Pre-pandemic assessment: a decade of progress in electronic health record adoption among U.S. hospitals

Electronic health records tools for treating obesity among adult patients in primary care: A scoping review

Background

Electronic health record (EHR)-based tools, such as clinical decision support systems (CDSS), support practitioners to promote evidence-based care, which may include obesity treatment. Our objective was to identify obesity-focused CDSS for adult patients in primary care settings to describe their designs, associated primary care practitioner (PCP) training, and outcomes among PCPs and patients.

Methods

We conducted a scoping review to identify and map available evidence using a search strategy for citations in MEDLINE from February 2009 to June 2024. We extracted information from included studies that described EHR-based CDSS tools designed to support obesity care (e.g., clinical decision support, counseling) for adult patients in primary care settings. We mapped common tool features to support weight management and synthesized key lessons learned during implementation of these tools.

Results

Of the 445 citations identified in our search, we included 13 citations reporting on 8 studies. The most common features across EHR-based CDSS tools were 1) identifying overweight or obesity using BMI (88 %) and 2) suggesting treatment strategies (88 %), particularly lifestyle modifications. Most studies provided limited information on the training PCPs received. Few PCPs used the CDSS with eligible patients (<20 %), describing these tools as cumbersome and lacking clinical workflow integration. Novel approaches included using CDSS during weight management-dedicated visits or for referral to obesity medicine physicians, which both showed promising early results of patients achieving weight reduction.

Conclusion

There is a growing body of evidence for obesity-focused CDSS among adult patients in the primary care setting. Our review identified three key lessons that may inform future health system implementation: 1) EHR-based CDSS tools need to be easy to use and integrate with clinical workflows; 2) PCPs need training on these tools for obesity treatment; and 3) Primary care workflow or work-scope may need to be modified to address obesity.

Lower electronic health record adoption and interoperability in rural versus urban physician participants: a cross-sectional analysis from the CMS quality payment program

BACKGROUND

The Health Information Technology for Economic and Clinical Health Act of 2009 introduced the Meaningful Use program to incentivize the adoption of electronic health records (EHRs) in the U.S. This study investigates the disparities in EHR adoption and interoperability between rural and urban physicians in the context of federal programs like the Medicare Access and CHIP Reauthorization Act of 2015 and the 21st Century Cures Act.

METHODS

A cross-sectional analysis was conducted using the 2021 Quality Payment Program Experience Report Public Use File to compare EHR adoption and Promoting Interoperability scores (PISs) between urban and rural physician participants. Data were linked with the Certified Health IT Product List to assess certified EHR adoption and interoperability.

RESULTS

The study included 209,152 physician participants, 12% of whom practiced in rural communities. EHR adoption was significantly higher in urban (74%) than in rural areas (64%). Epic Systems dominated the market in both settings. Multivariable logistic regression indicated lower odds of EHR adoption among rural physicians (OR: 0.79, CI: 0.76-0.82). Rural physicians also had lower PISs (β: -3.5, CI: -4.1 to -3.0). Factors like extreme hardship, small practitioner status, and location in a health professional shortage area significantly impacted EHR adoption and PISs.

CONCLUSIONS

Significant disparities exist in EHR adoption and interoperability between rural and urban physicians. These disparities highlight the need for targeted interventions to enhance EHR adoption and interoperability in rural settings to ensure equitable access to healthcare technologies and improved patient outcomes across all communities.

Success Factors of Growth-Stage Digital Health Companies: Systematic Literature Review

BACKGROUND

Over the past decade, digital health technologies (DHTs) have grown rapidly, driven by innovations such as electronic health records and accelerated by the COVID-19 pandemic. Increased funding and regulatory support have further pushed the sector's expansion. Despite early success, many DHT companies struggle to scale, with notable examples like Pear Therapeutics and Proteus Digital Health, which both declared bankruptcy after initial breakthroughs. These cases highlight the challenges of sustaining growth in a highly regulated health care environment. While there is research on success factors across industries, a gap remains in understanding the specific challenges faced by growth-stage DHT companies.

OBJECTIVE

This study aims to identify and discuss key factors that make growth-stage DHT companies successful. Specifically, we address three questions: (1) What are the success factors of growth-stage digital companies in general and (2) digital health companies in particular? (3) How do these success factors vary across DHTs?

METHODS

Following established PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, a systematic literature review was conducted to answer the questions. A comprehensive literature search was conducted using management and medical literature databases: EBSCO, ProQuest, PubMed, Scopus, and Web of Science. The review spanned scientific articles published from 2000 to 2023, using a rigorous screening process and quality assessment using the Critical Appraisal Skills Programme (CASP) checklist.

