Learning From Past Respiratory Infections to Predict COVID-19 Outcomes: Retrospective Study

BACKGROUND

For the clinical care of patients with well-established diseases, randomized trials, literature, and research are supplemented with clinical judgment to understand disease prognosis and inform treatment choices. In the void created by a lack of clinical experience with COVID-19, artificial intelligence (AI) may be an important tool to bolster clinical judgment and decision making. However, a lack of clinical data restricts the design and development of such AI tools, particularly in preparation for an impending crisis or pandemic.

OBJECTIVE

This study aimed to develop and test the feasibility of a "patients-like-me" framework to predict the deterioration of patients with COVID-19 using a retrospective cohort of patients with similar respiratory diseases.

METHODS

Our framework used COVID-19-like cohorts to design and train AI models that were then validated on the COVID-19 population. The COVID-19-like cohorts included patients diagnosed with bacterial pneumonia, viral pneumonia, unspecified pneumonia, influenza, and acute respiratory distress syndrome (ARDS) at an academic medical center from 2008 to 2019. In total, 15 training cohorts were created using different combinations of the COVID-19-like cohorts with the ARDS cohort for exploratory purposes. In this study, two machine learning models were developed: one to predict invasive mechanical ventilation (IMV) within 48 hours for each hospitalized day, and one to predict all-cause mortality at the time of admission. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, positive predictive value, and negative predictive value. We established model interpretability by calculating SHapley Additive exPlanations (SHAP) scores to identify important features.

RESULTS

Compared to the COVID-19-like cohorts (n=16,509), the patients hospitalized with COVID-19 (n=159) were significantly younger, with a higher proportion of patients of Hispanic ethnicity, a lower proportion of patients with smoking history, and fewer patients with comorbidities (P<.001). Patients with COVID-19 had a lower IMV rate (15.1 versus 23.2, P=.02) and shorter time to IMV (2.9 versus 4.1 days, P<.001) compared to the COVID-19-like patients. In the COVID-19-like training data, the top models achieved excellent performance (AUROC>0.90). Validating in the COVID-19 cohort, the top-performing model for predicting IMV was the XGBoost model (AUROC=0.826) trained on the viral pneumonia cohort. Similarly, the XGBoost model trained on all 4 COVID-19-like cohorts without ARDS achieved the best performance (AUROC=0.928) in predicting mortality. Important predictors included demographic information (age), vital signs (oxygen saturation), and laboratory values (white blood cell count, cardiac troponin, albumin, etc). Our models had class imbalance, which resulted in high negative predictive values and low positive predictive values.

CONCLUSIONS

We provided a feasible framework for modeling patient deterioration using existing data and AI technology to address data limitations during the onset of a novel, rapidly changing pandemic.

Predictive Maintenance in Building Facilities: A Machine Learning-Based Approach

The operation and maintenance of buildings has seen several advances in recent years. Multiple information and communication technology (ICT) solutions have been introduced to better manage building maintenance. However, maintenance practices in buildings remain less efficient and lead to significant energy waste. In this paper, a predictive maintenance framework based on machine learning techniques is proposed. This framework aims to provide guidelines to implement predictive maintenance for building installations. The framework is organised into five steps: data collection, data processing, model development, fault notification and model improvement. A sport facility was selected as a case study in this work to demonstrate the framework. Data were collected from different heating ventilation and air conditioning (HVAC) installations using Internet of Things (IoT) devices and a building automation system (BAS). Then, a deep learning model was used to predict failures. The case study showed the potential of this framework to predict failures. However, multiple obstacles and barriers were observed related to data availability and feedback collection. The overall results of this paper can help to provide guidelines for scientists and practitioners to implement predictive maintenance approaches in buildings.

Multicenter data to improve health for pediatric renal transplant recipients in North America: Complementary approaches of NAPRTCS and IROC

Kidney transplantation increases life expectancy and improves quality of life for children with end-stage kidney disease, yet sequelae of transplantation and treatment make it difficult for transplant recipients to enjoy health and quality of life similar to their healthy peers. The NAPRTCS network was among the first to use multicenter data to inform improvements in care and outcomes for children with a kidney transplant through observational research. Now, with new technologies and unprecedented access to data, it is possible to create learning health systems as envisioned by the US National Academy of Sciences to seamlessly integrate research and continuous improvement of clinical care. In this review, we present two pre-eminent North American networks focused on using multicenter data to drive improved care and outcomes for children with a kidney transplant. Whereas, for the past 30 years NAPRTCS has focused on discovery of best practices through observational research and clinical trials, the Improving Renal Outcomes Collaborative, established in 2016, engages patients, families, clinicians, and researchers in redesigning the healthcare delivery system to enable practice change and continuous improvement of health outcomes. We discuss the history and past contributions of these networks, as well as current activities, barriers, and potential future solutions to more fully realize the vision of a true learning health system for pediatric kidney transplant recipients.

Federated learning: a collaborative effort to achieve better medical imaging models for individual sites that have small labelled datasets

Despite the overall success of using artificial intelligence (AI) to assist radiologists in performing computer-aided patient diagnosis, it remains challenging to build good models with small datasets at individual sites. Because many medical images do not come with proper labelling for training, this requires radiologists to perform strenuous labelling work and to prepare the dataset for training. Placing such demands on radiologists is unsustainable, given the ever-increasing number of medical images taken each year. We propose an alternative solution using a relatively new learning framework. This framework, called federated learning, allows individual sites to train a global model in a collaborative effort. Federated learning involves aggregating training results from multiple sites to create a global model without directly sharing datasets. This ensures that patient privacy is maintained across sites. Furthermore, the added supervision obtained from the results of partnering sites improves the global model's overall detection abilities. This alleviates the issue of insufficient supervision when training AI models with small datasets. Lastly, we also address the major challenges of adopting federated learning.

