Transforming Hypertension Diagnosis and Management in The Era of Artificial Intelligence: A 2023 National Heart, Lung, and Blood Institute (NHLBI) Workshop Report.

Hypertension is among the most important risk factors for cardiovascular disease, chronic kidney disease, and dementia. The artificial intelligence (AI) field is advancing quickly, and there has been little discussion on how AI could be leveraged for improving the diagnosis and management of hypertension. AI technologies, including machine learning tools, could alter the way we diagnose and manage hypertension, with potential impacts for improving individual and population health. The development of successful AI tools in public health and health care systems requires diverse types of expertise with collaborative relationships between clinicians, engineers, and data scientists. Unbiased data sources, management, and analyses remain a foundational challenge. From a diagnostic standpoint, machine learning tools may improve the measurement of blood pressure and be useful in the prediction of incident hypertension. To advance the management of hypertension, machine learning tools may be useful to find personalized treatments for patients using analytics to predict response to antihypertension medications and the risk for hypertension-related complications. However, there are real-world implementation challenges to using AI tools in hypertension. Herein, we summarize key findings from a diverse group of stakeholders who participated in a workshop held by the National Heart, Lung, and Blood Institute in March 2023. Workshop participants presented information on communication gaps between clinical medicine, data science, and engineering in health care; novel approaches to estimating BP, hypertension risk, and BP control; and real-world implementation challenges and issues.

Erratum: Sociome Data Commons: A scalable and sustainable platform for investigating the full social context and determinants of health - ERRATUM.

[This corrects the article DOI: 10.1017/cts.2023.670.].

Student High Value Care Initiative: a Longitudinal Model for Student-Led Implementation and Scholarship.

BACKGROUND: Educating medical trainees to practice high value care is a critical component to improving quality of care and should be introduced at the beginning of medical education. AIM: To create a successful educational model that provides medical students and junior faculty with experiential learning in quality improvement and mentorship opportunities, and produce effective quality initiatives. SETTING: A tertiary medical center affiliated with a medical school in New York City. PARTICIPANTS: First year medical students, junior faculty in hospital medicine, and a senior faculty course director. PROGRAM DESCRIPTION: The Student High Value Care initiative is a longitudinal initiative comprised of six core elements: (1) project development, (2) value improvement curriculum, (3) mentorship, (4), Institutional support, (5) scholarship, and (6) student leadership. PROGRAM EVALUATION: During the first 3 years, 68 medical students and ten junior faculty participated in 10 quality improvement projects. Nine projects were successful in their measured outcomes, with statistically significant improvements. Nine had an abstract accepted to a regional or national meeting, and seven produced publications in peer-reviewed literature. DISCUSSION: In the first 3 years of the initiative, we successfully engaged medical students and junior faculty to create and support the implementation of successful quality improvement initiatives. Since that time, the program continues to offer meaningful mentorship and scholarship opportunities.

Use of clinical pathways integrated into the electronic health record to address the coronavirus disease 2019 (COVID-19) pandemic.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has required healthcare systems to meet new demands for rapid information dissemination, resource allocation, and data reporting. To help address these challenges, our institution leveraged electronic health record (EHR)-integrated clinical pathways (E-ICPs), which are easily understood care algorithms accessible at the point of care. OBJECTIVE: To describe our institution's creation of E-ICPs to address the COVID-19 pandemic, and to assess the use and impact of these tools. SETTING: Urban academic medical center with adult and pediatric hospitals, emergency departments, and ambulatory practices. METHODS: Using the E-ICP processes and infrastructure established at our institution as a foundation, we developed a suite of COVID-19-specific E-ICPs along with a process for frequent reassessment and updating. We examined the development and use of our COVID-19-specific pathways for a 6-month period (March 1-September 1, 2020), and we have described their impact using case studies. RESULTS: In total, 45 COVID-19-specific pathways were developed, pertaining to triage, diagnosis, and management of COVID-19 in diverse patient settings. Orders available in E-ICPs included those for isolation precautions, testing, treatments, admissions, and transfers. Pathways were accessed 86,400 times, with 99,081 individual orders were placed. Case studies demonstrate the impact of COVID-19 E-ICPs on stewardship of resources, testing optimization, and data reporting. CONCLUSIONS: E-ICPs provide a flexible and unified mechanism to meet the evolving demands of the COVID-19 pandemic, and they continue to be a critical tool leveraged by clinicians and hospital administrators alike for the management of COVID-19. Lessons learned may be generalizable to other urgent and nonurgent clinical conditions.

Sociome Data Commons: A scalable and sustainable platform for investigating the full social context and determinants of health.

