Jun",
day="7",
volume="9",
pages="e45943",
keywords="gout",
keywords="prevalence",
keywords="age-period-cohort analysis",
keywords="Global Burden of Disease Study 2019",
keywords="prediction",
keywords="Bayesian age-period-cohort analysis",
keywords="Norped age-period-cohort analysis",
abstract="Background: Gout is a common and debilitating condition that is associated with significant morbidity and mortality. Despite advances in medical treatment, the global burden of gout continues to increase, particularly in high--sociodemographic index (SDI) regions. Objective: To address the aforementioned issue, we used age-period-cohort (APC) modeling to analyze global trends in gout incidence and prevalence from 1990 to 2019. Methods: Data were extracted from the Global Burden of Disease Study 2019 to assess all-age prevalence and age-standardized prevalence rates, as well as years lived with disability rates, for 204 countries and territories. APC effects were also examined in relation to gout prevalence. Future burden prediction was carried out using the Nordpred APC prediction of future incidence cases and the Bayesian APC model. Results: The global gout incidence has increased by 63.44\% over the past 2 decades, with a corresponding increase of 51.12\% in global years lived with disability. The sex ratio remained consistent at 3:1 (male to female), but the global gout incidence increased in both sexes over time. Notably, the prevalence and incidence of gout were the highest in high-SDI regions (95\% uncertainty interval 14.19-20.62), with a growth rate of 94.3\%. Gout prevalence increases steadily with age, and the prevalence increases rapidly in high-SDI quantiles for the period effect. Finally, the cohort effect showed that gout prevalence increases steadily, with the risk of morbidity increasing in younger birth cohorts. The prediction model suggests that the gout incidence rate will continue to increase globally. Conclusions: Our study provides important insights into the global burden of gout and highlights the need for effective management and prophylaxis of this condition. The APC model used in our analysis provides a novel approach to understanding the complex trends in gout prevalence and incidence, and our findings can inform the development of targeted interventions to address this growing health issue. ",
doi="10.2196/45943",
url="https://publichealth.jmir.org/2023/1/e45943",
url="http://www.ncbi.nlm.nih.gov/pubmed/37285198"
}


@Article{info:doi/10.2196/40657,
author="Yuan, Ruixia
and Ren, Fang
and Xie, Yingying
and Li, Kaixiang
and Tong, Zhuang",
title="The Global, Regional, and National Burdens of Cervical Cancer Attributable to Smoking From 1990 to 2019: Population-Based Study",
journal="JMIR Public Health Surveill",
year="2022",
month="Dec",
day="23",
volume="8",
number="12",
pages="e40657",
keywords="global burden of disease",
keywords="cervical cancer",
keywords="smoking women",
keywords="time trends",
abstract="Background: Cervical cancer is the fourth most common cause of cancer death in women worldwide. Smoking is one of the risk factors for cervical cancer. Understanding the global distribution of the disease burden of cervical cancer attributable to smoking and related changes is of clear significance for the prevention and control of cervical cancer in key populations and for tobacco control. As far as we know, research on the burden of cervical cancer attributable to smoking is lacking. Objective: We estimated the disease burden and mortality of cervical cancer attributable to smoking and related trends over time at the global, regional, and national levels. Methods: Data were obtained from the Global Burden of Disease study website. Age-standardized rates were used to facilitate comparisons of mortality and disability-adjusted life years (DALYs) at different levels. The estimated annual percentage change (EAPC) was used to assess trends in the age-standardized mortality rate (ASMR) and the age-standardized DALY rate (ASDR). A Pearson correlation analysis was used to evaluate correlations between the sociodemographic index and the age-standardized rates. Results: In 2019, there were 30,136.65 (95\% uncertainty interval [UI]: 14,945.09-49,639.87) cervical cancer--related deaths and 893,735.25 (95\% UI 469,201.51-1,440,050.85) cervical cancer--related DALYs attributable to smoking. From 1990 to 2019, the global burden of cervical cancer attributable to smoking showed a decreasing trend around the world; the EAPCs for ASMR and ASDR were --2.11 (95\% CI --2.16 to --2.06) and --2.22 (95\% CI --2.26 to --2.18), respectively. In terms of age characteristics, in 2019, an upward trend was observed