Biosignal Compression Toolbox for Digital Biomarker Discovery

A critical challenge to using longitudinal wearable sensor biosignal data for healthcare applications and digital biomarker development is the exacerbation of the healthcare "data deluge," leading to new data storage and organization challenges and costs. Data aggregation, sampling rate minimization, and effective data compression are all methods for consolidating wearable sensor data to reduce data volumes. There has been limited research on appropriate, effective, and efficient data compression methods for biosignal data. Here, we examine the application of different data compression pipelines built using combinations of algorithmic- and encoding-based methods to biosignal data from wearable sensors and explore how these implementations affect data recoverability and storage footprint. Algorithmic methods tested include singular value decomposition, the discrete cosine transform, and the biorthogonal discrete wavelet transform. Encoding methods tested include run-length encoding and Huffman encoding. We apply these methods to common wearable sensor data, including electrocardiogram (ECG), photoplethysmography (PPG), accelerometry, electrodermal activity (EDA), and skin temperature measurements. Of the methods examined in this study and in line with the characteristics of the different data types, we recommend direct data compression with Huffman encoding for ECG, and PPG, singular value decomposition with Huffman encoding for EDA and accelerometry, and the biorthogonal discrete wavelet transform with Huffman encoding for skin temperature to maximize data recoverability after compression. We also report the best methods for maximizing the compression ratio. Finally, we develop and document open-source code and data for each compression method tested here, which can be accessed through the Digital Biomarker Discovery Pipeline as the "Biosignal Data Compression Toolbox," an open-source, accessible software platform for compressing biosignal data.

A performance-based measure of emotion response control: A preliminary MRI study

Identifying performance-based assessments of emotion regulation is needed for the study of myriad mood and neurological disorders. Color and form responses on the Rorschach Inkblot Method are valid measures of emotion response control, but have not been studied in relation to known neural correlations of emotion regulation. A discrepancy of color (CF + C) greater than form (FC) responses suggests low cognitive control over emotional responses. This preliminary report explores the discrepancy between form-color responses as a correlate of regional cortical thickness. A sample of community-dwelling adults were administered the Rorschach Inkblot Method and participated in a structural MRI scan. Greater middle frontal cortex thickness was associated with a positive discrepancy score [(CF + C) - FC], indicating less emotion response control (r_s  = 0.48, p < 0.05); a moderate, non-significant correlation was also observed with insula cortex (r_s  = 0.42, p = 0.07).The results provide evidence in support of the Rorschach Inkblot Method as a valid behavioral measure of emotion response control. More specifically, these results support the use of color-related variables included in contemporary evidence-based Rorschach methods. The results are discussed with implications for the study of emotion regulation in mood disorders and sensitivity analyses based on the observed effect sizes are reported to inform future study planning.

Lifelog Data-Based Prediction Model of Digital Health Care App Customer Churn: Retrospective Observational Study

Background

Customer churn is the rate at which customers stop doing business with an entity. In the field of digital health care, user churn prediction is important not only in terms of company revenue but also for improving the health of users. Churn prediction has been previously studied, but most studies applied time-invariant model structures and used structured data. However, additional unstructured data have become available; therefore, it has become essential to process daily time-series log data for churn predictions.

Objective

We aimed to apply a recurrent neural network structure to accept time-series patterns using lifelog data and text message data to predict the churn of digital health care users.

Methods

This study was based on the use data of a digital health care app that provides interactive messages with human coaches regarding food, exercise, and weight logs. Among the users in Korea who enrolled between January 1, 2017 and January 1, 2019, we defined churn users according to the following criteria: users who received a refund before the paid program ended and users who received a refund 7 days after the trial period. We used long short-term memory with a masking layer to receive sequence data with different lengths. We also performed topic modeling to vectorize text messages. To interpret the contributions of each variable to model predictions, we used integrated gradients, which is an attribution method.

Results

A total of 1868 eligible users were included in this study. The final performance of churn prediction was an F1 score of 0.89; that score decreased by 0.12 when the data of the final week were excluded (F1 score 0.77). Additionally, when text data were included, the mean predicted performance increased by approximately 0.085 at every time point. Steps per day had the largest contribution (0.1085). Among the topic variables, poor habits (eg, drinking alcohol, overeating, and late-night eating) showed the largest contribution (0.0875).

Conclusions

The model with a recurrent neural network architecture that used log data and message data demonstrated high performance for churn classification. Additionally, the analysis of the contribution of the variables is expected to help identify signs of user churn in advance and improve the adherence in digital health care.

Development and implementation of common data elements for venous thromboembolism research: on behalf of SSC Subcommittee on official Communication from the SSC of the ISTH

Clinical research in venous thromboembolism (VTE) is hindered by variability in the collection and reporting of data and outcomes. A consistent data language facilitates efficiencies, leads to higher quality data, and permits between-study comparisons and evidence synthesis. The International Society on Thrombosis and Haemostasis (ISTH) launched an international task force of more than 50 researchers to develop common data elements for clinical research in venous thromboembolism. The project was organized in seven working groups, each focusing on a topic area: General Core Data Elements; Anticoagulation and Other Therapies; Chronic VTE and Functional Outcomes; Diagnosis of VTE; Malignancy; Perioperative; and Predictors of VTE. The groups met via teleconference to collaboratively identify key data elements and develop definitions and data standards that were structured in a project-specific taxonomy. A Steering Committee met by teleconference and in-person to determine the overall scope of the project and resolve questions arising from the working groups. ISTH held an open public comment period to enable broader stakeholder involvement and feedback. The common data elements were then refined by the working groups to create a set of 512 unique data elements that are publicly available at http://isth.breakthrough.healthcare. The ISTH VTE Common Data Elements are intended to be a living project with ongoing curation, future expansion, and adaptation to meet the needs of the thrombosis and hemostasis research community.

Governing secondary research use of health data and specimens: the inequitable distribution of regulatory burden between federally funded and industry research

Some of the most promising recent advances in health research offer opportunities to improve diagnosis and therapy for millions of patients. They also require access to massive collections of health data and specimens. This need has generated an aggressive and lucrative push toward amassing troves of human data and biospecimens within academia and private industry. But the differences between the strict regulations that govern federally funded researchers in academic medical centers (AMCs) versus those that apply to the collection of health data and specimens by industry can entrench disparities. This article will discuss the value of secondary research with data and specimens and analyze why AMCs have been put at a disadvantage as compared to industry in amassing the large datasets that enable this work. It will explore the limitations of this current governance structure and propose that, moving forward, AMCs should set their own standards for commercialization of the data and specimens they generate in-house, the ability of their researchers to use industry data for their own work, and baseline informed consent standards for their own patients in order to ensure future data accessibility.

