Public and Population Health Informatics: The Bridging of Big Data to Benefit Communities

Machine Learning Models for Frailty Classification of Older Adults in Northern Thailand: Model Development and Validation Study

Background

Frailty is defined as a clinical state of increased vulnerability due to the age-associated decline of an individual's physical function resulting in increased morbidity and mortality when exposed to acute stressors. Early identification and management can reverse individuals with frailty to being robust once more. However, we found no integration of machine learning (ML) tools and frailty screening and surveillance studies in Thailand despite the abundance of evidence of frailty assessment using ML globally and in Asia.

Objective

We propose an approach for early diagnosis of frailty in community-dwelling older individuals in Thailand using an ML model generated from individual characteristics and anthropometric data.

Methods

Datasets including 2692 community-dwelling Thai older adults in Lampang from 2016 and 2017 were used for model development and internal validation. The derived models were externally validated with a dataset of community-dwelling older adults in Chiang Mai from 2021. The ML algorithms implemented in this study include the k-nearest neighbors algorithm, random forest ML algorithms, multilayer perceptron artificial neural network, logistic regression models, gradient boosting classifier, and linear support vector machine classifier.

Results

Logistic regression showed the best overall discrimination performance with a mean area under the receiver operating characteristic curve of 0.81 (95% CI 0.75-0.86) in the internal validation dataset and 0.75 (95% CI 0.71-0.78) in the external validation dataset. The model was also well-calibrated to the expected probability of the external validation dataset.

Conclusions

Our findings showed that our models have the potential to be utilized as a screening tool using simple, accessible demographic and explainable clinical variables in Thai community-dwelling older persons to identify individuals with frailty who require early intervention to become physically robust.

Population health and public health: Commonalities and differences

OBJECTIVE

To explore the synergy between population health and public health by initiating a discourse about their interconnected roles, responsibilities, and approaches in achieving optimal health outcomes.

OVERVIEW

Population health and public health, although distinct, are interconnected disciplines critical for enhancing health outcomes. Population health focuses on analyzing health determinants and outcomes within specific groups, employing data to guide targeted interventions and policies. Public health, on the other hand, prioritizes broader preventive measures and community-wide interventions to safeguard health. Both fields benefit from a transdisciplinary approach that integrates strategies to address and improve health. Such integration is essential for addressing health disparities and improving the efficiency of health systems. By combining the analytical strengths of population health with the implementation capabilities of public health, a more comprehensive framework can be developed. These collaborations will not only enhance the effectiveness of health programs but also promote health equity by leveraging collective expertise and resources. They will facilitate the development of interventions that are both preventive and responsive, capable of addressing the upstream determinants of health and the immediate needs of communities. Such transdisciplinary efforts were demonstrated within the oral health field during the COVID-19 pandemic.

CONCLUSIONS

The synergy between population and public health can lead to robust health outcomes, fostering comprehensive health promotion and disease prevention strategies. By aligning research, practices, and policies, these integrated approaches will transcend traditional boundaries within the healthcare sector to build efficient health systems.

Exploring the Italian Population's attitudes toward health data sharing for healthcare purpose and scientific research: a cross-sectional study

BACKGROUND

This study aimed to explore the Italian population's knowledge and perceptions regarding health data storage and sharing for treatment and research and to identify factors associated with citizens' attitudes toward data storage and sharing.

METHODS

A cross-sectional questionnaire, distributed to 1389 participants, collected sociodemographic information, assessed knowledge and gauged attitudes toward sharing data for treatment and research. Descriptive analyses and logistic regressions were performed to examine the associations between sociodemographic factors and knowledge/attitudes about data storage and sharing.

RESULTS

Most respondents wrongly believed that healthcare providers could access personal health-related data across the entire national territory, while 94% expressed willingness to share personal health data nationwide. A substantial percentage of respondents (73%) fully agreed that storing and sharing personal health-related data could improve research and quality of care.Males and younger individuals (<41 years) were likelier to have higher data-sharing knowledge. Lower educational-level respondents exhibited lower positive attitudes towards sharing health data for treatment and research purposes.

CONCLUSIONS

The results provide valuable insights for policymakers, healthcare professionals and researchers seeking to improve data management, promote collaboration and leverage the full potential of health data for personalized care and scientific advancements.

Elevating Clinical Informatics: Dynamic Resident Training to Enhance Subspecialty Appeal

OBJECTIVE

 This study aimed to bridge the educational gap in clinical informatics (CI) at the residency level and stimulate interest in CI as a rewarding career path.

METHODS

 We developed an innovative CI and quality improvement (QI) resident rotation. This rotation replaced traditional QI blocks for Internal Medicine and several other residency programs, offering comprehensive exposure to core informatics and QI principles. The curriculum featured prerecorded didactics, hands-on projects, department meetings, and an optional EPIC SmartUser program. Resident participation and feedback were evaluated through postrotation surveys.

RESULTS

 Since its inception on July 1, 2022, 57 residents have completed the rotation, with a majority rating their experience favorably. Residents also valued the educational course content and expressed an increased likelihood of integrating informatics into their future careers.

CONCLUSION

 The rotation has successfully integrated into existing multiple residency programs, demonstrating an effective model for delivering informatics education. Initial outcomes show enhanced resident engagement and competency in CI, promising a progressive impact on the future physician workforce. Continued expansion and evaluation of this rotation are expected to further encourage formal CI training and career interest.

Topics and Trends of Health Informatics Education Research: Scientometric Analysis

BACKGROUND

Academic and educational institutions are making significant contributions toward training health informatics professionals. As research in health informatics education (HIE) continues to grow, it is useful to have a clearer understanding of this research field.

OBJECTIVE

This study aims to comprehensively explore the research topics and trends of HIE from 2014 to 2023. Specifically, it aims to explore (1) the trends of annual articles, (2) the prolific countries/regions, institutions, and publication sources, (3) the scientific collaborations of countries/regions and institutions, and (4) the major research themes and their developmental tendencies.

METHODS

Using publications in Web of Science Core Collection, a scientometric analysis of 575 articles related to the field of HIE was conducted. The structural topic model was used to identify topics discussed in the literature and to reveal the topic structure and evolutionary trends of HIE research.

RESULTS

Research interest in HIE has clearly increased from 2014 to 2023, and is continually expanding. The United States was found to be the most prolific country in this field. Harvard University was found to be the leading institution with the highest publication productivity. Journal of Medical Internet Research, Journal of The American Medical Informatics Association, and Applied Clinical Informatics were the top 3 journals with the highest articles in this field. Countries/regions and institutions having higher levels of international collaboration were more impactful. Research on HIE could be modeled into 7 topics related to the following areas: clinical (130/575, 22.6%), mobile application (123/575, 21.4%), consumer (99/575, 17.2%), teaching (61/575, 10.6%), public health (56/575, 9.7%), discipline (55/575, 9.6%), and nursing (51/575, 8.9%). The results clearly indicate the unique foci for each year, depicting the process of development for health informatics research.

CONCLUSIONS

This is believed to be the first scientometric analysis exploring the research topics and trends in HIE. This study provides useful insights and implications, and the findings could be used as a guide for HIE contributors.

Comparing public health-related material in print and web page versions of legacy media

Objectives

The objectives of this study were to create a database of public health content from a sample of legacy media, and to compare the prevalence of public health themes in print and web-based versions over time.

Materials and Methods

A database was created from eleven nationally published magazines as a sample of legacy media content. Relevant material was extracted and coded by the title of the article, periodical, print or web edition, month of publication, item type, and 1-3 public health theme codes.

Results

Theme codes emerged as the documents were reviewed based on the primary discussion in each piece. A total of 2558 unique documents were extracted from print issues and 6440 from web-based issues. Seventeen public health themes were identified. Individual coded documents were saved with file names identical to the code string, thus creating a searchable database.

Discussion

Legacy media are those that existed before the internet and social media. Publishers target readership groups defined by age, gender, race, sexual orientation, and other commonalities. Although legacy media have been identified as trusted sources of health information, they have not been examined as sources of public health communication. Because both print and web-based versions exist as unstructured textual data, these are rarely examined with informatics methods.

Conclusion

The process described can serve as a model for application of informatics approaches to similar data and assist development of targeted public health communications. Having a better understanding of what types of health content is distributed through legacy media can help to target health messages to specific demographic and interest groups in ways that are understandable and appealing to them.