RESULTS

From the 2972 studies initially screened, 36 were selected, revealing 52 success factors. We categorized them into internal factor categories (Product and Services, Operations, Business Models, and Team Composition) and external factor categories (Customers, Health Care System, Government and Regulators, Investors and Shareholders, Suppliers and Partners, and Competitors). Of the 52 factors, 19 were specific to DHT companies. The most frequently cited internal success factors included financial viability (n=18) and market demand and relevance of the product and service (n=13). External success factors emphasized the regulatory environment and policy framework (n=15). Key differences were observed between DHTs and broader digital companies in areas such as data security (P=.03), system interoperability (P=.01), and regulatory alignment (P=.02), with DHTs showing a higher frequency of these factors. In addition, success factors varied across different DHT categories. Health System Operational Software companies emphasized affordability and system integration, while Digital Therapeutics prioritized factors related to government regulations and regulatory approval.

CONCLUSIONS

Essential characteristics contributing to the success of growth-stage digital health companies have been identified. This work, therefore, fills a knowledge gap and provides relevant stakeholders, including investors and entrepreneurs, with a valuable resource that can support informed decision-making in investment decisions and, in turn, enhance the success of fast-growing digital health companies. In addition, it provides the research community with a direction for future studies, enhancing the understanding, implementation, and growth of DHTs.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1101/2024.05.06.24306674.

Artificial intelligence: a primer for pediatric radiologists

Artificial intelligence (AI) is increasingly recognized for its transformative potential in radiology; yet, its application in pediatric radiology is relatively limited when compared to the whole of radiology. This manuscript introduces pediatric radiologists to essential AI concepts, including topics such as use case, data science, machine learning, deep learning, natural language processing, and generative AI as well as basics of AI training and validating. We outline the unique challenges of applying AI in pediatric imaging, such as data scarcity and distinct clinical characteristics, and discuss the current uses of AI in pediatric radiology, including both image interpretive and non-interpretive tasks. With this overview, we aim to equip pediatric radiologists with the foundational knowledge needed to engage with AI tools and inspire further exploration and innovation in the field.

AI-readiness for Biomedical Data: Bridge2AI Recommendations

Biomedical research and clinical practice are in the midst of a transition toward significantly increased use of artificial intelligence (AI) and machine learning (ML) methods. These advances promise to enable qualitatively deeper insight into complex challenges formerly beyond the reach of analytic methods and human intuition while placing increased demands on ethical and explainable artificial intelligence (XAI), given the opaque nature of many deep learning methods. The U.S. National Institutes of Health (NIH) has initiated a significant research and development program, Bridge2AI, aimed at producing new "flagship" datasets designed to support AI/ML analysis of complex biomedical challenges, elucidate best practices, develop tools and standards in AI/ML data science, and disseminate these datasets, tools, and methods broadly to the biomedical community. An essential set of concepts to be developed and disseminated in this program along with the data and tools produced are criteria for AI-readiness of data, including critical considerations for XAI and ethical, legal, and social implications (ELSI) of AI technologies. NIH Bridge to Artificial Intelligence (Bridge2AI) Standards Working Group members prepared this article to present methods for assessing the AI-readiness of biomedical data and the data standards perspectives and criteria we have developed throughout this program. While the field is rapidly evolving, these criteria are foundational for scientific rigor and the ethical design and application of biomedical AI methods.

Unveiling the Adoption and Barriers of Telemedicine in US Hospitals: A Comprehensive Analysis (2017-2022)

BACKGROUND

Telemedicine has emerged as a vital healthcare delivery model, especially pronounced during the COVID-19 pandemic. Our study uniquely focuses on an institutional lens, examining US hospitals to offer targeted policy implications.

OBJECTIVE

To investigate the trend in telemedicine adoption across US hospitals from 2017 to 2022 and analyze the institutional challenges they encounter, particularly in the realm of electronic health information exchange.

DESIGN

Cross-sectional study leveraging data from the American Hospital Association's (AHA) annual surveys for the years 2017 to 2021 and the 2022 AHA IT Supplement Survey.

SETTING

The study includes a national sample of US hospitals, covering a diverse range of hospital types including large, nonprofit, teaching, and system-affiliated institutions.

PARTICIPANTS

US hospitals form the study's participants, with a substantial response rate to the surveys.

MAIN MEASURES

Key metrics include the number of telemedicine patient encounters, percentage of hospitals offering telemedicine services, and institutional challenges to electronic health information exchange.

KEY RESULTS

Telemedicine encounters saw a 75% increase, growing from approximately 111.4 million in 2020 to nearly 194.4 million in 2021. The percentage of hospitals offering at least one form of telemedicine service went from 46% in 2017 to 72% in 2021. Larger, nonprofit, and teaching hospitals were more prone to telehealth adoption, without notable urban-rural disparities. While over 90% of hospitals allow patients to view and download medical records, only 41% permit online data submission. Importantly, 25% of hospitals identified Certified Health IT Developers such as EHR vendor as frequent culprits in information blocking, with cost being the primary obstacle.