Computational medicine, present and the future: obstetrics and gynecology perspective

Medicine is, in its essence, decision making under uncertainty; the decisions are made about tests to be performed and treatments to be administered. Traditionally, the uncertainty in decision making was handled using expertise collected by individual providers and, more recently, systematic appraisal of research in the form of evidence-based medicine. The traditional approach has been used successfully in medicine for a very long time. However, it has substantial limitations because of the complexity of the system of the human body and healthcare. The complex systems are a network of highly coupled components intensely interacting with each other. These interactions give those systems redundancy and thus robustness to failure and, at the same time, equifinality, that is, many different causative pathways leading to the same outcome. The equifinality of the complex systems of the human body and healthcare system demand the individualization of medical care, medicine, and medical decision making. Computational models excel in modeling complex systems and, consequently, enabling individualization of medical decision making and medicine. Computational models are theory- or knowledge-based models, data-driven models, or models that combine both approaches. Data are essential, although to a different degree, for computational models to successfully represent complex systems. The individualized decision making, made possible by the computational modeling of complex systems, has the potential to revolutionize the entire spectrum of medicine from individual patient care to policymaking. This approach allows applying tests and treatments to individuals who receive a net benefit from them, for whom benefits outweigh the risk, rather than treating all individuals in a population because, on average, the population benefits. Thus, the computational modeling-enabled individualization of medical decision making has the potential to both improve health outcomes and decrease the costs of healthcare.

Beyond ecosystem modeling: A roadmap to community cyberinfrastructure for ecological data-model integration

In an era of rapid global change, our ability to understand and predict Earth's natural systems is lagging behind our ability to monitor and measure changes in the biosphere. Bottlenecks to informing models with observations have reduced our capacity to fully exploit the growing volume and variety of available data. Here, we take a critical look at the information infrastructure that connects ecosystem modeling and measurement efforts, and propose a roadmap to community cyberinfrastructure development that can reduce the divisions between empirical research and modeling and accelerate the pace of discovery. A new era of data-model integration requires investment in accessible, scalable, and transparent tools that integrate the expertise of the whole community, including both modelers and empiricists. This roadmap focuses on five key opportunities for community tools: the underlying foundations of community cyberinfrastructure; data ingest; calibration of models to data; model-data benchmarking; and data assimilation and ecological forecasting. This community-driven approach is a key to meeting the pressing needs of science and society in the 21st century.

Drug induced stuttering: pharmacovigilance data

Background: Stuttering is a speech disorder characterized by poor fluency of speech despite the speech production organs being normal. Numerous factors contribute to stuttering, and it may also be an iatrogenic effect of certain drugs. The aim of this study was to investigate the association between stuttering and drug exposure.Research design and methods: We investigated the association between drugs and stuttering. We analyzed reports in the World Health Organization global individual case safety reports database (Vigibase) up to 31 May 2020 with the MedDRA lower level terms 'stutter' and 'stuttering.' The association between a drug and the occurrence of the adverse drug reaction was estimated by disproportionality analysis. Reporting odds ratios (ROR) were calculated with 95% confidence intervals.Results: In total, 724 notifications were identified using the MedDRA terms selected. The main drugs implicated were methylphenidate (ROR = 19.58; 95% CI: 13.3-28.8), topiramate (ROR = 12.5; 95% CI: 7.1-22.1), olanzapine (ROR = 12; 95% CI: 8-17.9) and golimumab (ROR = 10.2; 95% CI: 5.5-19.1).Conclusions: When stuttering occurs in a patient treated by drugs affecting neurotransmission, a drug-induced origin of the stutter should be considered.

Reduction of COVID-19 Incidence and Nonpharmacologic Interventions: Analysis Using a US County-Level Policy Data Set

BACKGROUND

Worldwide, nonpharmacologic interventions (NPIs) have been the main tool used to mitigate the COVID-19 pandemic. This includes social distancing measures (closing businesses, closing schools, and quarantining symptomatic persons) and contact tracing (tracking and following exposed individuals). While preliminary research across the globe has shown these policies to be effective, there is currently a lack of information on the effectiveness of NPIs in the United States.

OBJECTIVE

The purpose of this study was to create a granular NPI data set at the county level and then analyze the relationship between NPI policies and changes in reported COVID-19 cases.

METHODS

Using a standardized crowdsourcing methodology, we collected time-series data on 7 key NPIs for 1320 US counties.

RESULTS

This open-source data set is the largest and most comprehensive collection of county NPI policy data and meets the need for higher-resolution COVID-19 policy data. Our analysis revealed a wide variation in county-level policies both within and among states (P<.001). We identified a correlation between workplace closures and lower growth rates of COVID-19 cases (P=.004). We found weak correlations between shelter-in-place enforcement and measures of Democratic local voter proportion (R=0.21) and elected leadership (R=0.22).

CONCLUSIONS

This study is the first large-scale NPI analysis at the county level demonstrating a correlation between NPIs and decreased rates of COVID-19. Future work using this data set will explore the relationship between county-level policies and COVID-19 transmission to optimize real-time policy formulation.

Evaluating the Alzheimer's disease data landscape

INTRODUCTION

Numerous studies have collected Alzheimer's disease (AD) cohort data sets. To achieve reproducible, robust results in data-driven approaches, an evaluation of the present data landscape is vital.

METHODS

Previous efforts relied exclusively on metadata and literature. Here, we evaluate the data landscape by directly investigating nine patient-level data sets generated in major clinical cohort studies.

RESULTS

The investigated cohorts differ in key characteristics, such as demographics and distributions of AD biomarkers. Analyzing the ethnoracial diversity revealed a strong bias toward White/Caucasian individuals. We described and compared the measured data modalities. Finally, the available longitudinal data for important AD biomarkers was evaluated. All results are explorable through our web application ADataViewer (https://adata.scai.fraunhofer.de).