Returning value to the community through the All of Us Research Program Data Sandbox model

OBJECTIVE

The All of Us Research Program aims to return value to participants by developing research capacity in communities. We describe a novel set of introductory exercises (Data Sandboxes) and specialized trainings to orient researchers to the Researcher Workbench to foster health equity research.

MATERIALS AND METHODS

We developed a tailored training to familiarize researchers with the All of Us Research Program: (1) orientation, (2) tailored "data treasure hunt" using the Public Data Browser, and (3) overview of the analyses tools and platform.

RESULTS

Participants' pre- and post-knowledge of the contents and structure of the All of Us dataset scores increased significantly after training. These trainings effectively engaged researchers in exploring this rich dataset.

CONCLUSION

We describe ways of orienting and familiarizing a wide variety of researchers with the All of Us Research Program dataset, sparking their interest, and "jump-starting" their research.

Role of Telemedicine and Telehealth in Public Healthcare Sector: A Narrative Review

Clinicians, researchers in health services, and other experts have been investigating how to improve healthcare using advanced computer and telecommunication technology for more than 30 years. Adequate medical facilities are still lacking in many places of the world. In these kinds of situations, technology can be quite helpful in expanding healthcare access to rural locations and offering better care at a lower cost. The delivery of healthcare is changing dramatically because of telemedicine and telehealth, particularly in terms of improving access to care. This paper aims to provide an update on the history, background, applications, benefits, barriers, and challenges of these recent technologies. This review article also covers the healthcare conditions of rural as well as urban communities. Furthermore, the implications of technologies used and improvement in the health status of an individual are also discussed. During the COVID-19 epidemic, telehealth quickly gained popularity, bringing to light a number of issues. Effective primary medical networks are crucial, as the COVID-19 pandemic highlighted the need for improving public health responses during crises and revealed the existing fragmentation in healthcare delivery systems.

Nucleic Acid Based Testing (NABing): A Game Changer Technology for Public Health

Timely and accurate detection of the causal agent of a disease is crucial to restrict suffering and save lives. Mere symptoms are often not enough to detect the root cause of the disease. Better diagnostics applied for screening at a population level and sensitive detection assays remain the crucial component of disease surveillance which may include clinical, plant, and environmental samples, including wastewater. The recent advances in genome sequencing, nucleic acid amplification, and detection methods have revolutionized nucleic acid-based testing (NABing) and screening assays. A typical NABing assay consists of three modules: isolation of the nucleic acid from the collected sample, identification of the target sequence, and final reading the target with the help of a signal, which may be in the form of color, fluorescence, etc. Here, we review current NABing assays covering the different aspects of all three modules. We also describe the frequently used target amplification or signal amplification procedures along with the variety of applications of this fast-evolving technology and challenges in implementation of NABing in the context of disease management especially in low-resource settings.

Revolutionizing urogynecology: Machine learning application with patient-centric technology: Promise, challenges, and future directions

In an epoch where digital innovation is redefining the medical landscape, electronic health records (EHRs) stand out as a pivotal transformative force. Urogynecology, a discipline anchored in intricate patient histories and meticulous follow-ups, is on the brink of profound transformation due to these digital strides. While EHRs have unified patient data, challenges related to data privacy, interoperability, and access persist. In response, we present Pelvic Health Place (PHPlace) - a multilingual, patient-centric application. Purposefully designed to bolster patient engagement, PHPlace provides clinicians with essential pre-consultation insights, streamlines the consent process, vividly delineates surgical pathways, and assures comprehensive long-term monitoring. This platform also establishes a foundation for global data amalgamation, promising to invigorate research and potentially harness artificial intelligence (AI) capabilities. With AI integration, we anticipate a more tailored treatment approach and enriched patient education, signaling a pivotal shift in urogynecology and emphasizing the imperative for ongoing academic inquiry.

Big Data in Health Care: An Interprofessional Course

BACKGROUND

The widespread adoption of the electronic health record (EHR) has resulted in vast repositories of EHR big data that are being used to identify patterns and correlations that translate into data-informed health care decision making.

PROBLEM

Health care professionals need the skills necessary to navigate a digitized, data-rich health care environment as big data plays an increasingly integral role in health care.

APPROACH

Faculty incorporated the concept of big data in an asynchronous online course allowing an interprofessional mix of students to analyze EHR big data on over a million patients.

OUTCOMES

Students conducted a descriptive analysis of cohorts of patients with selected diagnoses and presented their findings.

CONCLUSIONS

Students collaborated with an interprofessional team to analyze EHR big data on selected variables. The teams used data visualization tools to describe an assigned diagnosis patient population.

Digital Transformation of Public Health for Noncommunicable Diseases: Narrative Viewpoint of Challenges and Opportunities

The recent SARS-CoV-2 pandemic underscored the effectiveness and rapid deployment of digital public health interventions, notably the digital proximity tracing apps, leveraging Bluetooth capabilities to trace and notify users about potential infection exposures. Backed by renowned organizations such as the World Health Organization and the European Union, digital proximity tracings showcased the promise of digital public health. As the world pivots from pandemic responses, it becomes imperative to address noncommunicable diseases (NCDs) that account for a vast majority of health care expenses and premature disability-adjusted life years lost. The narrative of digital transformation in the realm of NCD public health is distinct from infectious diseases. Public health, with its multifaceted approach from disciplines such as medicine, epidemiology, and psychology, focuses on promoting healthy living and choices through functions categorized as "Assessment," "Policy Development," "Resource Allocation," "Assurance," and "Access." The power of artificial intelligence (AI) in this digital transformation is noteworthy. AI can automate repetitive tasks, facilitating health care providers to prioritize personal interactions, especially those that cannot be digitalized like emotional support. Moreover, AI presents tools for individuals to be proactive in their health management. However, the human touch remains irreplaceable; AI serves as a companion guiding through the health care landscape. Digital evolution, while revolutionary, poses its own set of challenges. Issues of equity and access are at the forefront. Vulnerable populations, whether due to economic constraints, geographical barriers, or digital illiteracy, face the threat of being marginalized further. This transformation mandates an inclusive strategy, focusing on not amplifying existing health disparities but eliminating them. Population-level digital interventions in NCD prevention demand societal agreement. Policies, like smoking bans or sugar taxes, though effective, might affect those not directly benefiting. Hence, all involved parties, from policy makers to the public, should have a balanced perspective on the advantages, risks, and expenses of these digital shifts. For a successful digital shift in public health, especially concerning NCDs, AI's potential to enhance efficiency, effectiveness, user experience, and equity-the "quadruple aim"-is undeniable. However, it is vital that AI-driven initiatives in public health domains remain purposeful, offering improvements without compromising other objectives. The broader success of digital public health hinges on transparent benchmarks and criteria, ensuring maximum benefits without sidelining minorities or vulnerable groups. Especially in population-centric decisions, like resource allocation, AI's ability to avoid bias is paramount. Therefore, the continuous involvement of stakeholders, including patients and minority groups, remains pivotal in the progression of AI-integrated digital public health.

Advantages and disadvantages of using theory-based versus data-driven models with social and behavioral determinants of health data

OBJECTIVE

Theory-based research of social and behavioral determinants of health (SBDH) found SBDH-related patterns in interventions and outcomes for pregnant/birthing people. The objectives of this study were to replicate the theory-based SBDH study with a new sample, and to compare these findings to a data-driven SBDH study.

MATERIALS AND METHODS

Using deidentified public health nurse-generated Omaha System data, 2 SBDH indices were computed separately to create groups based on SBDH (0-5+ signs/symptoms). The data-driven SBDH index used multiple linear regression with backward elimination to identify SBDH factors. Changes in Knowledge, Behavior, and Status (KBS) outcomes, numbers of interventions, and adjusted R-squared statistics were computed for both models.

RESULTS

There were 4109 clients ages 13-40 years. Outcome patterns aligned with the original research: KBS increased from admission to discharge with Knowledge improving the most; discharge KBS decreased as SBDH increased; and interventions increased as SBDH increased. Slopes of the data-driven model were steeper, showing clearer KBS trends for data-driven SBDH groups. The theory-based model adjusted R-squared was 0.54 (SE = 0.38) versus 0.61 (SE = 0.35) for the data-driven model with an entirely different set of SBDH factors.

