Health Information Technology Research Articles

Empowering nurses to champion Health equity & BE FAIR: Bias elimination for fair and responsible AI in healthcare.

The concept of health equity by design encompasses a multifaceted approach that integrates actions aimed at eliminating biased, unjust, and correctable differences among groups of people as a fundamental element in the design of algorithms. As algorithmic tools are increasingly integrated into clinical practice at multiple levels, nurses are uniquely positioned to address challenges posed by the historical marginalization of minority groups and its intersections with the use of "big data" in healthcare settings; however, a coherent framework is needed to ensure that nurses receive appropriate training in these domains and are equipped to act effectively. We introduce the Bias Elimination for Fair AI in Healthcare (BE FAIR) framework, a comprehensive strategic approach that incorporates principles of health equity by design, for nurses to employ when seeking to mitigate bias and prevent discriminatory practices arising from the use of clinical algorithms in healthcare. By using examples from a "real-world" AI governance framework, we aim to initiate a wider discourse on equipping nurses with the skills needed to champion the BE FAIR initiative. Drawing on principles recently articulated by the Office of the National Coordinator for Health Information Technology, we conducted a critical examination of the concept of health equity by design. We also reviewed recent literature describing the risks of artificial intelligence (AI) technologies in healthcare as well as their potential for advancing health equity. Building on this context, we describe the BE FAIR framework, which has the potential to enable nurses to take a leadership role within health systems by implementing a governance structure to oversee the fairness and quality of clinical algorithms. We then examine leading frameworks for promoting health equity to inform the operationalization of BE FAIR within a local AI governance framework. The application of the BE FAIR framework within the context of a working governance system for clinical AI technologies demonstrates how nurses can leverage their expertise to support the development and deployment of clinical algorithms, mitigating risks such as bias and promoting ethical, high-quality care powered by big data and AI technologies. As health systems learn how well-intentioned clinical algorithms can potentially perpetuate health disparities, we have an opportunity and an obligation to do better. New efforts empowering nurses to advocate for BE FAIR, involving them in AI governance, data collection methods, and the evaluation of tools intended to reduce bias, mark important steps in achieving equitable healthcare for all.

Roles and Responsibilities of the Global Specialist Digital Health Workforce: Analysis of Global Census Data.

The Global Specialist Digital Health Workforce Census is the largest workforce survey of the specialist roles that support the development, use, management, and governance of health data, health information, health knowledge, and health technology. This paper aims to present an analysis of the roles and functions reported by respondents in the 2023 census. The 2023 census was deployed using Qualtrics and was open from July 1 to August 13, 2023. A broad definition was provided to guide respondents about who is in the specialist digital health workforce. Anyone who self-identifies as being part of this workforce could undertake the survey. The data was analyzed using descriptive statistical analysis and thematic analysis of the functions respondents reported in their roles. A total of 1103 respondents completed the census, with data reported about their demographic information and their roles. The majority of respondents lived in Australia (n=870, 78.9%) or New Zealand (n=130, 11.8%), with most (n=620, 56.3%) aged 35-54 years and identifying as female (n=720, 65.3%). The top four occupational specialties were health informatics (n=179, 20.2%), health information management (n=175, 19.8%), health information technology (n=128, 14.4%), and health librarianship (n=104, 11.7%). Nearly all (n=797, 90%) participants identified as a manager or professional. Less than half (430/1019, 42.2%) had a formal qualification in a specialist digital health area, and only one-quarter (244/938, 26%) held a credential in a digital health area. While two-thirds (502/763, 65.7%) reported undertaking professional development in the last year, most were self-directed activities, such as seeking information or consuming online content. Work undertaken by specialist digital health workers could be classified as either leadership, functional, occupational, or technological. Future specialist digital health workforce capability frameworks should include the aspects of leadership, function, occupation, and technology. This largely unqualified workforce is undertaking little formal professional development to upskill them to continue to support the safe delivery and management of health and care through the use of digital data and technology.