for age in the mortality of cervical cancer attributable to smoking. Analysis of the trend in DALYs with age revealed an initially increasing and then decreasing trend. From 1990 to 2019, the burden of disease in different age groups showed a downward trend. Among 204 countries, 180 countries showed downward trends, 10 countries showed upward trends, and the burden was stable in 14 countries. The Pearson correlation analysis revealed a significant negative correlation between sociodemographic index and the age-standardized rates of cervical cancer attributable to smoking ($\rho$=--0.228, P<.001 for ASMR and $\rho$=--0.223, P<.001 for ASDR). Conclusions: An increase over time in the absolute number of cervical cancer deaths and DALYs attributable to smoking and a decrease over time in the ASMR and ASDR for cervical cancer attributable to smoking were observed in the overall population, and differences in these variables were also observed between countries and regions. More attention should be paid to cervical cancer prevention and screening in women who smoke, especially in low- and middle-income countries. ",
doi="10.2196/40657",
url="https://publichealth.jmir.org/2022/12/e40657",
url="http://www.ncbi.nlm.nih.gov/pubmed/36563035"
}


@Article{info:doi/10.2196/37790,
author="Pickering, Gis{\`e}le
and Mezouar, Linda
and Kechemir, Hayet
and Ebel-Bitoun, Caty",
title="Paracetamol Use in Patients With Osteoarthritis and Lower Back Pain: Infodemiology Study and Observational Analysis of Electronic Medical Record Data",
journal="JMIR Public Health Surveill",
year="2022",
month="Oct",
day="27",
volume="8",
number="10",
pages="e37790",
keywords="osteoarthritis",
keywords="lower back pain",
keywords="general practice",
keywords="rheumatology",
keywords="paracetamol",
keywords="real-world evidence",
abstract="Background: Lower back pain (LBP) and osteoarthritis (OA) are common musculoskeletal disorders and account for around 17.0\% of years lived with disability worldwide; however, there is a lack of real-world data on these conditions. Paracetamol brands are frequently prescribed in France for musculoskeletal pain and include Doliprane, Dafalgan, and Ixprim (tramadol-paracetamol). Objective: The objective of this retrospective study was to understand the journey of patients with LBP or OA when treated with paracetamol. Methods: Three studies were undertaken. Two studies analyzed electronic medical records from general practitioners (GPs) and rheumatologists of patients with OA or LBP, who had received at least one paracetamol prescription between 2013 and 2018 in France. Data were extracted, anonymized, and stratified by gender, age, and provider specialty. The third study, an infodemiology study, analyzed associations between terms used on public medical forums and Twitter in France and the United States for OA only. Results: In the first 2 studies, among patients with LBP (98,998), most (n=92,068, 93.0\%) saw a GP, and Doliprane was a first-line therapy for 87.0\% (n=86,128) of patients (71.0\% [n=61,151] in combination with nonsteroidal anti-inflammatory drugs [NSAIDs] or opioids). Among patients with OA (99,997), most (n=84,997, 85.0\%) saw a GP, and Doliprane was a first-line therapy for 83.0\% (n=82,998) of patients (62.0\% [n=51,459] in combination). Overall, paracetamol monotherapy prescriptions decreased as episodes increased. In the third study, in line with available literature, the data confirmed that the prevalence of OA increases with age (91.5\% [212,875/232,650] above 41 years), OA is more predominant in females (46,530/232,650, 20.0\%), and paracetamol use varies between GPs and rheumatologists. Conclusions: This health surveillance analysis provides a better understanding of the journey for patients with LBP or OA. These data confirmed that although paracetamol remains the most common first-line analgesic for patients with LBP and OA, usage varies among patients and health care specialists, and there are concerns over efficacy. ",
doi="10.2196/37790",
url="https://publichealth.jmir.org/2022/10/e37790",
url="http://www.ncbi.nlm.nih.gov/pubmed/36301591"
}


@Article{info:doi/10.2196/35276,
author="Otridge, Jeremy
and Ogden, L. Cynthia
and Bernstein, T. Kyle
and Knuth, Martha
and Fishman, Julie
and Brooks, T. John",
title="Publication and Impact of Preprints Included in the First 100 Editions of the CDC COVID-19 Science Update: Content Analysis",
journal="JMIR Public Health Surveill",
year="2022",
month="Jul",
day="15",
volume="8",
number="7",
pages="e35276",
keywords="preprints",
keywords="preprint",
keywords="publishing",
keywords="publish",
keywords="bioRxiv",
keywords="medRxiv",
