Informatics Research Research Articles

A Study of Users' Privacy Preferences for Data Sharing on Symptoms-Tracking/Health App.

Symptoms-tracking applications allow crowdsensing of health and location related data from individuals to track the spread and outbreaks of infectious diseases. During the COVID-19 pandemic, for the first time in history, these apps were widely adopted across the world to combat the pandemic. However, due to the sensitive nature of the data collected by these apps, serious privacy concerns were raised and apps were critiqued for their insufficient privacy safeguards. The Covid Nearby project was launched to develop a privacy-focused symptoms-tracking app and to understand the privacy preferences of users in health emergencies. In this work, we draw on the insights from the Covid Nearby users' data, and present an analysis of the significantly varying trends in users' privacy preferences with respect to demographics, attitude towards information sharing, and health concerns, e.g. after being possibly exposed to COVID-19. These results and insights can inform health informatics researchers and policy designers in developing more socially acceptable health apps in the future.

DIABETES MELLITUS ATTRIBUTE CLASSIFICATION USING THE NAIVE BAYES ALGORITHM BASED ON FORWARD SELECTION

Diabetes Mellitus is a chronic condition that frequently results in death. Almost every nation has experienced and contributed to this rise in mortality. Consequently, several researchers are motivated to determine this disease's source and prevent the increase in mortality rates. The research was conducted in the field of informatics in partnership with health professionals to determine the causes of this condition. Many informatics researchers employ machine learning techniques to aid in analyzing existing data. This study suggests feature selection based on forward selection and the naive Bayes classification approach to determine this disease's primary aetiology. The results demonstrate that our proposed strategy can increase the classification accuracy of patients. The performance outcomes improved by 169%. According to this theory, it is also known that the primary cause of this disease is its dependence on body mass index and age. Therefore, additional research must explore these two variables' impact on various other disorders.

Inequity in Digital Health Planning in Canada.

An evaluation of the paper by Falk (2022) in this issue using a word count method found that it omits consideration of substantial efforts, inherent data rights and experiences with virtual care from certain jurisdictions, professions and Indigenous groups. Although equity is positioned as a core policy pillar of virtual care, it is not defined, nor are factors underlying digital health inequity described. Deficits in health informatics training, regulation, pedagogy and research in Canada likely contribute to an inequitable approach to health informatics planning. A commitment to definitional rigour, taxonomic clarity and evidence-informed informatics will help promote digital health equity.

Organisational Change: Using Health Informatics Education as a Change Agent.

This paper highlights some of the challenges, achievements and collaborations using health informatics education and research as a change agent in which I have been involved over the last 40 years. The Open Software Library (OSL) was a specialist publisher of Computer-Based Training materials (CBT) mainly authored by nurses and medics. The "Rainbow" series of distance learning materials, "Using Information in Managing the Nursing Resource" sold over 55,000 copies. It was utilized as the basis for seven Universities' Certificate and Diploma programmes and in-house training by the NHS to encourage organisational change. Workshops at Manchester University's HSMU focusing on evaluation studies highlighted that most NHS IT projects failed because of human and organisational issues rather than IT. This led to the development of a master's degree in Health Informatics shared between four European Universities. IMIA conferences, Working Groups and the development of the IMIA approved Education Recommendations and the IMIA Knowledge Base are effectively used worldwide.

Capacity Development to Leverage Advances in Health Informatics for All.

In this essay we will discuss capacity development in health informatics research and application, which to us is among the major contributions of Professor John Mantas scholarship. Specifically, driven by the inspiration of his scholarship we will elaborate on advancing new applications areas, additional actors and geographical uptake of health informatics and eHealth solutions over time. We will illustrate capacity development in health informatics and address challenges that systematically foster digital health literacy, engagement and empowerment, and building health informatics capacities regionally, in Europe and globally.