DISCUSSION

Our evaluation exposed critical limitations in the AD data landscape that impede comparative approaches across multiple data sets. Comparison of our results to those gained by metadata-based approaches highlights that thorough investigation of real patient-level data is imperative to assess a data landscape.

Estimating assistive product need in Cameroon and India: results of population-based surveys and comparison of self-report and clinical impairment assessment approaches

OBJECTIVES

To estimate population need and coverage for distance glasses, hearing aids and wheelchairs in India and Cameroon, and to explore the relationship between assistive product (AP) need measured through self-report and clinical impairment assessment.

METHODS

Population-based surveys of approximately 4000 people each were conducted in Mahabubnagar district, India and Fundong district, Cameroon. Participants underwent standardised vision, hearing and musculoskeletal impairment assessment to assess need for distance glasses, hearing aids, wheelchairs. Participants with moderate or worse impairment and/or self-reported difficulties in functioning were also asked about their self-reported AP need.

RESULTS

6.5% (95% CI 5.4-7.9) in India and 1.9% (95% CI 1.5-2.4) in Cameroon of the population needed at least one of the three APs based on moderate or worse impairments. Total need was highest for distance glasses [3.7% (95% CI 2.8-4.7) India; 0.8% (95% CI 0.5-1.1), Cameroon] and lowest for wheelchairs (0.1% both settings; 95% CI 0.03-0.3 India, 95% CI 0.04-0.3 Cameroon). Coverage for each AP was below 40%, except for distance glasses in India, where it was 87% (95% CI 77.1-93.0). The agreement between self-report and clinical impairment assessment of AP need was poor. For instance, in India, 60% of people identified through clinical assessment as needing distance glasses did not self-report a need. Conversely, in India, 75% of people who self-reported needing distance glasses did not require one based on clinical impairment assessment.

CONCLUSIONS

There is high need and low coverage of three APs in two low-and middle-income settings. Methodological shortcomings highlight the need for improved survey methods compatible with the international classification of functioning, disability and health to estimate population-level need for AP and related services to inform advocacy and planning.

Maintaining Privacy in Artificial Intelligence-driven Bioinformatics: An Inquiry into the Suitability of Australia's Laws

Since its humble origins in 1950, artificial intelligence (AI) has experienced exponential growth. In 2020 it seems that there is an AI for just about every aspect of life - from targeted advertising to minimally invasive surgery. It is generally thought that advancements in AI lead to advancements in human life. However, AI is an unprecedented form of technology with the ability to exceed human expectation and act in unexpected manners. This article considers the intersection between AI and bioinformatics with a particular focus on how artificial capabilities may affect the individual's right to privacy. A further question is raised as to whether current Australian laws are equipped to protect the individual's right to privacy, in light of artificial capabilities.

Public Perception of the COVID-19 Pandemic on Twitter: Sentiment Analysis and Topic Modeling Study

Background

COVID-19 is a scientifically and medically novel disease that is not fully understood because it has yet to be consistently and deeply studied. Among the gaps in research on the COVID-19 outbreak, there is a lack of sufficient infoveillance data.

Objective

The aim of this study was to increase understanding of public awareness of COVID-19 pandemic trends and uncover meaningful themes of concern posted by Twitter users in the English language during the pandemic.

Methods

Data mining was conducted on Twitter to collect a total of 107,990 tweets related to COVID-19 between December 13 and March 9, 2020. The analyses included frequency of keywords, sentiment analysis, and topic modeling to identify and explore discussion topics over time. A natural language processing approach and the latent Dirichlet allocation algorithm were used to identify the most common tweet topics as well as to categorize clusters and identify themes based on the keyword analysis.

Results

The results indicate three main aspects of public awareness and concern regarding the COVID-19 pandemic. First, the trend of the spread and symptoms of COVID-19 can be divided into three stages. Second, the results of the sentiment analysis showed that people have a negative outlook toward COVID-19. Third, based on topic modeling, the themes relating to COVID-19 and the outbreak were divided into three categories: the COVID-19 pandemic emergency, how to control COVID-19, and reports on COVID-19.

Conclusions

Sentiment analysis and topic modeling can produce useful information about the trends in the discussion of the COVID-19 pandemic on social media as well as alternative perspectives to investigate the COVID-19 crisis, which has created considerable public awareness. This study shows that Twitter is a good communication channel for understanding both public concern and public awareness about COVID-19. These findings can help health departments communicate information to alleviate specific public concerns about the disease.

From sequence to information

Today massive amounts of sequenced metagenomic and metatranscriptomic data from different ecological niches and environmental locations are available. Scientific progress depends critically on methods that allow extracting useful information from the various types of sequence data. Here, we will first discuss types of information contained in the various flavours of biological sequence data, and how this information can be interpreted to increase our scientific knowledge and understanding. We argue that a mechanistic understanding of biological systems analysed from different perspectives is required to consistently interpret experimental observations, and that this understanding is greatly facilitated by the generation and analysis of dynamic mathematical models. We conclude that, in order to construct mathematical models and to test mechanistic hypotheses, time-series data are of critical importance. We review diverse techniques to analyse time-series data and discuss various approaches by which time-series of biological sequence data have been successfully used to derive and test mechanistic hypotheses. Analysing the bottlenecks of current strategies in the extraction of knowledge and understanding from data, we conclude that combined experimental and theoretical efforts should be implemented as early as possible during the planning phase of individual experiments and scientific research projects.

This article is part of the theme issue ‘Integrative research perspectives on marine conservation’.

A Data Visualization and Dissemination Resource to Support HIV Prevention and Care at the Local Level: Analysis and Uses of the AIDSVu Public Data Resource

BACKGROUND

AIDSVu is a public resource for visualizing HIV surveillance data and other population-based information relevant to HIV prevention, care, policy, and impact assessment.

OBJECTIVE

The site, AIDSVu.org, aims to make data about the US HIV epidemic widely available, easily accessible, and locally relevant to inform public health decision making.