CONCLUSIONS

The findings underscore the rapid yet uneven adoption of telemedicine services in U.S. hospitals. The results point to the need for comprehensive policy interventions to address the challenges identified and realize telemedicine's full potential in healthcare delivery and resilience.

New Horizons for Consumer-Mediated Health Information Exchange

OBJECTIVES

In this paper, we discuss current trends in consumer-mediated health information exchange (HIE) within the U.S. and globally, including new approaches, relevant standards that support HIE and interoperability centered around the patient, remaining challenges, and potential future directions.

METHODS

We conducted a narrative review of the peer-reviewed and gray literature to characterize the current HIE landscape in relation to patient-centered data. Our searches targeted literature in three key areas related to consumer-mediated HIE: policy and initiatives, standards, and the technology landscape.

RESULTS

We discuss current trends in consumer-mediated exchange within the U.S. and globally, focusing on policies, standards, and technology that support information exchange centered around the patient. We also outline remaining challenges and potential future directions.

CONCLUSIONS

The current landscape in the U.S. and globally supports a more patient-centered care model. Ongoing advances in technology and data standards provide the technical infrastructure to empower consumers to electronically exchange their information with different stakeholders in ways not possible just a few years ago. These advancements hold great promise for patients to play a more central role in sharing their information in support of more patient-centered care. Additional research and analyzes along with public policies are needed.

Using the Electronic Health Record to Develop a Gastric Cancer Risk Prediction Model

Background and Aims

Gastric cancer (GC) is a leading cause of cancer incidence and mortality globally. Population screening is limited by the low incidence and prevalence of GC in the United States. A risk prediction algorithm to identify high-risk patients allows for targeted GC screening. We aimed to determine the feasibility and performance of a logistic regression model based on electronic health records to identify individuals at high risk for noncardia gastric cancer (NCGC).

Methods

We included 614 patients who had a diagnosis of NCGC between ages 40 and 80 years and who were seen at our large tertiary medical center in multiple states between 2010 and 2021. Controls without a diagnosis of NCGC were randomly selected in a 1:10 ratio of cases to controls. Multiple imputation by chained equations for missing data followed by logistic regression on imputed datasets was used to estimate the probability of NCGC. Area under the curve and the 0.632 estimator was used as the estimate for discrimination.

Results

The 0.632 estimator value was 0.731, indicating robust model performance. Probability of NCGC was higher with increasing age (odds ratio [OR] = 1.16, 95% confidence interval [CI]: 1.04-1.3), male sex (OR = 1.97; 95% CI: 1.64-2.36), Black (OR = 3.07; 95% CI: 2.46-3.83) or Asian race (OR = 4.39; 95% CI: 2.60-7.42), tobacco use (OR = 1.61; 95% CI: 1.34-1.94), anemia (OR = 1.35; 95% CI: 1.09-1.68), and pernicious anemia (OR = 6.12, 95% CI: 3.42-10.95).

Conclusion

We demonstrate the feasibility and good performance of an electronic health record-based logistic regression model for estimating the probability of NCGC. Future studies will refine and validate this model, ultimately identifying a high-risk cohort who could be eligible for NCGC screening.

Big data and electronic health records for glaucoma research

The digitization of health records through electronic health records (EHRs) has transformed the landscape of ophthalmic research, particularly in the study of glaucoma. EHRs offer a wealth of structured and unstructured data, allowing for comprehensive analyses of patient characteristics, treatment histories, and outcomes. This review comprehensively discusses different EHR data sources, their strengths, limitations, and applicability towards glaucoma research. Institutional EHR repositories provide detailed multimodal clinical data, enabling in-depth investigations into conditions such as glaucoma and facilitating the development of artificial intelligence applications. Multicenter initiatives such as the Sight Outcomes Research Collaborative and the Intelligent Research In Sight registry offer larger, more diverse datasets, enhancing the generalizability of findings and supporting large-scale studies on glaucoma epidemiology, treatment outcomes, and practice patterns. The All of Us Research Program, with a special emphasis on diversity and inclusivity, presents a unique opportunity for glaucoma research by including underrepresented populations and offering comprehensive health data even beyond the EHR. Challenges persist, such as data access restrictions and standardization issues, but may be addressed through continued collaborative efforts between researchers, institutions, and regulatory bodies. Standardized data formats and improved data linkage methods, especially for ophthalmic imaging and testing, would further enhance the utility of EHR datasets for ophthalmic research, ultimately advancing our understanding and treatment of glaucoma and other ocular diseases on a global scale.