keywords="Centers for Disease Control and Prevention",
keywords="CDC",
keywords="preprint server",
keywords="public health",
keywords="health information",
keywords="COVID-19",
keywords="pandemic",
keywords="publication",
keywords="Altmetric attention score",
keywords="Altmetric",
keywords="attention score",
keywords="citation count",
keywords="citation",
keywords="science update",
keywords="decision-making",
abstract="Background: Preprints are publicly available manuscripts posted to various servers that have not been peer reviewed. Although preprints have existed since 1961, they have gained increased popularity during the COVID-19 pandemic due to the need for immediate, relevant information. Objective: The aim of this study is to evaluate the publication rate and impact of preprints included in the Centers for Disease Control and Prevention (CDC) COVID-19 Science Update and assess the performance of the COVID-19 Science Update team in selecting impactful preprints. Methods: All preprints in the first 100 editions (April 1, 2020, to July 30, 2021) of the Science Update were included in the study. Preprints that were not published were categorized as ``unpublished preprints.'' Preprints that were subsequently published exist in 2 versions (in a peer-reviewed journal and on the original preprint server), which were analyzed separately and referred to as ``peer-reviewed preprint'' and ``original preprint,'' respectively. Time to publish was the time interval between the date on which a preprint was first posted and the date on which it was first available as a peer-reviewed article. Impact was quantified by Altmetric Attention Score and citation count for all available manuscripts on August 6, 2021. Preprints were analyzed by publication status, publication rate, preprint server, and time to publication. Results: Of the 275 preprints included in the CDC COVID-19 Science Update during the study period, most came from three servers: medRxiv (n=201, 73.1\%), bioRxiv (n=41, 14.9\%), and SSRN (n=25, 9.1\%), with 8 (2.9\%) coming from other sources. Additionally, 152 (55.3\%) were eventually published. The median time to publish was 2.3 (IQR 1.4-3.7). When preprints posted in the last 2.3 months were excluded (to account for the time to publish), the publication rate was 67.8\%. Moreover, 76 journals published at least one preprint from the CDC COVID-19 Science Update, and 18 journals published at least three. The median Altmetric Attention Score for unpublished preprints (n=123, 44.7\%) was 146 (IQR 22-552) with a median citation count of 2 (IQR 0-8); for original preprints (n=152, 55.2\%), these values were 212 (IQR 22-1164) and 14 (IQR 2-40), respectively; for peer-review preprints, these values were 265 (IQR 29-1896) and 19 (IQR 3-101), respectively. Conclusions: Prior studies of COVID-19 preprints found publication rates between 5.4\% and 21.1\%. Preprints included in the CDC COVID-19 Science Update were published at a higher rate than overall COVID-19 preprints, and those that were ultimately published were published within months and received higher attention scores than unpublished preprints. These findings indicate that the Science Update process for selecting preprints had a high fidelity in terms of their likelihood to be published and their impact. The incorporation of high-quality preprints into the CDC COVID-19 Science Update improves this activity's capacity to inform meaningful public health decision-making. ",
doi="10.2196/35276",
url="https://publichealth.jmir.org/2022/7/e35276",
url="http://www.ncbi.nlm.nih.gov/pubmed/35544426"
}


@Article{info:doi/10.2196/30697,
author="Foraker, Randi
and Guo, Aixia
and Thomas, Jason
and Zamstein, Noa
and Payne, RO Philip
and Wilcox, Adam
and ",
title="The National COVID Cohort Collaborative: Analyses of Original and Computationally Derived Electronic Health Record Data",
journal="J Med Internet Res",
year="2021",
month="Oct",
day="4",
volume="23",
number="10",
pages="e30697",
keywords="synthetic data",
keywords="protected health information",
keywords="COVID-19",
keywords="electronic health records and systems",
keywords="data analysis",