Main Points of Teaching and Training of Multi-Media Technology in Takraw

Multimedia information technology is an indispensable thing in modern school teaching. The introduction of PPT in the course and the use of multimedia equipment let us know the importance of multimedia. Multimedia-assisted teaching is one of the modern teaching methods. It can not only effectively stimulate students' interest in learning, but also improve classroom learning efficiency. Nowadays, multimedia teaching has become the main means of teaching cultural courses, but its application rate in physical education is still very low. How to combine physical education courses with modern technology has become a gap that must be overcome in physical education teaching innovation. It is precisely because of this that more and more scholars and educators have devoted themselves to the research of physical education informatization.

MHealth Technology Design and Evaluation for Early Childhood Health Promotion: Systematic Literature Review.

BackgroundRecent increases in smartphone ownership among underserved populations have inspired researchers in medicine, computing, and health informatics to design and evaluate mobile health (mHealth) interventions, specifically for those supporting child development and growth. Although these interventions demonstrate possible effectiveness at larger scales, few of these interventions are evaluated to address racial disparities and health equity, which are known factors that affect relevance, uptake, and adherence in target populations.ObjectiveIn this study, we aimed to identify and document the current design and evaluation practices of mHealth technologies that promote early childhood health, with a specific focus on opportunities for those processes to address health disparities and health equity.MethodsWe completed a systematic literature review of studies that design and evaluate mHealth interventions for early childhood health promotion. We then analyzed these studies to identify opportunities to address racial disparities in early- and late-stage processes and to understand the potential efficacy of these interventions.ResultsAcross the literature from medical, computing, and health informatics fields, we identified 15 articles that presented a design or evaluation of a parent-facing health intervention. We found that using mobile-based systems to deliver health interventions was generally well accepted by parents of children aged <5 years. We also found that, when measured, parenting knowledge of early childhood health topics and confidence to engage in health-promoting behaviors improved. Design and evaluation methods held internal consistency within disciplines (eg, experimental study designs were the most prevalent in medical literature, while computing researchers used user-centered design methods in computing fields). However, there is little consistency in design or evaluation methods across fields.ConclusionsTo support more interventions with a comprehensive design and evaluation process, we recommend attention to design at the intervention (eg, reporting content sources) and system level; interdisciplinary collaboration in early childhood health intervention development can lead to large-scale deployment and success among populations.Trial RegistrationPROSPERO CRD42022359797; https://tinyurl.com/586nx9a2

De-identified data quality assessment approaches by data vendors who license data to healthcare and life sciences researchers.

To gain insights into how data vendor companies (DVs), an important source of de-identified/anonymized licensed patient-related data (D/ALD) used in clinical informatics research in life sciences and the pharmaceutical industry, characterize, conduct, and communicate data quality assessments to researcher purchasers of D/ALD. A qualitative study with interviews of DVs executives and decision-makers in data quality assessments (n = 12) and content analysis of interviews transcripts. Data quality, from the perspective of DVs, is characterized by how it is defined, validated, and processed. DVs identify data quality as the main contributor to successful collaborations with life sciences/pharmaceutical research partners. Data quality feedback from clients provides the basis for DVs reviews and inspections of quality processes. DVs value customer interactions, view collaboration, shared common goals, mutual expertise, and communication related to data quality as success factors. Data quality evaluation practices are important. However, no uniform DVs industry standards for data quality assessment were identified. DVs describe their orientation to data quality evaluation as a direct result of not only the complex nature of data sources, but also of techniques, processes, and approaches used to construct data sets. Because real-world data (RWD), eg, patient data from electronic medical records, is used for real-world evidence (RWE) generation, the use of D/ALD will expand and require refinement. The focus on (and rigor in) data quality assessment (particularly in research necessary to make regulatory decisions) will require more structure, standards, and collaboration between DVs, life sciences/pharmaceutical, informaticists, and RWD/RWE policy-making stakeholders.

About The Author

About The Author

A Novel 3D Unsupervised Domain Adaptation Framework for Cross-Modality Medical Image Segmentation.