CONCLUSIONS

The theory-based approach provided a framework to identity patterns and relationships and may be applied consistently across studies and populations. In contrast, the data-driven approach can provide insights based on novel patterns for a given dataset and reveal insights and relationships not predicted by existing theories. Data-driven methods may be an advantage if there is sufficiently comprehensive SBDH data upon which to create the data-driven models.

Initiatives, Concepts, and Implementation Practices of the Findable, Accessible, Interoperable, and Reusable Data Principles in Health Data Stewardship: Scoping Review

BACKGROUND

Thorough data stewardship is a key enabler of comprehensive health research. Processes such as data collection, storage, access, sharing, and analytics require researchers to follow elaborate data management strategies properly and consistently. Studies have shown that findable, accessible, interoperable, and reusable (FAIR) data leads to improved data sharing in different scientific domains.

OBJECTIVE

This scoping review identifies and discusses concepts, approaches, implementation experiences, and lessons learned in FAIR initiatives in health research data.

METHODS

The Arksey and O'Malley stage-based methodological framework for scoping reviews was applied. PubMed, Web of Science, and Google Scholar were searched to access relevant publications. Articles written in English, published between 2014 and 2020, and addressing FAIR concepts or practices in the health domain were included. The 3 data sources were deduplicated using a reference management software. In total, 2 independent authors reviewed the eligibility of each article based on defined inclusion and exclusion criteria. A charting tool was used to extract information from the full-text papers. The results were reported using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines.

RESULTS

A total of 2.18% (34/1561) of the screened articles were included in the final review. The authors reported FAIRification approaches, which include interpolation, inclusion of comprehensive data dictionaries, repository design, semantic interoperability, ontologies, data quality, linked data, and requirement gathering for FAIRification tools. Challenges and mitigation strategies associated with FAIRification, such as high setup costs, data politics, technical and administrative issues, privacy concerns, and difficulties encountered in sharing health data despite its sensitive nature were also reported. We found various workflows, tools, and infrastructures designed by different groups worldwide to facilitate the FAIRification of health research data. We also uncovered a wide range of problems and questions that researchers are trying to address by using the different workflows, tools, and infrastructures. Although the concept of FAIR data stewardship in the health research domain is relatively new, almost all continents have been reached by at least one network trying to achieve health data FAIRness. Documented outcomes of FAIRification efforts include peer-reviewed publications, improved data sharing, facilitated data reuse, return on investment, and new treatments. Successful FAIRification of data has informed the management and prognosis of various diseases such as cancer, cardiovascular diseases, and neurological diseases. Efforts to FAIRify data on a wider variety of diseases have been ongoing since the COVID-19 pandemic.

CONCLUSIONS

This work summarises projects, tools, and workflows for the FAIRification of health research data. The comprehensive review shows that implementing the FAIR concept in health data stewardship carries the promise of improved research data management and transparency in the era of big data and open research publishing.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/22505.

Digital Biobanking and Big Data as a New Research Tool: A Position Paper

Big data analytics in medicine is driving significant change, as it offers vital information for improving functions, developing cutting-edge solutions and overcoming inefficiencies. With the right archiving and analysis tools, all players in the healthcare system, from hospitals to patients and from medical personnel to the pharmaceutical industry, can yield numerous benefits. Therefore, to analyze and interpret these analytics effectively, so that they can be useful for the advancement of scientific knowledge, we require information sharing, specific skills, training, integration between all system players, unique infrastructures and security. All these characteristics will make it possible to establish and harmonize real big data biobanks, for which it will be appropriate to consider new forms of governance compared to those traditionally conceived for large-sample biobanks.

Critical risk and success factors for sustainability of an electronic health data capture, processing and dissemination platform for Uganda

Several studies have investigated challenges that have marred success or even caused the failure of eHealth implementations in Uganda; however, none has focused on the risks and success factors of their sustainability. This study explored critical risk and success factors for the sustainability of an electronic health data capture, processing and dissemination platform for Uganda. A mixed-method research design was followed involving collecting empirical data from all four regions of Uganda. A purposive sampling strategy was used to select the study districts per region, health facilities per district, and respondents/participants per facility or district. Findings revealed several risks and success factors for sustainability, including; bad leadership, corruption, lack of sustainable maintenance programs, lack of suitable sustainability plans, lack of ICT infrastructure investment, poor management systems, funds, stakeholder buy-ins, data sharing and access rights. The success factors included reinvestments as a partial sustainability plan for ICT infrastructure. These factors can be leveraged to ensure the continued operation of eHealth implementations in Uganda. Every electronic health project aiming at success should always make due consideration/sustainability plan at the onset of project conceptualisation; as lack of such a plan has often resulted in failed projects after the initial funds have been withdrawn.

Leveraging Responsible, Explainable, and Local Artificial Intelligence Solutions for Clinical Public Health in the Global South

In the present paper, we will explore how artificial intelligence (AI) and big data analytics (BDA) can help address clinical public and global health needs in the Global South, leveraging and capitalizing on our experience with the "Africa-Canada Artificial Intelligence and Data Innovation Consortium" (ACADIC) Project in the Global South, and focusing on the ethical and regulatory challenges we had to face. "Clinical public health" can be defined as an interdisciplinary field, at the intersection of clinical medicine and public health, whilst "clinical global health" is the practice of clinical public health with a special focus on health issue management in resource-limited settings and contexts, including the Global South. As such, clinical public and global health represent vital approaches, instrumental in (i) applying a community/population perspective to clinical practice as well as a clinical lens to community/population health, (ii) identifying health needs both at the individual and community/population levels, (iii) systematically addressing the determinants of health, including the social and structural ones, (iv) reaching the goals of population's health and well-being, especially of socially vulnerable, underserved communities, (v) better coordinating and integrating the delivery of healthcare provisions, (vi) strengthening health promotion, health protection, and health equity, and (vii) closing gender inequality and other (ethnic and socio-economic) disparities and gaps. Clinical public and global health are called to respond to the more pressing healthcare needs and challenges of our contemporary society, for which AI and BDA can help unlock new options and perspectives. In the aftermath of the still ongoing COVID-19 pandemic, the future trend of AI and BDA in the healthcare field will be devoted to building a more healthy, resilient society, able to face several challenges arising from globally networked hyper-risks, including ageing, multimorbidity, chronic disease accumulation, and climate change.

Vestibular cognition assessment system: Tablet-based computerized visuospatial abilities test battery

Introduction

The vestibular system is anatomically connected to extensive regions of the cerebral cortex, hippocampus, and amygdala. However, studies focusing on the impact of vestibular impairment on visuospatial cognition ability are limited. This study aimed to develop a mobile tablet-based vestibular cognitive assessment system (VCAS), enhance the dynamic and three-dimensional (3D) nature of the test conditions, and comprehensively evaluate the visuospatial cognitive ability of patients with vestibular dysfunction.

Materials and methods

First, the VCAS assessment dimensions (spatial memory, spatial navigation, and mental rotation) and test content (weeding, maze, card rotation, and 3D driving tests) were determined based on expert interviews. Second, VCAS was developed based on Unity3D, using the C# language and ILruntime hot update framework development technology, combined with the A* algorithm, prime tree algorithm, and dynamic route rendering. Further, the online test was built using relevant game business logic. Finally, healthy controls (HC) and 78 patients with vertigo (VP) were recruited for the VCAS test. The validity of VCAS was verified using the test results of random controls.

Results

In the weeding test, the HC group had a significantly longer span and faster velocity backward than did the VP group. In the 12 × 12 maze, statistically significant differences in step and time were observed between the two groups, with VP taking longer time and more steps. In the mental rotation task, no significant difference was observed between the two groups. Similarly, no significant difference was found in the performance of the two groups on maps 2, 3, and 4 in the 3D driving task.

Discussion

Thus, impaired visuospatial cognition in patients with vestibular dysfunction is primarily related to spatial memory and navigation. VCAS is a clinically applicable visuospatial cognitive ability test for VP.