METHODS

AIDSVu develops visualizations, maps, and downloadable datasets using results from HIV surveillance systems, other population-based sources of information (eg, US Census and national probability surveys), and other data developed specifically for display and dissemination through the website (eg, pre-exposure prophylaxis [PrEP] prescriptions). Other types of content are developed to translate surveillance data into summarized content for diverse audiences using infographic panels, interactive maps, local and state fact sheets, and narrative blog posts.

RESULTS

Over 10 years, AIDSVu.org has used an expanded number of data sources and has progressively provided HIV surveillance and related data at finer geographic levels, with current data resources providing HIV prevalence data down to the census tract level in many of the largest US cities. Data are available at the county level in 48 US states and at the ZIP Code level in more than 50 US cities. In 2019, over 500,000 unique users consumed AIDSVu data and resources, and HIV-related data and insights were disseminated through nearly 4,000,000 social media posts. Since AIDSVu's inception, at least 249 peer-reviewed publications have used AIDSVu data for analyses or referenced AIDSVu resources. Data uses have included targeting of HIV testing programs, identifying areas with inequitable PrEP uptake, including maps and data in academic and community grant applications, and strategically selecting locations for new HIV treatment and care facilities to serve high-need areas.

CONCLUSIONS

Surveillance data should be actively used to guide and evaluate public health programs; AIDSVu translates high-quality, population-based data about the US HIV epidemic and makes that information available in formats that are not consistently available in surveillance reports. Bringing public health surveillance data to an online resource is a democratization of data, and presenting information about the HIV epidemic in more visual formats allows diverse stakeholders to engage with, understand, and use these important public health data to inform public health decision making.

Opportunities and Challenges Surrounding the Use of Data From Wearable Sensor Devices in Health Care: Qualitative Interview Study

BACKGROUND

Wearable sensors connected via networked devices have the potential to generate data that may help to automate processes of care, engage patients, and increase health care efficiency. The evidence of effectiveness of such technologies is, however, nascent and little is known about unintended consequences.

OBJECTIVE

Our objective was to explore the opportunities and challenges surrounding the use of data from wearable sensor devices in health care.

METHODS

We conducted a qualitative, theoretically informed, interview-based study to purposefully sample international experts in health care, technology, business, innovation, and social sciences, drawing on sociotechnical systems theory. We used in-depth interviews to capture perspectives on development, design, and use of data from wearable sensor devices in health care, and employed thematic analysis of interview transcripts with NVivo to facilitate coding.

RESULTS

We interviewed 16 experts. Although the use of data from wearable sensor devices in health and care has significant potential in improving patient engagement, there are a number of issues that stakeholders need to negotiate to realize these benefits. These issues include the current gap between data created and meaningful interpretation in health and care contexts, integration of data into health care professional decision making, negotiation of blurring lines between consumer and medical care, and pervasive monitoring of health across previously disconnected contexts.

CONCLUSIONS

Stakeholders need to actively negotiate existing challenges to realize the integration of data from wearable sensor devices into electronic health records. Viewing wearables as active parts of a connected digital health and care infrastructure, in which various business, personal, professional, and health system interests align, may help to achieve this.

The Politics, Promises, and Perils of Data: Evidence-Driven Policy and Practice for Menstrual Health

Data determine what we know about the menstrual cycle; they inform policy and program decisions; they can point us to neglected issues and populations. But collecting and analyzing data are complicated and often fraught processes, because data are political and subjective, decisions on what data we collect and what data we do not collect are not determined by accident. As a result, despite the significant potential of the current rise in attention to menstruation, we also see risks: a lack of a solid evidence base for program decisions and resulting sensationalization; concerns about data privacy; an overreliance on participants' recall, on the one hand, while not involving participants adequately in decision making, on the other hand; and a lack of contextualized and disaggregated data. Yet better communication, contextualization, and collaboration can address many of these risks.

Negotiated Sharing of Pandemic Data, Models, and Resources

Urgent responses to the COVID-19 pandemic depend on increased collaboration and sharing of data, models, and resources among scientists and researchers. In many scientific fields and disciplines, institutional norms treat data, models, and resources as proprietary, emphasizing competition among scientists and researchers locally and internationally. Concurrently, long-standing norms of open data and collaboration exist in some scientific fields and have accelerated within the last two decades. In both cases-where the institutional arrangements are ready to accelerate for the needed collaboration in a pandemic and where they run counter to what is needed-the rules of the game are "on the table" for institutional-level renegotiation. These challenges to the negotiated order in science are important, difficult to study, and highly consequential. The COVID-19 pandemic offers something of a natural experiment to study these dynamics. Preliminary findings highlight: the chilling effect of politics where open sharing could be expected to accelerate; the surprisingly conservative nature of contests and prizes; open questions around whether collaboration will persist following an inflection point in the pandemic; and the strong potential for launching and sustaining pre-competitive initiatives.

Your Spreadsheets Can Be FAIR: A Tool and FAIRification Workflow for the eNanoMapper Database

The field of nanoinformatics is rapidly developing and provides data driven solutions in the area of nanomaterials (NM) safety. Safe by Design approaches are encouraged and promoted through regulatory initiatives and multiple scientific projects. Experimental data is at the core of nanoinformatics processing workflows for risk assessment. The nanosafety data is predominantly recorded in Excel spreadsheet files. Although the spreadsheets are quite convenient for the experimentalists, they also pose great challenges for the consequent processing into databases due to variability of the templates used, specific details provided by each laboratory and the need for proper metadata documentation and formatting. In this paper, we present a workflow to facilitate the conversion of spreadsheets into a FAIR (Findable, Accessible, Interoperable, and Reusable) database, with the pivotal aid of the NMDataParser tool, developed to streamline the mapping of the original file layout into the eNanoMapper semantic data model. The NMDataParser is an open source Java library and application, making use of a JSON configuration to define the mapping. We describe the JSON configuration syntax and the approaches applied for parsing different spreadsheet layouts used by the nanosafety community. Examples of using the NMDataParser tool in nanoinformatics workflows are given. Challenging cases are discussed and appropriate solutions are proposed.