We consider the problem of volumetric (3D) unsupervised domain adaptation (UDA) in cross-modality medical image segmentation, aiming to perform segmentation on the unannotated target domain (e.g. MRI) with the help of labeled source domain (e.g. CT). Previous UDA methods in medical image analysis usually suffer from two challenges: 1) they focus on processing and analyzing data at 2D level only, thus missing semantic information from the depth level; 2) one-to-one mapping is adopted during the style-transfer process, leading to insufficient alignment in the target domain. Different from the existing methods, in our work, we conduct a first of its kind investigation on multi-style image translation for complete image alignment to alleviate the domain shift problem, and also introduce 3D segmentation in domain adaptation tasks to maintain semantic consistency at the depth level. In particular, we develop an unsupervised domain adaptation framework incorporating a novel quartet self-attention module to efficiently enhance relationships between widely separated features in spatial regions on a higher dimension, leading to a substantial improvement in segmentation accuracy in the unlabeled target domain. In two challenging cross-modality tasks, specifically brain structures and multi-organ abdominal segmentation, our model is shown to outperform current state-of-the-art methods by a significant margin, demonstrating its potential as a benchmark resource for the biomedical and health informatics research community.

Using Jupyter Tools to Design an Interactive Textbook to Guide Undergraduate Research in Materials Informatics

With the growing desire to incorporate data science and informatics into STEM curricula, there is an opportunity to integrate research-based software and tools (e.g., Python) within existing pedagogical methods to craft new, accessible learning experiences. We show how the open-source Jupyter Book software can achieve this goal by creating a digital, interactive textbook compiled from Jupyter notebooks, which are already commonplace in research. Using Jupyter Book, we design an open-source, introductory materials informatics research curriculum where the Python programming exercises are supplemented with prose, graphics, slides, and discussion questions, all of which are embedded into a uniform web interface for streamlined access. Interactive programming capabilities, enabled through the JupyterHub cloud infrastructure, provide opportunities in these digital spaces for students to interrogate the code, test their own hypotheses, and deepen their comprehension. These authentic learning experiences demonstrate the broad utility of the Jupyter ecosystem in sustaining the growth of materials informatics education.

Sharing Species Pages through Living Atlases using Plinian Core: Current state and new developments

Living Atlases (living-atlases.gbif.org) is a community of developers and organizations built around the software platform developed by the Atlas of Living Australia (ALA, ala.org.au). ALA includes a number of open source reusable modules designed to assemble biodiversity data portals. Nowadays, more than 25 institutional and national biodiversity portals around the world have been implemented with the ALA tools (living-atlases.gbif.org/participants). The community organizes workshops and prepares training materials to present ALA modules to other institutions that want to implement it, to improve already existing portals and to learn from each other’s achievements (living-atlases.gbif.org/about). ALA based portals integrate data from multiple sources using biodiversity data standards ruled by TDWG, such as Darwin Core for species occurrences. The Living Atlases community is working in the integration of other data types, like species records and sampling events. Plinian Core (PliC) is a generalistic specification, oriented to share descriptions and nomenclature, as well as many other aspects (e.g. legal, conservation, and management details) of species level information from local and regional sources (Pando 2018). Following several years of development and earlier versions, PliC version 3.1 was made publicly available in 2012. The following year, after the approval of the “Species Information Interest Group'' by the TDWG Executive, a TDWG Task Group was created to start aligning Plinian Core with the TDWG Standards Documentation Standard (SDS). Several full-fledged implementations of Plinian Core were produced, between 2014 and 2019, including the Atlas of Living Costa Rica (CRBio.cr), the Cross-Nature Project (datos.iepnb.es), the Vasque Country (Spain) Official Nature Information System (ivap.euskadi.eus), the Colombian Biodiversity Catalog (catalogo.biodiversidad.co) and Enciclovida (Mexican Species Catalog, enciclovida.mx). These last three years, the Plinian Core Task Group has reviewed definitions of terms and formal declarations, assisted by the TDWG Technical Architecture Group (TAG), with the objective of ratifying PliC as a TDWG Standard. One of the most used tools to share standardized biodiversity data is the GBIF Integrated Publishing Toolkit (IPT, gbif.org/en/ipt). The IPT is an open source web application that allows institutions to standardize, to publish and share biodiversity data sets through Living Atlases, GBIF, and other biodiversity networks. The toolkit simplifies the process of publishing core data types (e.g. taxon occurrence, taxon checklists, sampling event) and, by means of extensions, it is possible to associate additional data with records of the core type. As part of our project, the extensions of PliC, accessible in the IPT Sandbox, were validated to show how they can be used by institutions to publish species pages through the IPT. In order to fully integrate Plinian Core based species pages into the ALA architecture, the Biodiversity Informatics Research Center (CRBio) has been working on the adoption of the Biodiversity Information Explorer (BIE), an ALA module which manages taxonomic and species contents by integrating global resources like EOL or Wikipedia. This adoption includes the required modifications of the Portal codebase to use the data model of the Plinian Core (github.com/tdwg/PlinianCore) to display a much richer content. This year, with assistance from the Capacity Enhancement Support Programme (CESP) from GBIF, we have revisited the integration of species pages information and expanded the content and type of information provided by the Atlas of Living Costa Rica. We present here the updated ALA Species Pages (ALA-BIE) and Index (BIE-Index) Modules and general documentation that could be applied to any ALA installation in order to prepare species records using the IPT and PliC standard, index and display them through the ALA-BIE Module.