abstract="Background: Computationally derived (``synthetic'') data can enable the creation and analysis of clinical, laboratory, and diagnostic data as if they were the original electronic health record data. Synthetic data can support data sharing to answer critical research questions to address the COVID-19 pandemic. Objective: We aim to compare the results from analyses of synthetic data to those from original data and assess the strengths and limitations of leveraging computationally derived data for research purposes. Methods: We used the National COVID Cohort Collaborative's instance of MDClone, a big data platform with data-synthesizing capabilities (MDClone Ltd). We downloaded electronic health record data from 34 National COVID Cohort Collaborative institutional partners and tested three use cases, including (1) exploring the distributions of key features of the COVID-19--positive cohort; (2) training and testing predictive models for assessing the risk of admission among these patients; and (3) determining geospatial and temporal COVID-19--related measures and outcomes, and constructing their epidemic curves. We compared the results from synthetic data to those from original data using traditional statistics, machine learning approaches, and temporal and spatial representations of the data. Results: For each use case, the results of the synthetic data analyses successfully mimicked those of the original data such that the distributions of the data were similar and the predictive models demonstrated comparable performance. Although the synthetic and original data yielded overall nearly the same results, there were exceptions that included an odds ratio on either side of the null in multivariable analyses (0.97 vs 1.01) and differences in the magnitude of epidemic curves constructed for zip codes with low population counts. Conclusions: This paper presents the results of each use case and outlines key considerations for the use of synthetic data, examining their role in collaborative research for faster insights. ",
doi="10.2196/30697",
url="https://www.jmir.org/2021/10/e30697",
url="http://www.ncbi.nlm.nih.gov/pubmed/34559671"
}


@Article{info:doi/10.2196/31122,
author="Lee, Junghwan
and Kim, Hyun Jae
and Liu, Cong
and Hripcsak, George
and Natarajan, Karthik
and Ta, Casey
and Weng, Chunhua",
title="Columbia Open Health Data for COVID-19 Research: Database Analysis",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="30",
volume="23",
number="9",
pages="e31122",
keywords="COVID-19",
keywords="open data",
keywords="electronic health record",
keywords="data science",
keywords="research",
keywords="data",
keywords="access",
keywords="database",
keywords="symptom",
keywords="cohort",
keywords="prevalence",
abstract="Background: COVID-19 has threatened the health of tens of millions of people all over the world. Massive research efforts have been made in response to the COVID-19 pandemic. Utilization of clinical data can accelerate these research efforts to combat the pandemic since important characteristics of the patients are often found by examining the clinical data. Publicly accessible clinical data on COVID-19, however, remain limited despite the immediate need. Objective: To provide shareable clinical data to catalyze COVID-19 research, we present Columbia Open Health Data for COVID-19 Research (COHD-COVID), a publicly accessible database providing clinical concept prevalence, clinical concept co-occurrence, and clinical symptom prevalence for hospitalized patients with COVID-19. COHD-COVID also provides data on hospitalized patients with influenza and general hospitalized patients as comparator cohorts. Methods: The data used in COHD-COVID were obtained from NewYork-Presbyterian/Columbia University Irving Medical Center's electronic health records database. Condition, drug, and procedure concepts were obtained from the visits of identified patients from the cohorts. Rare concepts were excluded, and the true concept counts were perturbed using Poisson randomization to protect patient privacy. Concept prevalence, concept prevalence ratio, concept co-occurrence, and symptom prevalence were calculated using the obtained concepts. Results: Concept prevalence and concept prevalence ratio analyses showed the clinical characteristics of the COVID-19 cohorts, confirming the well-known characteristics of COVID-19 (eg, acute lower respiratory tract infection and cough). The concepts related to the well-known characteristics of COVID-19 recorded high prevalence and high prevalence ratio in the COVID-19 cohort compared to the hospitalized influenza cohort and general hospitalized cohort. Concept co-occurrence analyses showed potential associations between specific concepts. In case of acute lower respiratory tract infection in the COVID-19 cohort, a high co-occurrence ratio was obtained with COVID-19--related concepts and commonly used drugs (eg, disease due to coronavirus and acetaminophen). Symptom prevalence analysis indicated symptom-level characteristics of the cohorts and confirmed that well-known symptoms of COVID-19 (eg, fever, cough, and dyspnea) showed higher prevalence than the hospitalized influenza cohort and the general hospitalized cohort. Conclusions: We present COHD-COVID, a publicly accessible database providing useful clinical data for hospitalized patients with COVID-19, hospitalized patients with influenza, and general hospitalized patients. We expect COHD-COVID to provide researchers and clinicians quantitative measures of COVID-19--related clinical features to better understand and combat the pandemic. ",