Nurse Involvement in Health Information Technology Design for Computerized Nursing Practice: A Scoping Review.

This scoping review assesses evidence regarding nurse involvement in health information technology (health IT) design, focusing on the method(s), frequency, capacity, and levels of involvement. The JBI methodology for scoping reviews was used to search seven multidisciplinary databases, yielding 2948 articles. After screening, 98 articles were included for data abstraction. Textual data summary is ongoing. Preliminary findings highlight that nurses are often involved in the late stages of health IT design, with less frequency in the early and pre-programming design phases. Most studies used a user-centered design approach to elicit nurses' views about health IT tools after the tools had been developed, with nearly half being point of care nurses. Increasing nurse involvement in health IT design may help to improve nurses' perceptions of health IT that nurses use.

Clinical Outcomes of a Novel Multidisciplinary Care Program in Advanced Kidney Disease (PEAK)

IntroductionMulti-disciplinary care (MDC) for late-stage chronic kidney disease (CKD) has been associated with improved patient outcomes compared with traditional nephrology care, but the optimal MDC model is unknown. In 2015, we implemented a novel MDC model for patients with late-stage CKD informed by the Chronic Care Model conceptual framework, including an expanded MDC team, care plan meetings, clinical risk prediction, and a patient dashboard. MethodsWe conducted a single-center, retrospective cohort study of adults with late-stage CKD (estimated glomerular filtration rate [eGFR] < 30 mL/min per 1.73m2) enrolled from May 2015 to February 2020 in the Program for Education in Advanced Kidney disease (PEAK). Our primary composite outcome was an optimal transition to end-stage kidney disease (ESKD) defined as starting in-center hemodialysis (ICHD) as an outpatient with an arteriovenous fistula (AVF) or graft (AVG), or receiving home dialysis, or a pre-emptive kidney transplant. Secondary outcomes included home dialysis initiation, pre-emptive transplantation, vascular access at dialysis initiation, and location of ICHD initiation. We used logistic regression to examine trends in outcomes. Results were stratified by race, ethnicity, and insurance payor and compared with national and regional averages from the United States Renal Data System (USRDS) averaged from 2015 to 2019. ResultsAmong 489 patients in the PEAK program, 37 (8%) died prior to ESKD and 151 (31%) never progressed to ESKD. Of the 301 (62%) patients who progressed to ESKD, 175 (58%) achieved an optimal transition to ESKD, including 54 (18%) peritoneal dialysis, 16 (5%) home hemodialysis, and 36 (12%) preemptive transplant. Of the 195 (65%) patients starting ICHD, 51% started with an AVF or AVG and 52% started as an outpatient. The likelihood of starting home dialysis increased by 1.34 times per year from 2015 to 2020 (95% CI 1.05 – 1.71, p = 0.018) in multivariable adjusted results. Optimal transitions to ESKD and home dialysis rates were higher than national USRDS data (58% vs. 30%; 23% vs. 11%) across patient race, ethnicity, and payor. ConclusionsPatients enrolled in a novel comprehensive MDC model coupled with risk prediction and health information technology were nearly twice as likely to achieve an optimal transition to ESKD and start dialysis at home, compared with national averages.

Road to a National Health Information Network: US Trusted Exchange Framework and Common Agreement (TEFCA).

The Trusted Exchange Framework and Common Agreement (TEFCA) is a U.S. government initiative aimed at promoting the secure and interoperable exchange of electronic health information (EHI) across the healthcare ecosystem. In the U.S., TEFCA was established as part of the 21st Century Cures Act, signed into law in December 2016. Methods: A literature search using the PRISMA guidelines will be conducted through PubMed, CINAHL, Google Scholar, and Web of Science, for dates 2013-2024 will be conducted. Results will be demonstrated with a timeline, graphics, and written text on the key points of technical and operational standards for HIE, rules and expectations for data sharing under the Common Agreement, governance framework for implementation and enforcement principles, stakeholders and collaborators, and interoperability challenges. TEFCA seeks to improve patient care, reduce healthcare costs, and enhance overall healthcare quality by facilitating the seamless exchange of data between different healthcare entities. Sharing this information can contribute to nursing informatics practice and knowledge as the U.S. and other countries strive towards better interoperability in the race to improve patient care and outcomes using health information technology.