Summary of Year-One Effort of the RCMI Consortium to Enhance Research Capacity and Diversity with Data Science

Despite being disproportionately impacted by health disparities, Black, Hispanic, Indigenous, and other underrepresented populations account for a significant minority of graduates in biomedical data science-related disciplines. Given their commitment to educating underrepresented students and trainees, minority serving institutions (MSIs) can play a significant role in enhancing diversity in the biomedical data science workforce. Little has been published about the reach, curricular breadth, and best practices for delivering these data science training programs. The purpose of this paper is to summarize six Research Centers in Minority Institutions (RCMIs) awarded funding from the National Institute of Minority Health Disparities (NIMHD) to develop new data science training programs. A cross-sectional survey was conducted to better understand the demographics of learners served, curricular topics covered, methods of instruction and assessment, challenges, and recommendations by program directors. Programs demonstrated overall success in reach and curricular diversity, serving a broad range of students and faculty, while also covering a broad range of topics. The main challenges highlighted were a lack of resources and infrastructure and teaching learners with varying levels of experience and knowledge. Further investments in MSIs are needed to sustain training efforts and develop pathways for diversifying the biomedical data science workforce.

Development of an Administrative Data-Based Frailty Index for Older Adults Receiving Dialysis

Background

Frailty is present in ≥50% of older adults receiving dialysis. Our objective was to a develop an administrative data-based frailty index and assess the frailty index's predictive validity for mortality and future hospitalizations.

Methods

We used United States Renal Data System data to establish two cohorts of adults aged ≥65 years, initiating dialysis in 2013 and in 2017. Using the 2013 cohort (development dataset), we applied the deficit accumulation index approach to develop a frailty index. Adjusting for age and sex, we assessed the extent to which the frailty index predicts the hazard of time until death and time until first hospitalization over 12 months. We assessed the Harrell's C-statistic of the frailty index, a comorbidity index, and jointly. The 2017 cohort was used as a validation dataset.

Results

Using the 2013 cohort (n=20,974), we identified 53 deficits for the frailty index across seven domains: disabilities, diseases, equipment, procedures, signs, tests, and unclassified. Among those with ≥1 deficit, the mean (SD) frailty index was 0.30 (0.13), range 0.02-0.72. Over 12 months, 18% (n=3842) died, and 55% (n=11,493) experienced a hospitalization. Adjusted hazard ratios for each 0.1-point increase in frailty index in models of time to death and time to first hospitalization were 1.41 (95% confidence interval, 1.37 to 1.44) and 1.33 (95% confidence interval, 1.31 to 1.35), respectively. For mortality, C-statistics for frailty index, comorbidity index, and both indices were 0.65, 0.65, and 0.66, respectively. For hospitalization, C-statistics for frailty index, comorbidity index, and both indices were 0.61, 0.60, and 0.61, respectively. Data from the 2017 cohort were similar.

Conclusions

We developed a novel frailty index for older adults receiving dialysis. Further studies are needed to improve on this frailty index and validate its use for clinical and research applications.

Artificial intelligence for early stroke diagnosis in acute vestibular syndrome

Objective

Measuring the Vestibular-Ocular-Reflex (VOR) gains with the video head impulse test (vHIT) allows for accurate discrimination between peripheral and central causes of acute vestibular syndrome (AVS). In this study, we sought to investigate whether the accuracy of artificial intelligence (AI) based vestibular stroke classification applied in unprocessed vHIT data is comparable to VOR gain classification.

Methods

We performed a prospective study from July 2015 until April 2020 on all patients presenting at the emergency department (ED) with signs of an AVS. The patients underwent vHIT followed by a delayed MRI, which served as a gold standard for stroke confirmation. The MRI ground truth labels were then applied to train a recurrent neural network (long short-term memory architecture) that used eye- and head velocity time series extracted from the vHIT examinations.

Results

We assessed 57 AVS patients, 39 acute unilateral vestibulopathy patients (AUVP) and 18 stroke patients. The overall sensitivity, specificity and accuracy for detecting stroke with a VOR gain cut-off of 0.57 was 88.8, 92.3, and 91.2%, respectively. The trained neural network was able to classify strokes with a sensitivity of 87.7%, a specificity of 88.4%, and an accuracy of 87.9% based on the unprocessed vHIT data. The accuracy of these two methods was not significantly different (p = 0.09).

Conclusion

AI can accurately diagnose a vestibular stroke by using unprocessed vHIT time series. The quantification of eye- and head movements with the use of machine learning and AI can serve in the future for an automated diagnosis in ED patients with acute dizziness. The application of different neural network architectures can potentially further improve performance and enable direct inference from raw video recordings.

Evaluation of School Children Nutritional Status in Ecuador Using Nutrimetry: A Proposal of an Education Protocol to Address the Determinants of Malnutrition

The education sector is a cornerstone in the battle against malnutrition in children. However, there are still no consolidated protocols that outline strategies for how nutrition programs in low- and middle-income countries can be delivered through the education sector. Establishing the correct community diagnosis is essential prior to the elaboration of an intervention plan for a school population that takes into account more than just traditional variables related to the nutritional status. A total of 574 boys and girls aged 3–11 years from three educational institutions in different municipalities in Ecuador participated in the study. Sociodemographic, anthropometric (weight and height) and coproparasitological data were obtained. Nutrimetry, which is a combination of two classical anthropometrics indicators, was used for the analysis of the nutritional status, and the indicators’ frequencies varied among the schools. In order to improve the nutritional status of children, we proposed a framework mainly focusing on establishing alliances with the education sector and taking into account gender equality; respect for the environment; and the customs, beliefs and traditions of each population. The results obtained from the analyses of other variables demonstrated the importance of an adequate diagnosis prior to any type of intervention at the nutritional level, since characteristics could vary by local area and have an impact on the successfulness of the intervention.

Comparing person-level matching algorithms to identify risk across disparate datasets among patients with a controlled substance prescription: retrospective analysis

Background

The opioid epidemic in the United States has precipitated a need for public health agencies to better understand risk factors associated with fatal overdoses. Matching person-level information stored in public health, medical, and human services datasets can enhance the understanding of opioid overdose risk factors and interventions.

Objective

This study compares approximate match versus exact match algorithms to link disparate datasets together for identifying persons at risk from an applied perspective.

Methods

This study used statewide prescription drug monitoring program (PDMP), arrest, and mortality data matched at the person-level using an approximate match and 2 exact match algorithms. Impact of matching was assessed by analyzing 3 independent concepts: (1) the prevalence of key risk indicators used by PDMP programs in practice, (2) the prevalence of arrests and fatal opioid overdose, and (3) the performance of a multivariate logistic regression for fatal opioid overdose. The PDMP key risk indicators included (1) multiple provider episodes (MPE), or patients with prescriptions from multiple prescribers and dispensers, (2) high morphine milligram equivalents (MMEs), which represents an opioid’s potency relative to morphine, and (3) overlapping opioid and benzodiazepine prescriptions.

Results

Prevalence of PDMP-based risk indicators were higher in the approximate match population for MPEs (n = 4893/1 859 445 [0.26%]) and overlapping opioid/benzodiazepines (n = 57 888/1 859 445 [4.71%]), but the exact-basic match population had the highest prevalence of individuals with high MMEs (n = 664/1 910 741 [3.11%]). Prevalence of arrests and deaths were highest for the approximate match population compared with the exact match populations. Model performance was comparable across the 3 matching algorithms (exact-basic validation area under the receiver operating characteristic curve [AUC]: 0.854; approximate validation AUC: 0.847; exact + zip validation AUC: 0.826) but resulted in different cutoff points balancing sensitivity and specificity.

Conclusions

Our study illustrates the specific tradeoffs of different matching methods. Further research should be performed to compare matching algorithms and its impact on the prevalence of key risk indicators in an applied setting that can improve understanding of risk within a population.

Improving the Prediction of Persistent High Healthcare Utilizers: Using an Ensemble Methodology

Background

A small proportion of high-need patients persistently use the bulk of health care services and incur disproportionate costs. Population health management (PHM) programs often refer to these patients as persistent high utilizers (PHUs). Accurate PHU prediction enables PHM programs to better align scarce health care resources with high-need PHUs while generally improving outcomes. While prior research in PHU prediction has shown promise, traditional regression methods used in these studies have yielded limited accuracy.

Objective

We are seeking to improve PHU predictions with an ensemble approach in a retrospective observational study design using insurance claim records.

Methods

We defined a PHU as a patient with health care costs in the top 20% of all patients for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in next 24 months. Our study population included 165,595 patients in the Johns Hopkins Health Care plan, with 8359 (5.1%) patients identified as PHUs in 2014 and 2015. We assessed the performance of several standalone machine learning methods and then an ensemble approach combining multiple models.