doi="10.2196/31122",
url="https://www.jmir.org/2021/9/e31122",
url="http://www.ncbi.nlm.nih.gov/pubmed/34543225"
}


@Article{info:doi/10.2196/22446,
author="Al Tamime, Reham
and Weber, Ingmar",
title="Tracking Exposure to Ads Amid the COVID-19 Pandemic: Development of a Public Google Ads Data Set",
journal="JMIR Data",
year="2021",
month="Sep",
day="14",
volume="2",
number="1",
pages="e22446",
keywords="COVID-19",
keywords="coronavirus",
keywords="SARS-CoV-2",
keywords="panic buying",
keywords="Google Ads",
keywords="data",
keywords="database",
keywords="tracking",
keywords="research",
keywords="public availability",
keywords="online behaviors",
abstract="Background: The COVID-19 pandemic has had a substantial impact on economies, governments, businesses, and most importantly, people's health. To bring the spread of COVID-19 under control, strict lockdown measures have been implemented across the globe. These lockdown measures resulted in a spate of panic buying and increase in demand for hygiene products and other grocery items. Objective: In this paper, we describe a data set from Google Ads that looks at the presentation of ads to people while they browse the web during the COVID-19 pandemic. We are making the data set available to the research community. Methods: We started this ongoing data collection on March 28, 2020, leveraging Developer Tools' network requests to retrieve Google Ads data. We identified a list of items related and unrelated to panic buying. We then captured these items as targeting criteria under what people are actively researching or planning on Google Ads. Google Ads data has been filtered using additional targeting criteria such as country, gender, and parental status. Results: Since the inception of our collection, we have actively maintained and updated our repository on a monthly basis. In total, we have published over 4116 data points. This paper also presents basic statistics that reveal variations in Google Ads data across countries, gender, and parental status. Conclusions: We hope that this Google Ads data set can increase our understanding of ad exposure during the COVID-19 outbreak. In particular, this data set can lead to further studies that look at the relationship between exposure to ads, time spent web browsing, and health outcomes. ",
doi="10.2196/22446",
url="https://data.jmir.org/2021/1/e22446"
}


@Article{info:doi/10.2196/29310,
author="Patterson, Rees Jenny
and Shaw, Donna
and Thomas, R. Sharita
and Hayes, A. Julie
and Daley, R. Christopher
and Knight, Stefania
and Aikat, Jay
and Mieczkowska, O. Joanna
and Ahalt, C. Stanley
and Krishnamurthy, K. Ashok",
title="COVID-19 Data Utilization in North Carolina: Qualitative Analysis of Stakeholder Experiences",
journal="JMIR Public Health Surveill",
year="2021",
month="Sep",
day="2",
volume="7",
number="9",
pages="e29310",
keywords="qualitative research",
keywords="interview",
keywords="COVID-19",
keywords="SARS-CoV-2",
keywords="pandemic",
keywords="data collection",
keywords="data reporting",
keywords="data",
keywords="public health",
keywords="coronavirus disease 2019",
abstract="Background: As the world faced the pandemic caused by the novel coronavirus disease 2019 (COVID-19), medical professionals, technologists, community leaders, and policy makers sought to understand how best to leverage data for public health surveillance and community education. With this complex public health problem, North Carolinians relied on data from state, federal, and global health organizations to increase their understanding of the pandemic and guide decision-making. Objective: We aimed to describe the role that stakeholders involved in COVID-19--related data played in managing the pandemic in North Carolina. The study investigated the processes used by organizations throughout the state in using, collecting, and reporting COVID-19 data. Methods: We used an exploratory qualitative study design to investigate North Carolina's COVID-19 data collection efforts. To better understand these processes, key informant interviews were conducted with employees from organizations that collected COVID-19 data across the state. We developed an interview guide, and open-ended semistructured interviews were conducted during the period from June through November 