A Different View of Health Information Technology Workarounds in Critical Care.

When health information technology (HIT) was introduced into the hospital setting there was an obvious disruption to nursing workflow. In many cases it took a nurse extra steps or extra time to complete processes such as clinical documentation and medication administration. In response to HIT problems, nurses developed workarounds. Research on nursing workarounds has been hindered by a lack of variable definitions, measures and research models. This paper offers the results of an exploratory mixed methods study that proposes definitions for workarounds and describes the variable relationships with turbulence and patient safety in critical care.

Evaluating ChatGPT's Performance in the EU*US eHealth Work Foundational Curriculum Using the HITCOMP Self-Assessment Quiz.

This study investigated the performance of OpenAI's Chat Generative Pre-trained Transformer (ChatGPT) in responding to the EU*US eHealth Work Foundational Curriculum. This curriculum, a collaborative effort between European and U.S. institutions, provides an extensive framework for eHealth learning. The assessment involved 321 questions from the online Health Information Technology Competencies (HITCOMP) self-assessment quiz. Using GPT-3.5 model, the study presented each question three times to assess ChatGPT's consistency. Findings revealed an accuracy of 70.7%, indicating a reasonable grasp of eHealth topics, although performance was uneven across the 21 modules. These results underscore ChatGPT's potential in health information technology education and highlight the need for further model enhancements to fully encompass eHealth competencies.

Technology-Related Safety Event Analysis in Community Clinical Informatics: A Case Study.

This case study presents a process that was iteratively developed for clinical informaticians to identify, analyse, and respond to safety events related to health information technologies (HIT) in community care settings (This research was supported by the CIHR Health Systems Impact Fellowship Program. We would also like to thank Vancouver Coastal Health for their valuable contributions.). The goal was to build capacity within a clinical informatics team to integrate patient safety into their work and to help them recognize and respond to HIT-related safety events. The technology-related safety event analysis process that was ultimately developed included three key components: 1) an internal workflow to analyse voluntarily reported HIT-related safety events using a sociotechnical model, 2) safety huddles to amplify learnings from reviewed events, and 3) a cumulative analysis of all events over time to identify and respond to patterns. A systematic approach to quickly identify and understand HIT safety concerns enables informatics teams to proactively reduce risks and prevent harm.

Enhancing MAUDE Database Utility by GPT-4 and Cause-Effect Visualization.

The MAUDE database is a valuable public resource for understanding malfunctions and adverse events related to medical devices and health IT. However, its extensive data and complex structure pose challenges. To overcome this, we have developed an automated analytical pipeline using GPT-4, a cutting-edge large language model. This pipeline is intended to efficiently extract, categorize, and visualize safety events with minimal human annotation. In our analysis of 4,459 colonoscopy reports from MAUDE (2011-2021), the events were categorized into operational, human factor, and device-related. Ishikawa diagrams visualized a subset stored in a vector database for easy retrieval and comparison through a similarity search. This innovative approach streamlines access to vital safety insights, reducing the workload on human annotators, and holds promise to enhance the utility of the MAUDE database.

Applying Socio-Technical Models to Alarm Management: Tailoring Bed Exit Alerts in Medical-Surgical Units.

Integration of smartphone technology with the patient call-bell system provides the opportunity to enhance patient safety by supporting nurses' ability to communicate and prioritize care delivery directly. However, challenges are associated with achieving a balance between alarm support and alarm fatigue, including distracting nurses from patient care or desensitizing the nurse to other alarms and calls [1]. Our hospitals have quantitative and anecdotal reports of seriously high volumes of wireless alerts on the nurses' smartphones. Nurses have complained that the phones are generating too much noise to consume or timely prioritize. Preliminary alarm inventory revealed the Bed Exit wireless alert as a leading contributor of signal volume across many units and hospitals. The lack of standard policies and workflow improvement processes has increased nuisance alarms, making these Health Information Technologies less useful and safe. Using system data, workflow observations, and nursing interviews, Singh and Sittig's HIT Safety framework [2] was applied to identify and prioritize sociotechnical factors and interventions that impact the end-to-end Bed Exit alarm workflow. This study reviews the application of sociotechnical models and frameworks to reduce wireless calls without introducing risk and impacting patient care.