MEDIC: a multi-task learning dataset for disaster image classification

Recent research in disaster informatics demonstrates a practical and important use case of artificial intelligence to save human lives and suffering during natural disasters based on social media contents (text and images). While notable progress has been made using texts, research on exploiting the images remains relatively under-explored. To advance image-based approaches, we propose MEDIC (https://crisisnlp.qcri.org/medic/index.html), which is the largest social media image classification dataset for humanitarian response consisting of 71,198 images to address four different tasks in a multi-task learning setup. This is the first dataset of its kind: social media images, disaster response, and multi-task learning research. An important property of this dataset is its high potential to facilitate research on multi-task learning, which recently receives much interest from the machine learning community and has shown remarkable results in terms of memory, inference speed, performance, and generalization capability. Therefore, the proposed dataset is an important resource for advancing image-based disaster management and multi-task machine learning research. We experiment with different deep learning architectures and report promising results, which are above the majority baselines for all tasks. Along with the dataset, we also release all relevant scripts (https://github.com/firojalam/medic).

Interdisciplinary Informatics to Support Primary Care Sentinel Surveillance of Respiratory Infectious Disease Including COVID-19: Donabedian Evaluation.

The Oxford-Royal College of General Practitioners (RCGP) Research and Surveillance Centre (RSC) is one of Europe's oldest sentinel systems, providing sentinel surveillance since 1967. We report the interdisciplinary informatics required to run such a system. We used the Donabedian framework to describe the interdisciplinary informatics roles that support the structures, processes and outcomes of the RSC. Over the course of the COVID-19 pandemic University, RCGP, information technology specialists, SQL developers, analysts, practice liaison team, network member primary care providers, and their registered patients have nearly quadrupled the size of the RSC from working with 5 million to 19 million peoples pseudonymised health data. We have produced outputs used by the UK Health Security Agency to describe the epidemiology of COVID-19 and report vaccine effectiveness. We have also supported a trial of community-based therapies for COVID-19 and other observational studies. The home of the primary care sentinel surveillance network is with a clinical informatics research group. Interdisciplinary informatics teamwork was required to support primary care sentinel surveillance; such teams can accelerate the scale, scope and digital maturity of surveillance systems as demonstrated by the RSC across the COVID-19 pandemic.

Comprehension, utility, and preferences of prostate cancer survivors for visual timelines of patient-reported outcomes co-designed for limited graph literacy: meters and emojis over comics.