2020. Interviews lasted between 30 and 45 minutes and were conducted by data scientists by videoconference. Data were subsequently analyzed using qualitative data analysis software. Results: Results indicated that electronic health records were primary sources of COVID-19 data. Often, data were also used to create dashboards to inform the public or other health professionals, to aid in decision-making, or for reporting purposes. Cross-sector collaboration was cited as a major success. Consistency among metrics and data definitions, data collection processes, and contact tracing were cited as challenges. Conclusions: Findings suggest that, during future outbreaks, organizations across regions could benefit from data centralization and data governance. Data should be publicly accessible and in a user-friendly format. Additionally, established cross-sector collaboration networks are demonstrably beneficial for public health professionals across the state as these established relationships facilitate a rapid response to evolving public health challenges. ",
doi="10.2196/29310",
url="https://publichealth.jmir.org/2021/9/e29310",
url="http://www.ncbi.nlm.nih.gov/pubmed/34298500"
}


@Article{info:doi/10.2196/25714,
author="Vaghela, Uddhav
and Rabinowicz, Simon
and Bratsos, Paris
and Martin, Guy
and Fritzilas, Epameinondas
and Markar, Sheraz
and Purkayastha, Sanjay
and Stringer, Karl
and Singh, Harshdeep
and Llewellyn, Charlie
and Dutta, Debabrata
and Clarke, M. Jonathan
and Howard, Matthew
and 
and Serban, Ovidiu
and Kinross, James",
title="Using a Secure, Continually Updating, Web Source Processing Pipeline to Support the Real-Time Data Synthesis and Analysis of Scientific Literature: Development and Validation Study",
journal="J Med Internet Res",
year="2021",
month="May",
day="6",
volume="23",
number="5",
pages="e25714",
keywords="structured data synthesis",
keywords="data science",
keywords="critical analysis",
keywords="web crawl data",
keywords="pipeline",
keywords="database",
keywords="literature",
keywords="research",
keywords="COVID-19",
keywords="infodemic",
keywords="decision making",
keywords="data",
keywords="data synthesis",
keywords="misinformation",
keywords="infrastructure",
keywords="methodology",
abstract="Background: The scale and quality of the global scientific response to the COVID-19 pandemic have unquestionably saved lives. However, the COVID-19 pandemic has also triggered an unprecedented ``infodemic''; the velocity and volume of data production have overwhelmed many key stakeholders such as clinicians and policy makers, as they have been unable to process structured and unstructured data for evidence-based decision making. Solutions that aim to alleviate this data synthesis--related challenge are unable to capture heterogeneous web data in real time for the production of concomitant answers and are not based on the high-quality information in responses to a free-text query. Objective: The main objective of this project is to build a generic, real-time, continuously updating curation platform that can support the data synthesis and analysis of a scientific literature framework. Our secondary objective is to validate this platform and the curation methodology for COVID-19--related medical literature by expanding the COVID-19 Open Research Dataset via the addition of new, unstructured data. Methods: To create an infrastructure that addresses our objectives, the PanSurg Collaborative at Imperial College London has developed a unique data pipeline based on a web crawler extraction methodology. This data pipeline uses a novel curation methodology that adopts a human-in-the-loop approach for the characterization of quality, relevance, and key evidence across a range of scientific literature sources. Results: REDASA (Realtime Data Synthesis and Analysis) is now one of the world's largest and most up-to-date sources of COVID-19--related evidence; it consists of 104,000 documents. By capturing curators' critical appraisal methodologies through the discrete labeling and rating of information, REDASA rapidly developed a foundational, pooled, data science data set of over 1400 articles in under 2 weeks. These articles provide COVID-19--related information and represent around 10\% of all papers about COVID-19. Conclusions: This data set can act as ground truth for the future implementation of a live, automated systematic review. The three benefits of REDASA's design are as follows: (1) it adopts a user-friendly, human-in-the-loop methodology by embedding an efficient, user-friendly curation platform into a natural language processing search engine; (2) it provides a curated data set in the JavaScript Object Notation format for experienced academic reviewers' critical appraisal choices and decision-making methodologies; and (3) due to the wide scope and depth of its web crawling method, REDASA has already captured one of the world's largest COVID-19--related data corpora for searches and curation. ",