A Nursing Clinical Care Services Platform to Support Leadership Decision Making.

Like most organizations, The Children's Hospital of Philadelphia (CHOP) generates a lot of data of varying types, from clinical to staffing and operations. However, these datasets are separated, preventing effective analytics. To improve workforce management and care delivery, CHOP's Nursing department collaborated with the Data & Analytics team to create a dashboard-based platform for analyzing workforce metrics and patient outcomes, aiding nursing leaders in decision-making. This project involved multiple phases with contributions from Nursing, Data & Analytics, CHOP's Data Trust Office, and Human Resources. Key performance indicators were identified, and a variety of data sources were aggregated to provide a comprehensive view of the nursing enterprise. The resulting platform offers automated, current, and reliable analytics on various aspects, including nursing demographics, education, survey results, staffing actuals by job group, and patient and family experience data. The platform's usability was assessed using a modified Health Information Technology Usability Evaluation Scale survey, with a 29% response rate primarily from senior directors and managers. The findings showed high usability and satisfaction, indicating the dashboard is a valuable decision-support tool. Lessons learned include the need for analytics education for nurses and mid-managers, the inclusion of critical nursing-specific metrics (and development of the data pipelines making them possible), and the integration of multidisciplinary team metrics for comprehensive nursing analytics.

The Role of Health Information Technology During Hospital to Home Transitions.

The use of healthcare information technology (HIT) is vital for storing and exchanging health information during patient transitions, playing a significant role in care coordination for sepsis survivors. The critical role of HIT was evident during the pre-implementation phase of a study to implement an evidence-based protocol supporting the timely transition of sepsis survivors to home health and outpatient care. Through 61 semi-structured interviews involving 91 stakeholders, over half of the 33 identified themes were related to HIT. Notably, electronic health record (EHR) alert systems led to over-capture and alarm fatigue. Efficient information transfer during HHC referral highlighted the need for improved EHR access. The study underscores HIT's importance and potential while emphasizing the need for collaborative policy and interface development to promote effective transitions in care.

Artificial Intelligence in Nursing: Perspectives from Norwegian Nurses.

Nurses continue to face challenges in leading health information technology innovations such as Artificial Intelligence (AI). There is an acknowledged need to explore the attitude of nurses towards AI and nurses' acceptance of AI in clinical settings. We sought to address this gap in knowledge about the perceptions of AI by nursing-related professionals in their work and as a content area in the education of nursing students. Norwegian nurses and healthcare personnel interested in the topic met in a seminar in Oslo in 2023 to explore their perspectives on AI. Following a lecture on AI, audience members offered their insights in a recorded discussion. Data analysis consisted of inductive coding of concepts in the transcribed recording. Three major themes emerged: Expectations, Identified needs and related recommendations; and Policy to guard safety; as well as recommendations new to the literature.

Current Practices and Attitudes of Community Health Centers Toward the Use of Algorithmic Logic to Identify Patients with Undiagnosed Hypertension.

Treating patients with uncontrolled hypertension is a powerful intervention for reducing the risk of heart attack and stroke. Leveraging health information technology to identify patients with undiagnosed hypertension using algorithmic logic can be an effective approach for reaching hypertensive patients who may otherwise be overlooked. Despite evidence that this strategy can support favorable cardiovascular health outcomes in the safety-net healthcare setting, little is known about its implementation outside of targeted practice and research environments. In 2021-2022, Community Clinic Association of Los Angeles County and the Los Angeles County Department of Public Health collaborated on a mixed methods, organizational assessment of community health centers to better understand their practices and attitudes toward the use of algorithmic logic to identify patients with undiagnosed hypertension. Results from the assessment suggest that awareness and use of this approach are limited; numerous challenges are associated with its adoption and implementation.