Results

The candidate ensemble with complement naïve Bayes and random forest layers produced increased sensitivity and positive predictive value (PPV; 49.0% and 50.3%, respectively) compared to logistic regression (46.8% and 46.1%, respectively).

Conclusions

Our results suggest that ensemble machine learning can improve prediction of care management needs. Improved PPV implies reduced incorrect referral of low-risk patients. With the improved sensitivity/PPV balance of this approach, resources may be directed more efficiently to patients needing them most.

Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)-Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study

BACKGROUND

Eating disorders affect an increasing number of people. Social networks provide information that can help.

OBJECTIVE

We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain.

METHODS

We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model.

RESULTS

A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer-based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%).

CONCLUSIONS

Bidirectional encoder representations from transformer-based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder-related tweets.

Spatial Dynamics and Multiscale Regression Modelling of Population Level Indicators for COVID-19 Spread in Malaysia

As COVID-19 dispersion occurs at different levels of gradients across geographies, the application of spatiotemporal science via computational methods can provide valuable insights to direct available resources and targeted interventions for transmission control. This ecological-correlation study evaluates the spatial dispersion of COVID-19 and its temporal relationships with crucial demographic and socioeconomic determinants in Malaysia, utilizing secondary data sources from public domains. By aggregating 51,476 real-time active COVID-19 case-data between 22 January 2021 and 4 February 2021 to district-level administrative units, the incidence, global and local Moran indexes were calculated. Spatial autoregressive models (SAR) complemented with geographical weighted regression (GWR) analyses were executed to determine potential demographic and socioeconomic indicators for COVID-19 spread in Malaysia. Highest active case counts were based in the Central, Southern and parts of East Malaysia regions of Malaysia. Countrywide global Moran index was 0.431 (p = 0.001), indicated a positive spatial autocorrelation of high standards within districts. The local Moran index identified spatial clusters of the main high–high patterns in the Central and Southern regions, and the main low–low clusters in the East Coast and East Malaysia regions. The GWR model, the best fit model, affirmed that COVID-19 spread in Malaysia was likely to be caused by population density (β coefficient weights = 0.269), followed by average household income per capita (β coefficient weights = 0.254) and GINI coefficient (β coefficient weights = 0.207). The current study concluded that the spread of COVID-19 was concentrated mostly in the Central and Southern regions of Malaysia. Population’s average household income per capita, GINI coefficient and population density were important indicators likely to cause the spread amongst communities.

Examining Neighborhood Socioeconomic Status as a Mediator of Racial/Ethnic Disparities in Hypertension Control Across Two San Francisco Health Systems

BACKGROUND

A contextual understanding of hypertension control can inform population health management strategies to mitigate cardiovascular disease events. This retrospective cohort study links neighborhood-level data with patients' health records to describe racial/ethnic differences in uncontrolled hypertension and determine if and to what extent these differences are mediated by neighborhood socioeconomic status (nSES).

METHODS

We conducted a mediation analysis using a sample of patients with hypertension from 2 health care delivery systems in San Francisco over 2 years (n=47 031). We used generalized structural equation modeling, adjusted for age, sex, and health care system, to estimate the contribution of nSES to disparities in uncontrolled hypertension between White patients and Black, Hispanic/Latino, and Asian patients, respectively. Sensitivity analysis removed adjustment for health care system.

RESULTS

Over half the cohort (62%) experienced uncontrolled hypertension during the study period. Racial/ethnic groups showed substantial differences in prevalence of uncontrolled hypertension and distribution of nSES quintiles. Compared with White patients, Black, and Hispanic/Latino patients had higher adjusted odds of uncontrolled hypertension: odds ratio, 1.79 [95% CI, 1.67-1.91] and odds ratio, 1.38 [95% CI, 1.29-1.47], respectively and nSES accounted for 7% of the disparity in both comparisons. Asian patients had slightly lower adjusted odds of uncontrolled hypertension when compared with White patients: odds ratio, 0.95 [95% CI, 0.89-0.99] and the mediating effect of nSES did not change the direction of the relationship. Sensitivity analysis increased the proportion mediated by nSES to 11% between Black and White patients and 13% between Hispanic/Latino and White patients, but did not influence differences between Asian and White patients.

CONCLUSIONS

Among patients with hypertension in this study, nSES mediated a small proportion of racial/ethnic disparities in uncontrolled hypertension. Population health management strategies may be most effective by focusing on additional structural and interpersonal pathways such as racism and discrimination in health care settings.

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data

BACKGROUND

A high proportion of health care services are persistently utilized by a small subpopulation of patients. To improve clinical outcomes while reducing costs and utilization, population health management programs often provide targeted interventions to patients who may become persistent high users/utilizers (PHUs). Enhanced prediction and management of PHUs can improve health care system efficiencies and improve the overall quality of patient care.

OBJECTIVE

The aim of this study was to detect key classes of diseases and medications among the study population and to assess the predictive value of these classes in identifying PHUs.

METHODS

This study was a retrospective analysis of insurance claims data of patients from the Johns Hopkins Health Care system. We defined a PHU as a patient incurring health care costs in the top 20% of all patients' costs for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in 2014-2015. We applied latent class analysis (LCA), an unsupervised clustering approach, to identify patient subgroups with similar diagnostic and medication patterns to differentiate variations in health care utilization across PHUs. Logistic regression models were then built to predict PHUs in the full population and in select subpopulations. Predictors included LCA membership probabilities, demographic covariates, and health utilization covariates. Predictive powers of the regression models were assessed and compared using standard metrics.

RESULTS

We identified 164,221 patients with continuous enrollment between 2013 and 2015. The mean study population age was 19.7 years, 55.9% were women, 3.3% had ≥1 hospitalization, and 19.1% had 10+ outpatient visits in 2013. A total of 8359 (5.09%) patients were identified as PHUs in both 2014 and 2015. The LCA performed optimally when assigning patients to four probability disease/medication classes. Given the feedback provided by clinical experts, we further divided the population into four diagnostic groups for sensitivity analysis: acute upper respiratory infection (URI) (n=53,232; 4.6% PHUs), mental health (n=34,456; 12.8% PHUs), otitis media (n=24,992; 4.5% PHUs), and musculoskeletal (n=24,799; 15.5% PHUs). For the regression models predicting PHUs in the full population, the F1-score classification metric was lower using a parsimonious model that included LCA categories (F1=38.62%) compared to that of a complex risk stratification model with a full set of predictors (F1=48.20%). However, the LCA-enabled simple models were comparable to the complex model when predicting PHUs in the mental health and musculoskeletal subpopulations (F1-scores of 48.69% and 48.15%, respectively). F1-scores were lower than that of the complex model when the LCA-enabled models were limited to the otitis media and acute URI subpopulations (45.77% and 43.05%, respectively).

CONCLUSIONS

Our study illustrates the value of LCA in identifying subgroups of patients with similar patterns of diagnoses and medications. Our results show that LCA-derived classes can simplify predictive models of PHUs without compromising predictive accuracy. Future studies should investigate the value of LCA-derived classes for predicting PHUs in other health care settings.

Incidence and Geographic Distribution of Injuries Due to Falls Among Pediatric Communities of Maryland

OBJECTIVES

Falls are the leading cause of pediatric injury and account for the majority of emergency department injury visits, costing US $5 billion in medical costs annually. Epidemiology of pediatric falls has primarily been studied at single hospital centers and has not been analyzed statewide. We assessed pediatric falls across Maryland and geographically mapped them by census tract and block group.

METHODS

The study used Maryland Health Services Cost Review Commission discharge data to retrospectively analyze the demographics and cross-sectional incidence rates of fall injuries in Maryland from 2013 to 2015. Geographical clusters were calculated for pediatric falls in Maryland and Baltimore City.

RESULTS

From 2013 to 2015, Maryland hospitals discharged 738,819 pediatric patients, of whom 77,113 had fall injuries. Falls were more prevalent among males (56%), white race (55%), and patients with public insurance (56%). Over this period, 2 children who presented with fall injuries died. The incidence of falls did not vary from 2013 (27,481 children) to 2014 (27,261) and 2015 (26,451). Mapping fall injuries across Maryland identified Baltimore City as the primary cluster and rural pockets as secondary clusters of high incidence rates. Baltimore City maps showed a stable high-incidence cluster in the southwest region across all 3 years.