doi="10.2196/25714",
url="https://www.jmir.org/2021/5/e25714",
url="http://www.ncbi.nlm.nih.gov/pubmed/33835932"
}


@Article{info:doi/10.2196/24288,
author="Ossom-Williamson, Peace
and Williams, Maximilian Isaac
and Kim, Kukhyoung
and Kindratt, B. Tiffany",
title="Reporting and Availability of COVID-19 Demographic Data by US Health Departments (April to October 2020): Observational Study",
journal="JMIR Public Health Surveill",
year="2021",
month="Apr",
day="6",
volume="7",
number="4",
pages="e24288",
keywords="coronavirus disease 2019",
keywords="COVID-19",
keywords="SARS-CoV-2",
keywords="race",
keywords="ethnicity",
keywords="age",
keywords="sex",
keywords="health equity",
keywords="open data",
keywords="dashboards",
abstract="Background: There is an urgent need for consistent collection of demographic data on COVID-19 morbidity and mortality and sharing it with the public in open and accessible ways. Due to the lack of consistency in data reporting during the initial spread of COVID-19, the Equitable Data Collection and Disclosure on COVID-19 Act was introduced into the Congress that mandates collection and reporting of demographic COVID-19 data on testing, treatments, and deaths by age, sex, race and ethnicity, primary language, socioeconomic status, disability, and county. To our knowledge, no studies have evaluated how COVID-19 demographic data have been collected before and after the introduction of this legislation. Objective: This study aimed to evaluate differences in reporting and public availability of COVID-19 demographic data by US state health departments and Washington, District of Columbia (DC) before (pre-Act), immediately after (post-Act), and 6 months after (6-month follow-up) the introduction of the Equitable Data Collection and Disclosure on COVID-19 Act in the Congress on April 21, 2020. Methods: We reviewed health department websites of all 50 US states and Washington, DC (N=51). We evaluated how each state reported age, sex, and race and ethnicity data for all confirmed COVID-19 cases and deaths and how they made this data available (ie, charts and tables only or combined with dashboards and machine-actionable downloadable formats) at the three timepoints. Results: We found statistically significant increases in the number of health departments reporting age-specific data for COVID-19 cases (P=.045) and resulting deaths (P=.002), sex-specific data for COVID-19 deaths (P=.003), and race- and ethnicity-specific data for confirmed cases (P=.003) and deaths (P=.005) post-Act and at the 6-month follow-up (P<.05 for all). The largest increases were race and ethnicity state data for confirmed cases (pre-Act: 18/51, 35\%; post-Act: 31/51, 61\%; 6-month follow-up: 46/51, 90\%) and deaths due to COVID-19 (pre-Act: 13/51, 25\%; post-Act: 25/51, 49\%; and 6-month follow-up: 39/51, 76\%). Although more health departments reported race and ethnicity data based on federal requirements (P<.001), over half (29/51, 56.9\%) still did not report all racial and ethnic groups as per the Office of Management and Budget guidelines (pre-Act: 5/51, 10\%; post-Act: 21/51, 41\%; and 6-month follow-up: 27/51, 53\%). The number of health departments that made COVID-19 data available for download significantly increased from 7 to 23 (P<.001) from our initial data collection (April 2020) to the 6-month follow-up, (October 2020). Conclusions: Although the increased demand for disaggregation has improved public reporting of demographics across health departments, an urgent need persists for the introduced legislation to be passed by the Congress for the US states to consistently collect and make characteristics of COVID-19 cases, deaths, and vaccinations available in order to allocate resources to mitigate disease spread. ",
doi="10.2196/24288",
url="https://publichealth.jmir.org/2021/4/e24288",
url="http://www.ncbi.nlm.nih.gov/pubmed/33821804"
}


@Article{info:doi/10.2196/15603,
author="Bacon, Seb
and Goldacre, Ben",
title="Barriers to Working With National Health Service England's Open Data",
journal="J Med Internet Res",
year="2020",
month="Jan",
day="13",
volume="22",
number="1",
pages="e15603",
keywords="informatics",
keywords="health services",
keywords="software",
keywords="access to information",
doi="10.2196/15603",
url="https://www.jmir.org/2020/1/e15603",
url="http://www.ncbi.nlm.nih.gov/pubmed/31929101"
}