Implementing Self-Measured Blood Pressure Monitoring With Clinical Support: A Qualitative Study of Federally Qualified Health Centers.

Self-measured blood pressure monitoring (SMBP) with clinical support is effective at reducing blood pressure for people with hypertension. Although strengths and challenges around SMBP are well-documented, few studies describe the complexities of real-world implementation of SMBP with clinical support in the Federally Qualified Health Center (FQHC) setting. Between 2019 and 2023, the Ohio Department of Health funded the Ohio Association of Community Health Centers to manage a multiyear quality improvement (QI) project with 21 FQHCs. The project aimed to improve the identification and management of patients with hypertension, diabetes, and prediabetes. This study focuses on the activities implemented to provide SMBP support to patients with hypertension. FQHCs implemented clinical SMBP support using multiple roles, approaches, and resources. FQHCs established a process to identify patients eligible for SMBP support, provide blood pressure monitors, train patients on SMBP, track blood pressure readings, follow up with patients, and connect patients to resources. External evaluators interviewed 13 staff members within seven FQHCs from the QI project. Interviewed FQHCs were located across Ohio and represented urban, rural, suburban, and Appalachian areas. Clinical activities to support SMBP, facilitators, and barriers were identified with thematic analysis. The National Association of Community Health Centers SMBP Implementation Toolkit was used as a framework to assess SMBP activities. Facilitators included team-based care, health information technology capacity, funding for blood pressure monitors and staff time, leadership and staff support, and external support. Barriers included technology challenges, staffing shortages, low patient engagement, sustainability, and the COVID-19 pandemic. This study demonstrates how FQHCs can use a variety of staff, processes, and resources to implement clinical SMBP support across a range of geographic regions. To facilitate this, FQHCs and patients may need more comprehensive insurance coverage of blood pressure monitors, reimbursement for staff time, and technology support.

The challenges of and solutions for combining cocreation and agile in the development of health information technologies

BackgroundInvolving users has become a prominent principle in the development of Health Information Technologies (HIT) and has led to an uprise in agile and cocreation methods. Previous literature shows how the two can be combined in one method, but also suggest that using such a method may come with challenges, for which the solutions are unclear. PurposeTo identify the challenges of using a method that combines agile and cocreation, provide solutions for these challenges, and evaluate its usage. Methods and materialsThe setting for this research was the Agile Cocreation of Robots for Aging (ACCRA) project. The research consisted of three phases: 1) evaluating the Agile Cocreation method to identify challenges in its usage, by analysing documents from the project (e-mails, meeting notes), 2) solving the challenges to improve the method, by designing solutions in a cocreation session; and 3) evaluating the usage of the improved version via a survey among engineers and user researchers involved in the project. ResultsWe identified three main challenges and developed three solutions, which were used in the next phase of the project. First, to engage all stakeholders in cocreation, we implemented more fun and playful materials. Second, to bridge the differences between engineers and user researchers we invested in face-to-face meetings. Third, to manage knowledge in the project we intensified our meeting schedule to weekly meetings. In the quantitative evaluation of the improved cocreation method, the engineers and user researchers were positive about the agile cocreation method and about our improvements. ConclusionWhen developing HIT, a method that combines agile and cocreation is useful because it helps to identify user needs and to translate these needs into technology. To identify the needs of these users and other stakeholders it is important to involve them as active partners in cocreation using fun and playful materials. Engineers and user researchers should bridge their differences and meet face-to-face as much as possible.