CONCLUSIONS

Pediatric fall injuries comprise a large volume of emergency department visits yet have a low mortality. Geographic mapping shows that fall incidence varies across the state and persists over time. Statewide geographic information can be used to focus resource management and target prevention strategies.

Internet Access, Social Risk Factors, and Web-Based Social Support Seeking Behavior: Assessing Correlates of the "Digital Divide" Across Neighborhoods in The State of Maryland

We aimed to empirically measure the degree to which there is a “digital divide” in terms of access to the internet at the small-area community level within the State of Maryland and the City of Baltimore and to assess the relationship and association of this divide with community-level SDOH risk factors, community-based social service agency location, and web-mediated support service seeking behavior. To assess the socio-economic characteristics of the neighborhoods across the state, we calculated the Area Deprivation Index (ADI) using the U.S. Census, American Community Survey (5-year estimates) of 2017. To assess the digital divide, at the community level, we used the Federal Communications Commission (FCC) data on the number of residential fixed Internet access service connections. We assessed the availability of and web-based access to community-based social service agencies using data provided by the “Aunt Bertha” information platform. We performed community and regional level descriptive and special analyses for ADI social risk factors, connectivity, and both the availability of and web-based searches for community-based social services. To help assess potential neighborhood linked factors associated with the rates of web-based social services searches by individuals in need, we applied logistic regression using generalized estimating equation modeling. Baltimore City contained more disadvantaged neighborhoods compared to other areas in Maryland. In Baltimore City, 20.3% of neighborhoods (defined by census block groups) were disadvantaged with ADI at the 90th percentile while only 6.6% of block groups across Maryland were in this disadvantaged category. Across the State, more than half of all census tracts had 801–1000 households (per 1000 households) with internet subscription. In contrast, in Baltimore City about half of all census tracts had only 401–600 of the households (per 1000 households) with internet subscriptions. Most block groups in Maryland and Baltimore City lacked access to social services facilities (61% of block groups at the 90th percentile of disadvantage in Maryland and 61.3% of block groups at the 90th percentile of disadvantage in Baltimore City). After adjusting for other variables, a 1% increase in the ADI measure of social disadvantage, resulting in a 1.7% increase in the number of individuals seeking social services. While more work is needed, our findings support the premise that the digital divide is closely associated with other SDOH factors. The policymakers must propose policies to address the digital divide on a national level and also in disadvantaged communities experiencing the digital divide in addition to other SDOH challenges.

Measuring the Value of a Practical Text Mining Approach to Identify Patients With Housing Issues in the Free-Text Notes in Electronic Health Record: Findings of a Retrospective Cohort Study

Introduction: Despite the growing efforts to standardize coding for social determinants of health (SDOH), they are infrequently captured in electronic health records (EHRs). Most SDOH variables are still captured in the unstructured fields (i.e., free-text) of EHRs. In this study we attempt to evaluate a practical text mining approach (i.e., advanced pattern matching techniques) in identifying phrases referring to housing issues, an important SDOH domain affecting value-based healthcare providers, using EHR of a large multispecialty medical group in the New England region, United States. To present how this approach would help the health systems to address the SDOH challenges of their patients we assess the demographic and clinical characteristics of patients with and without housing issues and briefly look into the patterns of healthcare utilization among the study population and for those with and without housing challenges.

Methods: We identified five categories of housing issues [i.e., homelessness current (HC), homelessness history (HH), homelessness addressed (HA), housing instability (HI), and building quality (BQ)] and developed several phrases addressing each one through collaboration with SDOH experts, consulting the literature, and reviewing existing coding standards. We developed pattern-matching algorithms (i.e., advanced regular expressions), and then applied them in the selected EHR. We assessed the text mining approach for recall (sensitivity) and precision (positive predictive value) after comparing the identified phrases with manually annotated free-text for different housing issues.

Results: The study dataset included EHR structured data for a total of 20,342 patients and 2,564,344 free-text clinical notes. The mean (SD) age in the study population was 75.96 (7.51). Additionally, 58.78% of the cohort were female. BQ and HI were the most frequent housing issues documented in EHR free-text notes and HH was the least frequent one. The regular expression methodology, when compared to manual annotation, had a high level of precision (positive predictive value) at phrase, note, and patient levels (96.36, 95.00, and 94.44%, respectively) across different categories of housing issues, but the recall (sensitivity) rate was relatively low (30.11, 32.20, and 41.46%, respectively).

Conclusion: Results of this study can be used to advance the research in this domain, to assess the potential value of EHR's free-text in identifying patients with a high risk of housing issues, to improve patient care and outcomes, and to eventually mitigate socioeconomic disparities across individuals and communities.

Using Base-ml to Learn Classification of Common Vestibular Disorders on DizzyReg Registry Data

Background: Multivariable analyses (MVA) and machine learning (ML) applied on large datasets may have a high potential to provide clinical decision support in neuro-otology and reveal further avenues for vestibular research. To this end, we build base-ml, a comprehensive MVA/ML software tool, and applied it to three increasingly difficult clinical objectives in differentiation of common vestibular disorders, using data from a large prospective clinical patient registry (DizzyReg).

Methods: Base-ml features a full MVA/ML pipeline for classification of multimodal patient data, comprising tools for data loading and pre-processing; a stringent scheme for nested and stratified cross-validation including hyper-parameter optimization; a set of 11 classifiers, ranging from commonly used algorithms like logistic regression and random forests, to artificial neural network models, including a graph-based deep learning model which we recently proposed; a multi-faceted evaluation of classification metrics; tools from the domain of “Explainable AI” that illustrate the input distribution and a statistical analysis of the most important features identified by multiple classifiers.

Results: In the first clinical task, classification of the bilateral vestibular failure (N = 66) vs. functional dizziness (N = 346) was possible with a classification accuracy ranging up to 92.5% (Random Forest). In the second task, primary functional dizziness (N = 151) vs. secondary functional dizziness (following an organic vestibular syndrome) (N = 204), was classifiable with an accuracy ranging from 56.5 to 64.2% (k-nearest neighbors/logistic regression). The third task compared four episodic disorders, benign paroxysmal positional vertigo (N = 134), vestibular paroxysmia (N = 49), Menière disease (N = 142) and vestibular migraine (N = 215). Classification accuracy ranged between 25.9 and 50.4% (Naïve Bayes/Support Vector Machine). Recent (graph-) deep learning models classified well in all three tasks, but not significantly better than more traditional ML methods. Classifiers reliably identified clinically relevant features as most important toward classification.

Conclusion: The three clinical tasks yielded classification results that correlate with the clinical intuition regarding the difficulty of diagnosis. It is favorable to apply an array of MVA/ML algorithms rather than a single one, to avoid under-estimation of classification accuracy. Base-ml provides a systematic benchmarking of classifiers, with a standardized output of MVA/ML performance on clinical tasks. To alleviate re-implementation efforts, we provide base-ml as an open-source tool for the community.

Design of Generalized Search Interfaces for Health Informatics

In this paper, we investigate ontology-supported interfaces for health informatics search tasks involving large document sets. We begin by providing background on health informatics, machine learning, and ontologies. We review leading research on health informatics search tasks to help formulate high-level design criteria. We use these criteria to examine traditional design strategies for search interfaces. To demonstrate the utility of the criteria, we apply them to the design of ONTology-supported Search Interface (ONTSI), a demonstrative, prototype system. ONTSI allows users to plug-and-play document sets and expert-defined domain ontologies through a generalized search interface. ONTSI’s goal is to help align users’ common vocabulary with the domain-specific vocabulary of the plug-and-play document set. We describe the functioning and utility of ONTSI in health informatics search tasks through a workflow and a scenario. We conclude with a summary of ongoing evaluations, limitations, and future research.

Measuring the Interactions Between Health Demand, Informatics Supply, and Technological Applications in Digital Medical Innovation for China: Content Mapping and Analysis

BACKGROUND

There were 2 major incentives introduced by the Chinese government to promote medical informatics in 2009 and 2016. As new drugs are the major source of medical innovation, informatics-related concepts and techniques are a major source of digital medical innovation. However, it is unclear whether the research efforts of medical informatics in China have met the health needs, such as disease management and population health.