Replication and the Establishment of Scientific Truth

The idea of replication is based on the premise that there are empirical regularities or universal laws to be replicated and verified, and the scientific method is adequate for doing it. Scientific truth, however, is not absolute but relative to time, context, and the method used. Time and context are inextricably intertwined in that time (e.g., Christmas Day vs. New Year's Day) creates different contexts for behaviors and contexts create different experiences of time, rendering psychological phenomena inherently variable. This means that internal and external conditions fluctuate and are different in a replication study vs. the original. Thus, a replication experiment is just another empirical investigation in an ongoing effort to establish scientific truth. Neither the original nor a replication is the final arbiter of whether or not something exists. Discovered patterns need not be permanent laws of human behavior proven by the pinpoint statistical verification through replication. To move forward, phenomenon replications are needed to investigate phenomena in different ways, forms, contexts, and times. Such investigations look at phenomena not just in terms the magnitude of their effects but also by their frequency, duration, and intensity in labs and real life. They will also shed light on the extent to which lab manipulations may make many phenomena subjectively conscious events and effects (e.g., causal attributions) when they are nonconsciously experienced in real life, or vice versa. As scientific knowledge in physics is temporary and incomplete, should it be any surprise that science can only provide "temporary winners" for psychological knowledge of human behavior?

Gaps in Team Communication About Service Statistics Among Health Extension Workers in Ethiopia: Secondary Data Analysis

Background

In Ethiopia, health extension workers (HEWs) are deployed across the country by the government to meet public health needs. Team communication is important for effective teamwork, but community health workers in low-resource settings like Ethiopia may face challenges in carrying out team meetings to compile service statistics. This is due to the nature of their outreach activities, which requires extensive travel.

Objective

This study aimed to identify gaps in team communication about service statistics among HEWs in Ethiopia. Considering mobile communication and data collection as tools for bridging these gaps, we examined disparities in access to electricity, which has been identified as one of the major barriers to this approach.

Methods

Data from the most recent Performance Monitoring and Accountability 2020 service delivery point survey were used for our analysis. Logistic regression analysis was performed to identify disparities in team communication on service statistics for family planning, which is a major component of the HEW’s job. Disparities were examined across health facilities with different levels of HEW integration in their staffing structure (ie, no HEWs, at least one HEW, or only HEWs). Additionally, a chi-square test was conducted to examine disparities in access to electricity to explore the potential of mobile communication and data collection integration.

Results

In total, 427 health facilities of four different types (ie, hospitals, health centers, health posts, and health clinics) were included in our analysis. At most health posts (84/95, 88%), only HEWs were employed; none of the health clinics integrated the HEW model into their staffing structure. Among the 84 health posts, the odds of having team meetings on family planning service statistics in the past 12 months were 0.48 times the odds of those without HEWs (P=.02). No statistically significant differences were found between HEW-only facilities and facilities with at least one HEW. Most health facilities (69/83, 83.13%) with HEWs as the only staff had no electricity at the time of the survey while 71.25% (57/80) had intermittent access (ie, service disruption lasting 2 or more hours that day). There were statistically significant differences in electricity access among health facilities with different levels of HEW integration (P<.001).

Conclusions

Facilities employing only HEWs were less likely to have regular team meetings to discuss service statistics. Since their responsibilities involve extensive outreach activities, travel, and paper-based recordkeeping, empowering HEWs with mobile communication and data collection can be a workable solution. The empirical evidence regarding disparities in electricity access also supports the need for and the feasibility of this approach.

Weak Data: The Social Biography of a Measurement Instrument and How It Failed to Ensure Accountability in Home Care

Contemporary health and social care is saturated by processes of datafication. In many cases, these processes are nested within an ostensibly simple logic of accountability: Define a politically and morally desirable goal, then measure the level of achievement. This logic has come to permeate public health initiatives globally and today it operates in most health care systems in various ways. We explore here a particular instantiation of the logic associated with the introduction of a measurement instrument used in Danish home care. Building on ethnographic fieldwork, interviews, and analysis of policy documents, we show how the instigated processes of datafication-despite hopeful political claims-erode care levels and disempower older people. We believe that these findings can be of relevance for other settings that subscribe to the same accountability logic and to similar forms of measurement instruments.

The Marriage of Policy, Practices, and Data to Achieve Educational Reform

The policy decisions of state, district and school educators affect the extent to which students have access to high-quality practices. This is especially relevant for students with disabilities and their families. This article summarizes a presentation made at the 2019 AAIDD conference and proposes an operational role for policy makers. Two frequently cited advances in education are (a) the commitment to adopt "evidence-based practices," and (b) the impact of information technology and data systems on the active "use of data for decision making" in schools. This article reviews the integrative role that policy decisions make in transforming effective practices and good data systems into practical outcomes for children and families.

Playgrounds, Injuries, and Data: Keeping Children Safe

Child safety is a top priority in the school setting. Many accidents that occur on school playgrounds range from minor scrapes and bumps to fractures or other health problems that require quick medical response. Data can be a powerful tool for school nurses when seeking to promote changes in their schools.