A Compass for North Carolina Health Care Workers Navigating the Adoption of Artificial Intelligence

This article underscores the economic benefits of AI, the importance of collaborative innovation, and the need for workforce development to prepare health care professionals for an AI-enhanced future. We include guidance for strategic and ethical AI adoption while advocating for a unified approach to leveraging technology to improve patient outcomes.

MixEHR-SurG: A joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records

Survival models can help medical practitioners to evaluate the prognostic importance of clinical variables to patient outcomes such as mortality or hospital readmission and subsequently design personalized treatment regimes. Electronic Health Records (EHRs) hold the promise for large-scale survival analysis based on systematically recorded clinical features for each patient. However, existing survival models either do not scale to high dimensional and multi-modal EHR data or are difficult to interpret. In this study, we present a supervised topic model called MixEHR-SurG to simultaneously integrate heterogeneous EHR data and model survival hazard. Our contributions are three-folds: (1) integrating EHR topic inference with Cox proportional hazards likelihood; (2) integrating patient-specific topic hyperparameters using the PheCode concepts such that each topic can be identified with exactly one PheCode-associated phenotype; (3) multi-modal survival topic inference. This leads to a highly interpretable survival topic model that can infer PheCode-specific phenotype topics associated with patient mortality. We evaluated MixEHR-SurG using a simulated dataset and two real-world EHR datasets: the Quebec Congenital Heart Disease (CHD) data consisting of 8211 subjects with 75,187 outpatient claim records of 1767 unique ICD codes; the MIMIC-III consisting of 1458 subjects with multi-modal EHR records. Compared to the baselines, MixEHR-SurG achieved a superior dynamic AUROC for mortality prediction, with a mean AUROC score of 0.89 in the simulation dataset and a mean AUROC of 0.645 on the CHD dataset. Qualitatively, MixEHR-SurG associates severe cardiac conditions with high mortality risk among the CHD patients after the first heart failure hospitalization and critical brain injuries with increased mortality among the MIMIC-III patients after their ICU discharge. Together, the integration of the Cox proportional hazards model and EHR topic inference in MixEHR-SurG not only leads to competitive mortality prediction but also meaningful phenotype topics for in-depth survival analysis. The software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-SurG.

Knowledge, attitudes, and perceptions of healthcare students and professionals on the use of artificial intelligence in healthcare in Pakistan

The advent of artificial intelligence (AI) technologies has emerged as a promising solution to enhance healthcare efficiency and improve patient outcomes. The objective of this study is to analyse the knowledge, attitudes, and perceptions of healthcare professionals in Pakistan about AI in healthcare. We conducted a cross-sectional study using a questionnaire distributed via Google Forms. This was distributed to healthcare professionals (e.g., doctors, nurses, medical students, and allied healthcare workers) working or studying in Pakistan. Consent was taken from all participants before initiating the questionnaire. The questions were related to participant demographics, basic understanding of AI, AI in education and practice, AI applications in healthcare systems, AI's impact on healthcare professions and the socio-ethical consequences of the use of AI. We analyzed the data using Statistical Package for Social Sciences (SPSS) statistical software, version 26.0. Overall, 616 individuals responded to the survey while n = 610 (99.0%) of respondents consented to participate. The mean age of participants was 32.2 ± 12.5 years. Most of the participants (78.7%, n = 480) had never received any formal sessions or training in AI during their studies/employment. A majority of participants, 70.3% (n = 429), believed that AI would raise more ethical challenges in healthcare. In all, 66.4% (n = 405) of participants believed that AI should be taught at the undergraduate level. The survey suggests that there is insufficient training about AI in healthcare in Pakistan despite the interest of many in this area. Future work in developing a tailored curriculum regarding AI in healthcare will help bridge the gap between the interest in use of AI and training.

Challenges and dynamics of public health reporting and data exchange during COVID-19: insights from US hospitals

The US health care response during the early stages of the COVID-19 pandemic unveiled challenges in public health reporting systems and electronic clinical data exchange. Using data from the 2020 and 2022 American Hospital Association information technology supplement surveys, this study examined US hospitals' experiences in public health reporting, accessing clinical data from external providers for COVID-19 patient care, and their success in reporting vaccine-related adverse events to relevant state and federal agencies. Results showcase significant disparities in reporting practices across government levels due to inconsistent requirements. Although many hospitals leaned toward automated data transmission, a substantial portion continued to depend on manual processes. Pertaining to electronic clinical data, while entities like large commercial laboratories outperformed others, a considerable number were sluggish in delivering critical information. Moreover, a small percentage of hospitals reported challenges in recording vaccine-related adverse events, emphasizing the need for transparent reporting systems. The study underscores the necessity for standardized reporting protocols, explicit directives, and a pivot from manual to automated processes. Tackling these challenges is pivotal for ensuring prompt and reliable data, bolstering future public health responses, and rejuvenating public trust in health institutions.