The application of health information technology for the elderly care in the emergency department: a conceptual model

IntroductionIn the emergency departments (EDs), usually the longest waiting time for treatment and discharge belongs to the elderly patients. Moreover, the number of the ED admissions for the elderly increases every year. It seems that the use of health information technology in geriatric emergency departments can help to reduce the burden of the healthcare services for this group of patients. This research aimed to develop a conceptual model for using health information technology in the geriatric emergency department.MethodsThis study was conducted in 2021. The initial conceptual model was designed based on the findings derived from the previous research phases (literature review and interview with the experts). Then, the model was examined by an expert panel (n = 7). Finally, using the Delphi technique (two rounds), the components of the conceptual model were reviewed and finalized. To collect data, a questionnaire was used, and data were analyzed using descriptive statistics.ResultsThe common information technologies appropriate for the elderly care in the emergency departments included emergency department information system, clinical decision support system, electronic health records, telemedicine, personal health records, electronic questionnaires for screening, and other technologies such as picture archiving and communication systems (PACS), electronic vital sign monitoring systems, etc. The participants approved all of the proposed systems and their applications in the geriatric emergency departments.ConclusionThe proposed model can help to design and implement the most useful information systems in the geriatric emergency departments. As the application of technology accelerates care processes, investing in this field would help to support the care plans for the elderly and improve quality of care services. Further research is recommended to investigate the efficiency and effectiveness of using these technologies in the EDs.

Patient-Engagement Health Information Technology and Quality Process Outcomes in Federally Qualified Health Centers.

Health information technology (HIT) for patient-engagement can positively influence the quality and efficiency of health care delivery. Although this topic is of significant importance, it has not been fully addressed in the federally qualified health center (FQHC) context. This research investigates the relationship between the level of patient-engagement HIT and FQHC preventive health care quality outcomes. Based on the Uniform Data System (UDS), this study employed multivariable regression analysis to investigate the association between the level of patient-engagement HIT and FQHC preventive health care quality outcomes. FQHCs were placed in 4 mutually exclusive groups based on the level of FQHC use of patient-engagement HIT. The results indicate that compared with the most comprehensive patient-engagement HIT at FQHCs, less comprehensive patient-engagement HIT was associated with lower rates of preventive care provision. Comprehensive patient-engagement HIT across FQHCs may improve preventive health care quality outcomes. The results support policy incentives for FQHCs with less comprehensive levels of patient-engagement HIT to foster improved preventive care for their patients.

Plugging Public Health Data into the Health IT Ecosystem to Protect National Health

The Covid-19 pandemic exposed many challenges in the United States’ public health systems, and in particular the antiquated data ecosystem that hinders the nation’s ability to use timely data to detect and respond to emerging public health threats. One key challenge of the public health data ecosystem is the limited use of electronic, standardized, and interoperable ways for data to be readily shared between health care delivery and public health systems. At the start of the Covid-19 pandemic, most data exchange between health care and public health, and across public health, was manual, relying on faxes, labor-intensive data entry, and other outdated technology. Although significant progress has been made over the last several years to introduce more standardization and connectivity between public health and health care IT systems, more work is needed. This commentary describes the benefits and potential of robust, modern interoperability between health care and public health systems, defines key policies and technology activities that will drive toward a future state of a highly connected public health and health care data ecosystem, and summarizes potential challenges that must be overcome.

Data Lake, Data Warehouse, Datamart, and Feature Store: Their Contributions to the Complete Data Reuse Pipeline.

The growing adoption and use of health information technology has generated a wealth of clinical data in electronic format, offering opportunities for data reuse beyond direct patient care. However, as data are distributed across multiple software, it becomes challenging to cross-reference information between sources due to differences in formats, vocabularies, and technologies and the absence of common identifiers among software. To address these challenges, hospitals have adopted data warehouses to consolidate and standardize these data for research. Additionally, as a complement or alternative, data lakes store both source data and metadata in a detailed and unprocessed format, empowering exploration, manipulation, and adaptation of the data to meet specific analytical needs. Subsequently, datamarts are used to further refine data into usable information tailored to specific research questions. However, for efficient analysis, a feature store is essential to pivot and denormalize the data, simplifying queries. In conclusion, while data warehouses are crucial, data lakes, datamarts, and feature stores play essential and complementary roles in facilitating data reuse for research and analysis in health care.