Conceptualising Artificial Intelligence as a Digital Healthcare Innovation: An Introductory Review

Artificial intelligence (AI) is widely recognised as a transformative innovation and is already proving capable of outperforming human clinicians in the diagnosis of specific medical conditions, especially in image analysis within dermatology and radiology. These abilities are enhanced by the capacity of AI systems to learn from patient records, genomic information and real-time patient data. Uses of AI range from integrating with robotics to creating training material for clinicians. Whilst AI research is mounting, less attention has been paid to the practical implications on healthcare services and potential barriers to implementation. AI is recognised as a “Software as a Medical Device (SaMD)” and is increasingly becoming a topic of interest for regulators. Unless the introduction of AI is carefully considered and gradual, there are risks of automation bias, overdependence and long-term staffing problems. This is in addition to already well-documented generic risks associated with AI, such as data privacy, algorithmic biases and corrigibility. AI is able to potentiate innovations which preceded it, using Internet of Things, digitisation of patient records and genetic data as data sources. These synergies are important in both realising the potential of AI and utilising the potential of the data. As machine learning systems begin to cross-examine an array of databases, we must ensure that clinicians retain autonomy over the diagnostic process and understand the algorithmic processes generating diagnoses. This review uses established management literature to explore artificial intelligence as a digital healthcare innovation and highlight potential risks and opportunities.

dtoolAI: Reproducibility for Deep Learning

Deep learning, a set of approaches using artificial neural networks, has generated rapid recent advancements in machine learning. Deep learning does, however, have the potential to reduce the reproducibility of scientific results. Model outputs are critically dependent on the data and processing approach used to initially generate the model, but this provenance information is usually lost during model training. To avoid a future reproducibility crisis, we need to improve our deep-learning model management. The FAIR principles for data stewardship and software/workflow implementation give excellent high-level guidance on ensuring effective reuse of data and software. We suggest some specific guidelines for the generation and use of deep-learning models in science and explain how these relate to the FAIR principles. We then present dtoolAI, a Python package that we have developed to implement these guidelines. The package implements automatic capture of provenance information during model training and simplifies model distribution.

"Tomorrow Never Dies": Recent Advances in Diagnosis, Treatment, and Prevention Modalities against Coronavirus (COVID-19) amid Controversies

The outbreak of novel coronavirus disease (2019-nCoV or COVID-19) is responsible for severe health emergency throughout the world. The attack of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is found to be responsible for COVID-19. The World Health Organization has declared the ongoing global public health emergency as a pandemic. The whole world fights against this invincible enemy in various capacities to restore economy, lifestyle, and safe life. Enormous amount of scientific research work(s), administrative strategies, and economic measurements are in place to create a successful step against COVID-19. Furthermore, differences in opinion, facts, and implementation methods laid additional layers of complexities in this battle against survival. Thus, a timely overview of the recent, important, and overall inclusive developments against this pandemic is a pressing need for better understanding and dealing with COVID-19. In this review, we have systematically summarized the epidemiological studies, clinical features, biological properties, diagnostic methods, treatment modalities, and preventive measurements related to COVID-19.

International Access to Public Health Data: An Important Brazilian Legal Precedent

Accurate, up-to-date data are the bedrock of effective public health responses, including in the context of the suffering caused by COVID-19. Any action to inhibit the compilation of such data has ramifications locally, nationally and internationally, and risks impairing the global capacity to respond to the virus. This article contextualises the decision of the government of President Bolsonaro of Brazil to reduce the accessibility of contemporary data about COVID-19 infections in Brazil within his views about, and responses to, the virus. It identifies the nature of actions taken to suppress such data by the Brazilian Ministry of Health and then scrutinises a decision by De Moraes J of Brazil's High Court in Sustainability Network v The President of the Republic of Brazil (ADPF 690 MC/DF, 8 June 2020), which quashed the attempted suppression of public health data. The article hails the decision as an important public health law precedent.

The Role of the School Nurse in Increasing Instructional Time Using Multi-Tiered Systems of Support for Behavior (MTSS-B): A Quality Improvement Project

Frequent visits to the health office can lead to considerable time spent out of the classroom along with affecting relationships and health office resources and staffing. This article features the practice component of continuous quality improvement in the principal of quality improvement in the Framework for the 21st Century School Nursing Practice™ and is the third in a series focusing on the Framework. The article discusses how using multi-tiered systems of support for behavior (MTSS-B) to create expectations for the health office environment, along with intense, individualized plans for specific students, were successful in decreasing health office visits across the school district, with the ultimate goal of increasing instructional time. Outcome data revealed reductions in health office visits with a district-wide decrease of 4.1% one-year postimplementation of the project. More importantly, school nurses are providing better trauma-informed care with intentionality while still meeting the needs of students.

The Digital Phenotyping Project: A Psychoanalytical and Network Theory Perspective

A new method of observation is currently emerging in psychiatry, based on data collection and behavioral profiling of smartphone users. Numerical phenotyping is a paradigmatic example. This behavioral investigation method uses computerized measurement tools in order to collect characteristics of different psychiatric disorders. First, it is necessary to contextualize the emergence of these new methods and to question their promises and expectations. The international mental health research framework invites us to reflect on methodological issues and to draw conclusions from certain impasses related to the clinical complexity of this field. From this contextualization, the investigation method relating to digital phenotyping can be questioned in order to identify some of its potentials. These new methods are also an opportunity to test psychoanalysis. It is then necessary to identify the elements of fruitful analysis that clinical experience and research in psychoanalysis have been able to deploy regarding the challenges of digital technology. An analysis of this theme’s literature shows that psychoanalysis facilitates a reflection on the psychological effects related to digital methods. It also shows how it can profit from the research potential offered by new technical tools, considering the progress that has been made over the past 50 years. This cross-fertilization of the potentials and limitations of digital methods in mental health intervention in the context of theoretical issues at the international level invites us to take a resolutely non-reductionist position. In the field of research, psychoanalysis offers a specific perspective that can well be articulated to an epistemology of networks. Rather than aiming at a numerical phenotyping of patients according to the geneticists’ model, the case formulation method appears to be a serious prerequisite to give a limited and specific place to the integration of smartphones in clinical investigation.

Rethinking the Importance of the Individual within a Community of Data

The Covid-19 crisis has underscored the importance of the collection and analysis of clinical and research data and specimens for ongoing work. The federal government recently completed a related revision of the human subjects research regulations, founded in the traditional principles of research ethics, but in this commentary, we argue that the analysis underpinning this revision overemphasized the importance of informed consent, given the low risks of secondary research. Governing the interests of a community is different from governing the interests of individuals, and here we suggest that, moving forward, the analyses of the risks of secondary research protocols be assessed from the perspective of the former.

Thinking about Trust: People, Process, and Place

This brief paper is about trust. It explores the phenomenon from various angles, with the implicit assumptions that trust can be measured in some ways, that trust can be compared and rated, and that trust is of worth when we consider entities from data, through artificial intelligences, to humans, with side trips along the way to animals. It explores trust systems and trust empowerment as opposed to trust enforcement, the creation of trust models, applications of trust, and the reasons why trust is of worth.