Background/Objective: Non-clinical aspects of life, such as social, environmental, behavioral, psychological, and economic factors, what we call the sociome, play significant roles in shaping patient health and health outcomes. This paper introduces the Sociome Data Commons (SDC), a new research platform that enables large-scale data analysis for investigating such factors. Methods: This platform focuses on "hyper-local" data, i.e., at the neighborhood or point level, a geospatial scale of data not adequately considered in existing tools and projects. We enumerate key insights gained regarding data quality standards, data governance, and organizational structure for long-term project sustainability. A pilot use case investigating sociome factors associated with asthma exacerbations in children residing on the South Side of Chicago used machine learning and six SDC datasets. Results: The pilot use case reveals one dominant spatial cluster for asthma exacerbations and important roles of housing conditions and cost, proximity to Superfund pollution sites, urban flooding, violent crime, lack of insurance, and a poverty index. Conclusion: The SDC has been purposefully designed to support and encourage extension of the platform into new data sets as well as the continued development, refinement, and adoption of standards for dataset quality, dataset inclusion, metadata annotation, and data access/governance. The asthma pilot has served as the first driver use case and demonstrates promise for future investigation into the sociome and clinical outcomes. Additional projects will be selected, in part for their ability to exercise and grow the capacity of the SDC to meet its ambitious goals.

Framework for Integrating Equity Into Machine Learning Models: A Case Study.

Predictive analytic models leveraging machine learning methods increasingly have become vital to health care organizations hoping to improve clinical outcomes and the efficiency of care delivery for all patients. Unfortunately, predictive models could harm populations that have experienced interpersonal, institutional, and structural biases. Models learn from historically collected data that could be biased. In addition, bias impacts a model's development, application, and interpretation. We present a strategy to evaluate for and mitigate biases in machine learning models that potentially could create harm. We recommend analyzing for disparities between less and more socially advantaged populations across model performance metrics (eg, accuracy, positive predictive value), patient outcomes, and resource allocation and then identify root causes of the disparities (eg, biased data, interpretation) and brainstorm solutions to address the disparities. This strategy follows the lifecycle of machine learning models in health care, namely, identifying the clinical problem, model design, data collection, model training, model validation, model deployment, and monitoring after deployment. To illustrate this approach, we use a hypothetical case of a health system developing and deploying a machine learning model to predict the risk of mortality in 6 months for patients admitted to the hospital to target a hospital's delivery of palliative care services to those with the highest mortality risk. The core ethical concepts of equity and transparency guide our proposed framework to help ensure the safe and effective use of predictive algorithms in health care to help everyone achieve their best possible health.

Artificial Intelligence for the Orthopaedic Surgeon: An Overview of Potential Benefits, Limitations, and Clinical Applications.

Artificial intelligence (AI), along with its subset technology machine learning, has transformed numerous industries through newfound efficiencies and supportive decision-making. These technologies have similarly begun to find application within United States healthcare, particularly orthopaedics. Although these modalities have the potential to similarly transform health care, there exist limitations that must also be recognized and understood. Unfortunately, most clinicians do not have an understanding of the fundamentals of AI and therefore may have challenges in contextualizing its impact in modern healthcare. The purpose of this review was to provide an overview of the key concepts of AI and machine learning with the orthopaedic surgeon in mind. The review further highlights the potential benefits and limitations of AI, along with an overview of its applications, in orthopaedics.

Usability and Learnability of RxUniverse, an Enterprise-Wide App Prescribing Platform Used in an Academic Tertiary Care Hospital.

The objective of this study was to assess the usability of RxUniverse, a novel platform that enables health care providers to directly disseminate proven, evidence-based mobile health apps to patients. Among five pilot clinical sites, 40 physicians and front-line providers were trained on the RxUniverse platform. They were educated on the platform's functionality and instructed how to prescribe apps to their patients. The well-validated System Usability Score (SUS) was used to assess the usability of the platform. The adoption goal was set as 100 prescriptions of relevant apps within an 8-week pilot period. Within the pilot period, over 2000 apps were prescribed. Nineteen responses were received from the System Usability Score survey, and the platform received a usability score of 84.2, which is in the 96th percentile across all systems. The pilot study outcomes demonstrate the high adoption and usability of the RxUniverse platform.

The Broken Health Information Technology Innovation Pipeline: A Perspective from the NODE Health Consortium.

BACKGROUND: The Network of Digital Evidence (NODE) was formed to further advance the field of health information technology (HIT) and evidence-based digital medicine at different healthcare institutions nationwide. As the NODE network reviewed the state of the field, it was noted that despite substantial financial and human capital investments, the processes and results of HIT innovation seem chaotic and subpar, especially in comparison to the more well-established drug and device industries. During the course of this white paper, we will explore the causes for this observed phenomenon as well as propose possible solutions to improve the state of HIT. METHODS: We compared the entire process of discovery, proof of concept, Food and Drug Administration (FDA) review, and postmarket monitoring and distribution/implementation of HIT innovations to the equivalent processes for drugs and devices. Whereas drug and device innovations are subject to a standardized pipeline of production, HIT innovations are not held to equivalent standards. CONCLUSIONS: As a result, HIT lags behind the more mature drug and device industries in producing effective and reliable products. This leads to an inefficient use of already scarce healthcare resources. The authors believe that the HIT industry must adopt many of the mechanisms implemented by the drug and device industries as dictated by their innovation pipelines of discovery, proof of concept, FDA review, and postmarket monitoring and distribution/implementation. We propose an eight-point plan to fundamentally evolve the HIT lifecycle, including reforms for institutions such as neutral government agencies, new health system boards and management systems, modified incentive structures, improved relationships with financial investors and start-ups, patient engagement, and enhanced mechanisms to improve HIT adoption.