Visual timelines of patient-reported outcomes (PRO) can help prostate cancer survivors manage longitudinal data, compare with population averages, and consider future trajectories. PRO visualizations are most effective when designed with deliberate consideration of users. Yet, graph literacy is often overlooked as a design constraint, particularly when users with limited graph literacy are not engaged in their development. We conducted user testing to assess comprehension, utility, and preference of longitudinal PRO visualizations designed for prostate cancer survivors with limited literacy. Building upon our prior work co-designing longitudinal PRO visualizations with survivors, we engaged 18 prostate cancer survivors in a user study to assess 4 prototypes: Meter, Words, Comic, and Emoji. During remote sessions, we collected data on prototype comprehension (gist and verbatim), utility, and preference. Participants were aged 61-77 (M = 69), of whom half were African American. The majority of participants had less than a college degree (95%), had inadequate health literacy (78%), and low graph literacy (89%). Among the 4 prototypes, Meter had the best gist comprehension and was preferred. Emoji was also preferred, had the highest verbatim comprehension, and highest rated utility, including helpfulness, confidence, and satisfaction. Meter and Words both rated mid-range for utility, and Words scored lower than Emoji and Meter for comprehension. Comic had the poorest comprehension, lowest utility, and was least preferred. Findings identify design considerations for PRO visualizations, contributing to the knowledge base for visualization best practices. We describe our process to meaningfully engage patients from diverse and hard-to-reach groups for remote user testing, an important endeavor for health equity in biomedical informatics. Graph literacy is an important design consideration for PRO visualizations. Biomedical informatics researchers should be intentional in understanding user needs by involving diverse and representative individuals during development.

Neighborhood-based analysis of adolescent hidradenitis suppurativa prevalence in a large metropolitan area

Neighborhood-based analysis of adolescent hidradenitis suppurativa prevalence in a large metropolitan area

Preliminary comparison of gun homicide deaths for non-probation and probation clients.

ObjectiveTo measure a baseline rate of gun homicide deaths for adults on probation in Cook County, Illinois, USA. To compare this rate to the rates for the population of the City of Chicago and for all of Cook County, which includes Chicago and suburban Cook County. ApproachIn March of 2022, two data contributing partners, Cook County Adult Probation Department (APD) and Cook County Medical Examiner’s Office (CCME), partnered with Cook County Health for salt and crypto generation and the Medical Research Analytics and Informatics Alliance (MRAIA) as the data generator. We used the open source Linkja program (https://linkja.github.io/) to match adult probation records with gun homicide death records from CCME. For our study period, CY 2018 through 2021, APD submitted a hashed roster of 53,969 unique individuals active on probation, which was matched to 307 records of gun homicide deaths. ResultsOverall, there were 3,728 gun homicides in the CCME data, 8% (n=307) involved individuals on probation. The average age was 34 years at death, almost 91% were male (n=3,374), 71% Black (n=2,650), and 14% Hispanic (n=536). Among individuals who died from gun violence, compared to those not in the probation data, probation clients tended to be younger (29 vs 33, p&lt;.001) and more likely to be Black (89% vs. 69.5%; p&lt;.001), We found that the rate of gun homicide deaths per 100,000 probation clients was 569, ~22 times higher than the rate for the City of Chicago in 2020 (rate=25 per 100,000) and ~33 times higher than the rate for Cook County in 2020 (rate=17 per 100,000). ConclusionPrivacy-preserving record linkage software enabled a cross-departmental data sharing project that heretofore was not realized due to privacy concerns and existing data use agreements. Our results highlight an excessive risk of homicide among adult probation clients, particularly among young black males.

Successful operational integration of healthcare analytics at Seattle Children's.