Unlocking the Power of School Nursing Documentation

School nurses may be underestimating the power of their documentation to advance the visibility of their work and the needs of the students they serve. The first step toward unlocking the value of their documentation is recognizing the role that quality documentation plays in advancing these goals. The purpose of this article is to demonstrate the utility of the nursing process for improving the quality of documentation and provide examples of how to use nursing documentation formats.

[Thoughts and suggestions on analysis of death cases report during COVID-19 epidemic]

It is an essential task to discuss the death cases for clinicians. During the emergent public events, the report and analysis of death cases is of far-reaching significance. The epidemic of coronavirus disease 2019(COVID-19) has brought huge losses to China, and the medical system has been sustaining tremendous pressure. The best weapon to defeat the epidemic is medical data and related scientific research, of which the systematic analysis and efficient use of death cases is a key step. Based on the incomplete record of death case report, the lack of humanistic perspective and patient report, every department and institution is facing great challenge in terms of data management. Given that the relevant systems need to be improved, and that the integration of standardized reports and clinical research is not mature,as well as other problems, we put forward several methodological suggestions: ① Establish national medical and health data center and improve relevant laws and regulations. ② Increase investment in medical data management and start data collection and analysis as early as possible during the epidemic. ③ Refine the content of death case report and promote the standardization of report. ④ Pay close attention to the report of death cases, review, summary and analysis. More importantly, we should continue to build and improve platforms and programs related to disease control, carry out epidemic-associated scientific research, enhance the managing efficiency of public health data, elevate the anti-risk capability of our medical system, and promote the steady progress of the health China strategy.

Amplifying the role of knowledge translation platforms in the COVID-19 pandemic response

The COVID-19 pandemic presents the worst public health crisis in recent history. The response to the COVID-19 pandemic has been challenged by many factors, including scientific uncertainties, scarcity of relevant research, proliferation of misinformation and fake news, poor access to actionable evidence, time constraints, and weak collaborations among relevant stakeholders. Knowledge translation (KT) platforms, composed of organisations, initiatives and networks supporting evidence-informed policy-making, can play an important role in providing relevant and timely evidence to inform pandemic responses and bridge the gap between science, policy, practice and politics. In this Commentary, we highlight the emerging roles of KT platforms in light of the COVID-19 pandemic. We also reflect on the lessons learned from the efforts of a KT platform in a middle-income country to inform decision-making and practice during the COVID-19 pandemic. The lessons learned can be integrated into strengthening the role, structures and mandates of KT platforms as hubs for trustworthy evidence that can inform policies and practice during public health crises and in promoting their integration and institutionalisation within the policy-making processes.

Contextual Data in IPUMS DHS: Physical and Social Environment Variables linked to the Demographic and Health Surveys

The Demographic and Health Surveys (DHS) are the most important source of comparative information on the health of women and young children in low- and middle-income countries and are well-suited for studies of the relationship between environmental factors and health. However, barriers have limited the use of the DHS for these purposes. IPUMS DHS, an online data dissemination tool, overcomes these barriers, simplifying comparative analyses with DHS. IPUMS DHS recently incorporated environmental variables that can easily be attached to individual or household records, facilitating the use of DHS data for the study of population and environment issues. We provide a brief introduction to IPUMS DHS, describe the current and anticipated environmental variables and how to use them, and provide an example of the novel research possibilities facilitated by this latest IPUMS DHS development. IPUMS-DHS is available free online at dhs.ipums.org.

Nursing Informatics and School Nursing: Specialists Wanted

Hospitals and healthcare systems have nursing informaticists who contribute to quality patient care and safety by managing data and facilitating the use of technology. Schools typically do not employ nurses specifically in positions labeled as nursing informaticists, though the role is critical in the schools. This article highlights the subspecialty of nursing informatics within the school nurse role. Three school nurses will share their use of nursing informatics skills to optimize student health.

Chinese affective platform economies: dating, live streaming, and performative labor on Blued

This article analyzes the political economy of sexually affective data on the Chinese gay dating platform Blued. Having launched in 2012 as a location-based dating app akin to Grindr, Blued has now become a multipurpose platform providing extra services such as newsfeeds and live streaming. Through the continuous imbrication of old and new functionalities and related affordances, users are transformed from dating subjects into performative laborers. Based on Internet ethnographic research that lasted 2 years, this article focuses on sexual-affective data flows (e.g. virtual gifting, following, liking, commenting, and sharing) produced by gay live streamers within the parameters of same-sex desires such as infatuation, sexual arousal, and online intimacy. It argues that these sexually affective data flows increasingly constitute key corporate assets with which Blued attracts venture capital. This analysis of live streamers and their viewers extends understandings of dating apps in two ways. First, it shows how these apps now function as business platforms on top of being channels for hooking up. Second, it emphasizes that whereas users created data freely, now it is produced by paid labor.

How should we think about clinical data ownership?

The concept of 'ownership' is increasingly central to debates, in the media, health policy and bioethics, about the appropriate management of clinical data. I argue that the language of ownership acts as a metaphor and reflects multiple concerns about current data use and the disenfranchisement of citizens and collectives in the existing data ecosystem. But exactly which core interests and concerns ownership claims allude to remains opaque. Too often, we jump straight from 'ownership' to 'private property' and conclude 'the data belongs to the patient'. I will argue here that private property is only one type of relevant relationship between people, communities and data. There are several reasons to doubt that conceptualising data as private property presents a compelling response to concerns about clinical data ownership. In particular I argue that clinical data are co-constructed, so a property account would fail to confer exclusive rights to the patient. A non-property account of ownership acknowledges that the data are 'about the patient', and therefore the patient has relevant interests, without jumping to the conclusion that the data 'belongs to the patient'. On this broader account of ownership, the relevant harm is the severing of the connection between the patient and their data, and the solution is to re-engage and re-connect patients to the data research enterprise.