OBJECTIVE

We proposed an approach to mapping the interplay between different knowledge entities by using the tree structure of Medical Subject Headings (MeSH) to gain insights into the interactions between informatics supply, health demand, and technological applications in digital medical innovation in China.

METHODS

All terms under the MeSH tree parent node "Diseases [C]" or node "Health [N01.400]" or "Public Health [N06.850]" were labelled as H. All terms under the node "Information Science [L]" were labelled as I, and all terms under node "Analytical, Diagnostic and Therapeutic Techniques, and Equipment [E]" were labelled as T. The H-I-T interactions can be measured by using their co-occurrences in a given publication.

RESULTS

The H-I-T interactions in China are showing significant growth and a more concentrated interplay were observed. Computing methodologies, informatics, and communications media (such as social media and the internet) constitute the majority of I-related concepts and techniques used for resolving the health promotion and diseases management problems in China. Generally there is a positive correlation between the burden and informatics research efforts for diseases in China. We think it is not contradictory that informatics research should be focused on the greatest burden of diseases or where it can have the most impact. Artificial intelligence is a competing field of medical informatics research in China, with a notable focus on diagnostic deep learning algorithms for medical imaging.

CONCLUSIONS

It is suggested that technological transfers, namely the functionality to be realized by medical/health informatics (eg, diagnosis, therapeutics, surgical procedures, laboratory testing techniques, and equipment and supplies) should be strengthened. Research on natural language processing and electronic health records should also be strengthened to improve the real-world applications of health information technologies and big data in the future.

Developing Evidence-based Population Health Informatics curriculum: Integrating competency based model and job analysis

With the rapid pace of technological advancements, public health professions require a core set of informatics skills. The objective of the study is to integrate informatics competencies and job analysis to guide development of an evidence-based curriculum framework and apply it towards creation of a population health informatics program. We conducted content analysis of the Population Health Informatics related job postings in the state of New York between June and July 2019 using the Indeed job board. The search terms included "health informatics" and "population health informatics." The initial search yielded 496 job postings. After removal of duplicates, inactive postings and that did not include details of the positions' responsibilities resulted in 306 jobs. Information recorded from the publicly available job postings included job categories, type of hiring organization, educational degree preferred and required, work experience preferred and required, salary information, job type, job location, associated knowledge, skills and expertise and software skills. Most common job title was that of an analyst (21%, n=65) while more than one-third of the hiring organizations were health systems (35%, n=106). 95% (n=291) of the jobs were fulltime and nearly half of these jobs were in New York City (47%, n=143). Data/statistical analysis (68%, n=207), working in multidisciplinary teams (35%, n=108), and biomedical/clinical experience (30%, n=93) were the common skills needed. Structured query language (SQL), Python, and R language were common programming language skills. A broad framework of integrating informatics competencies, combined with analysis of the skills the jobs needed, and knowledge acquisition based on global health informatics projects guided the development of an online population health informatics curriculum in a rapidly changing technological environment.

Interdisciplinary data science to advance environmental health research and improve birth outcomes

Rates of preterm birth and low birthweight continue to rise in the United States and pose a significant public health problem. Although a variety of environmental exposures are known to contribute to these and other adverse birth outcomes, there has been a limited success in developing policies to prevent these outcomes. A better characterization of the complexities between multiple exposures and their biological responses can provide the evidence needed to inform public health policy and strengthen preventative population-level interventions. In order to achieve this, we encourage the establishment of an interdisciplinary data science framework that integrates epidemiology, toxicology and bioinformatics with biomarker-based research to better define how population-level exposures contribute to these adverse birth outcomes. The proposed interdisciplinary research framework would 1) facilitate data-driven analyses using existing data from health registries and environmental monitoring programs; 2) develop novel algorithms with the ability to predict which exposures are driving, in this case, adverse birth outcomes in the context of simultaneous exposures; and 3) refine biomarker-based research, ultimately leading to new policies and interventions to reduce the incidence of adverse birth outcomes.

Need and Importance of Nutrition Informatics in India: A Perspective

Nutrition informatics (NI) is the effective retrieval, organization, storage, and optimum use of information, data and knowledge for food-and-nutrition-related problem-solving and decision-making. There is a growing opportunity to facilitate technology-enabled behavioral change interventions to support NI research and practice. This paper highlights the changing landscape of food and nutrition practices in India to prepare a NI workforce that could provide some valuable tools to address the double burden of nutrition. Management and interpretation of data could help clarify the relationships and interrelationships of diet and disease in India on both national and regional levels. Individuals with expertise in food and nutrition may receive training in informatics to develop national informatics systems. NI professionals develop tools and techniques, manage various projects and conduct informatics research. These professionals should be well prepared to work in technological settings and communicate data and information effectively. Opportunities for training in NI are very limited in developing countries. Given the current progress in developing platforms and informatics infrastructure, India could serve as an example to other countries to promote NI to support achieving SDGs and other public health initiatives.

Analysis of Social Media Discussions on (#)Diet by Blue, Red, and Swing States in the U.S

The relationship between political affiliations and diet-related discussions on social media has not been studied on a population level. This study used a cost- and -time effective framework to leverage, aggregate, and analyze data from social media. This paper enhances our understanding of diet-related discussions with respect to political orientations in U.S. states. This mixed methods study used computational methods to collect tweets containing "diet" or "#diet" shared in a year, identified tweets posted by U.S. Twitter users, disclosed topics of tweets, and compared democratic, republican, and swing states based on the weight of topics. A qualitative method was employed to code topics. We found 32 unique topics extracted from more than 800,000 tweets, including a wide range of themes, such as diet types and chronic conditions. Based on the comparative analysis of the topic weights, our results revealed a significant difference between democratic, republican, and swing states. The largest difference was detected between swing and democratic states, and the smallest difference was identified between swing and republican states. Our study provides initial insight on the association of potential political leanings with health (e.g., dietary behaviors). Our results show diet discussions differ depending on the political orientation of the state in which Twitter users reside. Understanding the correlation of dietary preferences based on political orientation can help develop targeted and effective health promotion, communication, and policymaking strategies.

Identifying Opportunities to Strengthen the Public Health Informatics Infrastructure: Exploring Hospitals' Challenges with Data Exchange

Policy Points Even though most hospitals have the technological ability to exchange data with public health agencies, the majority continue to experience challenges. Most challenges are attributable to the general resources of public health agencies, although workforce limitations, technology issues such as a lack of data standards, and policy uncertainty around reporting requirements also remain prominent issues. Ongoing funding to support the adoption of technology and strengthen the development of the health informatics workforce, combined with revising the promotion of the interoperability scoring approach, will likely help improve the exchange of electronic data between hospitals and public health agencies.

CONTEXT

The novel coronavirus 2019 (COVID-19) pandemic has highlighted significant barriers in the exchange of essential information between hospitals and local public health agencies. Thus it remains important to clarify the specific issues that hospitals may face in reporting to public health agencies to inform focused approaches to improve the information exchange for the current pandemic as well as ongoing public health activities and population health management.

METHODS

This study uses cross-sectional data of acute-care, nonfederal hospitals from the 2017 American Hospital Association Annual Survey and Information Technology supplement. Guided by the technology-organization-environment framework, we coded the responses to a question regarding the challenges that hospitals face in submitting data to public health agencies by using content analysis according to the type of challenge (i.e., technology, organization, or environment), responsible entity (i.e., hospital, public health agency, vendor, multiple), and the specific issue described. We used multivariable logistic and multinomial regression to identify characteristics of hospitals associated with experiencing the types of challenges.

FINDINGS

Our findings show that of the 2,794 hospitals in our analysis, 1,696 (61%) reported experiencing at least one challenge in reporting health data to a public health agency. Organizational issues were the most frequently reported type of challenge, noted by 1,455 hospitals. The most common specific issue, reported by 1,117 hospitals, was the general resources of public health agencies. An advanced EHR system and participation in a health information exchange both decreased the likelihood of not reporting experiencing a challenge and increased the likelihood of reporting an organizational challenge.

CONCLUSIONS

Our findings inform policy recommendations such as improving data standards, increasing funding for public health agencies to improve their technological capabilities, offering workforce training programs, and increasing clarity of policy specifications and reporting. These approaches can improve the exchange of information between hospitals and public health agencies.

The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment

OBJECTIVE

Coronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers.

MATERIALS AND METHODS

The Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics.