As the quantity and complexity of health data grows, it is critical for healthcare organizations to devise analytic strategies that power data innovation so they can take advantage of new opportunities and improve outcomes. Seattle Children's Healthcare System (Seattle Children's) is an example of an organization that has built an operating model that integrates analytics into their business and daily operations. We present a roadmap for how Seattle Children's consolidated its fragmented analytics operations into a unified cohesive ecosystem capable of supporting advanced analytics capabilities and operational integration to transform care and accelerate research. In-depth interviews were conducted with ten leaders at Seattle Children's who have been instrumental in developing their enterprise analytics program. Interviews included the following leadership roles: Chief Data & Analytics Officer, Director of Research Informatics, Principal Systems Architect, Manager of Bioinformatics and High Throughput Analytics, Director of Neurocritical Care, Strategic Program Manager & Neuron Product Development Lead, Director of Dev Ops,Director of Clinical Analytics, Data Science Manager, and Advance Analytics Product Engineer. The interviews were unstructured and consisted of conversations intended to gather information from leadership about their experiences in building out Enterprise Analytics at Seattle Children's. Seattle Children's has built an advanced enterprise analytics ecosystem that is integrated into its daily operations by applying an entrepreneurial mindset and agile development practices that are common in a startup environment. Analytics efforts were approached iteratively by selecting high-value projects that were delivered through Multidisciplinary Delivery Teams that were integrated into service lines. Service line leadership, in partnership with the Delivery Team leads, were responsible for the success of the team by setting project priorities, determining project budgets, and maintaining overall governance of their analytics endeavors. This organizational structure has led to the development of a wide range of analytic products that have been used to improve both operations and clinical care at Seattle Children's. Seattle Children's has demonstrated how a leading healthcare system can successfully create a robust, scalable, near real-time analytics ecosystem- one that delivers significant value to the organization from the ever-expanding volume of health data we see today.

Engaging the disability community in informatics research: rationales and practical steps.

As the informatics community grows in its ability to address health disparities, there is an opportunity to expand our impact by focusing on the disability community as a health disparity population. Although informaticians have primarily catered design efforts to one disability at a time, digital health technologies can be enhanced by approaching disability from a more holistic framework, simultaneously accounting for multiple forms of disability and the ways disability intersects with other forms of identity. The urgency of moving toward this more holistic approach is grounded in ethical, legal, and design-related rationales. Shaped by our research and advocacy with the disability community, we offer a set of guidelines for effective engagement. We argue that such engagement is critical to creating digital health technologies which more fully meet the needs of all disabled individuals.

How the VA is training the Next-Generation workforce for learning health systems.

ObjectivesThe U.S. Department of Veterans Affairs (VA) has been a national leader in Learning Health System (LHS) implementation due to its combined mission of research, education, clinical care, and emergency preparedness. We describe the current VA LHS training ecosystem within the Veterans Health Administration's Office of Academic Affiliations (OAA), Office of Research and Development (ORD), ORD's Health Services Research and Development (HSR&D) program, and Innovation Ecosystem (IE), including lessons learned regarding their sustainment.MethodsThe VA LHS training ecosystem is based on the Learning Loop and HSR&D Quality Enhancement Research Initiative (QUERI) Roadmap, which describes VA learning opportunities, underlying infrastructures, and core competencies.ResultsVA‐focused LHS educational programs include data‐to‐knowledge initiatives in health sciences and analytics, for example, OAA/HSR&D health services and informatics research fellowships; knowledge‐to‐performance opportunities in implementation and quality improvement, for example, QUERI Learning Hubs and IEs' Diffusion of Excellence Initiative; and performance‐to‐data embedded opportunities, for example, IE's entrepreneur fellowship programs and QUERI's Advancing Diversity in Implementation Leadership. These training programs are supported by combined VA research and clinical operations investments in funding, informatics, governance, and processes. Lessons learned include ongoing alignment of research funding with operational priorities and capacity, relentless recruitment and retention of implementation, system, and information scientists especially from under‐represented groups, sustainment of data infrastructures suitable for research and quality improvement, and ensuring sustainable funding opportunities for researchers to work on system‐wide health care problems.ConclusionsThere is an urgent need to expand training opportunities in LHSs, especially as health care is increasingly driven by multiple interested parties, impacted by persistent health disparities exacerbated by emerging public health threats, and rapid technology growth. With ongoing alignment of research and clinical goals, foundational support through research funding, underlying clinical operations infrastructures, and active engagement interested parties, VA's LHS training ecosystem promotes a more LHS‐savvy, 21st century workforce.