RESULTS

Organized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access.

CONCLUSIONS

The N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19.

The Computer Will See You Now: Overcoming Barriers to Adoption of Computer-Assisted History Taking (CAHT) in Primary Care

Patient health information is increasingly collected through multiple modalities, including electronic health records, wearables, and connected devices. Computer-assisted history taking could provide an additional channel to collect highly relevant, comprehensive, and accurate patient information while reducing the burden on clinicians and face-to-face consultation time. Considering restrictions to consultation time and the associated negative health outcomes, patient-provided health data outside of consultation can prove invaluable in health care delivery. Over the years, research has highlighted the numerous benefits of computer-assisted history taking; however, the limitations have proved an obstacle to adoption. In this viewpoint, we review these limitations under 4 main categories (accessibility, affordability, accuracy, and acceptability) and discuss how advances in technology, computing power, and ubiquity of personal devices offer solutions to overcoming these.

Big Data and Digital Solutions: Laying the Foundation for Cardiovascular Population Management CME

There are huge gaps in evidence-based cardiovascular care at the national, organizational, practice, and provider level that can be attributed to variation in provider attitudes, lack of incentives for positive change and care standardization, and observed uncertainty in clinical decision making. Big data analytics and digital application platforms-such as patient care dashboards, clinical decision support systems, mobile patient engagement applications, and key performance indicators-offer unique opportunities for value-based healthcare delivery and efficient cardiovascular population management. Successful implementation of big data solutions must include a multidisciplinary approach, including investment in big data platforms, harnessing technology to create novel digital applications, developing digital solutions that can inform the actions of clinical and policy decision makers and relevant stakeholders, and optimizing engagement strategies with the public and information-empowered patients.

Identifying vulnerable older adult populations by contextualizing geriatric syndrome information in clinical notes of electronic health records

OBJECTIVE

Geriatric syndromes such as functional disability and lack of social support are often not encoded in electronic health records (EHRs), thus obscuring the identification of vulnerable older adults in need of additional medical and social services. In this study, we automatically identify vulnerable older adult patients with geriatric syndrome based on clinical notes extracted from an EHR system, and demonstrate how contextual information can improve the process.

MATERIALS AND METHODS

We propose a novel end-to-end neural architecture to identify sentences that contain geriatric syndromes. Our model learns a representation of the sentence and augments it with contextual information: surrounding sentences, the entire clinical document, and the diagnosis codes associated with the document. We trained our system on annotated notes from 85 patients, tuned the model on another 50 patients, and evaluated its performance on the rest, 50 patients.

RESULTS

Contextual information improved classification, with the most effective context coming from the surrounding sentences. At sentence level, our best performing model achieved a micro-F1 of 0.605, significantly outperforming context-free baselines. At patient level, our best model achieved a micro-F1 of 0.843.

DISCUSSION

Our solution can be used to expand the identification of vulnerable older adults with geriatric syndromes. Since functional and social factors are often not captured by diagnosis codes in EHRs, the automatic identification of the geriatric syndrome can reduce disparities by ensuring consistent care across the older adult population.

CONCLUSION

EHR free-text can be used to identify vulnerable older adults with a range of geriatric syndromes.

Another gender data gap: female drowning in Aotearoa, New Zealand

INTRODUCTION

A gender gap is present in drowning research and prevention interventions, resulting in an inequitable focus on males. This study aimed to address the gender data gap, exploring female drowning in Aotearoa, New Zealand.

METHODS

National data on female fatal and non-fatal drowning requiring hospitalisation between 2003 and 2019 were sourced from DrownBase, Water Safety New Zealand's drowning database. Univariate and χ² analyses were conducted for fatal and hospitalisation data. Crude rates were calculated and used to explore temporal trends and RR by age groups and ethnicity for fatal and non-fatal drowning. Ratios for drowning-related hospitalisations and Accident Compensation Corporation (ACC) claims to drowning deaths were also calculated.

RESULTS

From 2003 to 2019, a total of 1087 female drowning fatalities and non-fatal (76.0%) drowning incidents requiring hospitalisation occurred. Linear trends indicate hospitalisations increased (y=0.0766x+1.4271; R²=0.4438), while fatal drowning decreased (y=-0.0101x+0.7671; R²=0.1011). The highest fatal (1.60) and non-fatal (8.22) drowning rates were seen among children aged 0-4 years. For every one female drowning fatality, there are 3.46 hospital admissions and 675.55 ACC claims.

DISCUSSION

Female drowning represents a significant burden on the health system and the community in New Zealand. Further investment in interventions targeting females about their own risky behaviours around water (not only children in their care) is suggested, including interventions focused on hazardous conditions and alcohol consumption.

CONCLUSION

For decades, the focus of drowning prevention among adolescents and adults has been on males. However, efforts must be broadened to prevent any further increase in drowning-related incidents among females in Aotearoa, New Zealand.

Assessing the geographical distribution of comorbidity among commercially insured individuals in South Africa

BACKGROUND

Comorbidities are strong predictors of current and future healthcare needs and costs; however, comorbidities are not evenly distributed geographically. A growing need has emerged for comorbidity surveillance that can inform decision-making. Comorbidity-derived risk scores are increasingly being used as valuable measures of individual health to describe and explain disease burden in populations.

METHODS

This study assessed the geographical distribution of comorbidity and its associated financial implications among commercially insured individuals in South Africa (SA). A retrospective, cross-sectional analysis was performed comparing the geographical distribution of comorbidities for 2.6 million commercially insured individuals over 2016-2017, stratified by geographical districts in SA. We applied the Johns Hopkins ACG® System across the insurance claims data of a large health plan administrator in SA to measure comorbidity as a risk score for each individual. We aggregated individual risk scores to determine the average risk score per district, also known as the comorbidity index (CMI), to describe the overall disease burden of each district.

RESULTS

We observed consistently high CMI scores in districts of the Free State and KwaZulu-Natal provinces for all population groups before and after age adjustment. Some areas exhibited almost 30% higher healthcare utilization after age adjustment. Districts in the Northern Cape and Limpopo provinces had the lowest CMI scores with 40% lower than expected healthcare utilization in some areas after age adjustment.

CONCLUSIONS

Our results show underlying disparities in CMI at national, provincial, and district levels. Use of geo-level CMI scores, along with other social data affecting health outcomes, can enable public health departments to improve the management of disease burdens locally and nationally. Our results could also improve the identification of underserved individuals, hence bridging the gap between public health and population health management efforts.

A Digitally Competent Health Workforce: Scoping Review of Educational Frameworks

BACKGROUND

Digital health technologies can be key to improving health outcomes, provided health care workers are adequately trained to use these technologies. There have been efforts to identify digital competencies for different health care worker groups; however, an overview of these efforts has yet to be consolidated and analyzed.

OBJECTIVE

The review aims to identify and study existing digital health competency frameworks for health care workers and provide recommendations for future digital health training initiatives and framework development.

METHODS

A literature search was performed to collate digital health competency frameworks published from 2000. A total of 6 databases including gray literature sources such as OpenGrey, ResearchGate, Google Scholar, Google, and websites of relevant associations were searched in November 2019. Screening and data extraction were performed in parallel by the reviewers. The included evidence is narratively described in terms of characteristics, evolution, and structural composition of frameworks. A thematic analysis was also performed to identify common themes across the included frameworks.

RESULTS

In total, 30 frameworks were included in this review, a majority of which aimed at nurses, originated from high-income countries, were published since 2016, and were developed via literature reviews, followed by expert consultations. The thematic analysis uncovered 28 digital health competency domains across the included frameworks. The most prevalent domains pertained to basic information technology literacy, health information management, digital communication, ethical, legal, or regulatory requirements, and data privacy and security. The Health Information Technology Competencies framework was found to be the most comprehensive framework, as it presented 21 out of the 28 identified domains, had the highest number of competencies, and targeted a wide variety of health care workers.

CONCLUSIONS

Digital health training initiatives should focus on competencies relevant to a particular health care worker group, role, level of seniority, and setting. The findings from this review can inform and guide digital health training initiatives. The most prevalent competency domains identified represent essential interprofessional competencies to be incorporated into health care workers' training. Digital health frameworks should be regularly updated with novel digital health technologies, be applicable to low- and middle-income countries, and include overlooked health care worker groups such as allied health professionals.