Building Capacity for Pragmatic Trials of Digital Technology in Primary Care.

Frontline primary care teams face important challenges in seeking to transform the quality of care delivered to patients and to reduce clerical burden for clinicians. Digital technologies using artificial intelligence hold substantial promise to aid in this transformation. Both pragmatic clinical trials and implementation science are key tools to successfully introduce, evaluate, and sustain innovations in real-world primary care practices. Previous articles in this thematic series have provided an in-depth overview of pragmatic trials and implementation science. This paper demonstrates and provides a framework for how these concepts, together with digital transformation, can be used to solve many of the challenges facing primary care. This framework is conceived as the collaboration of frontline primary care teams with innovators in academic institutions and industry through pragmatic trials and implementation science.

Clinician Adoption of an Artificial Intelligence Algorithm to Detect Left Ventricular Systolic Dysfunction in Primary Care.

OBJECTIVE: To compare the clinicians' characteristics of "high adopters" and "low adopters" of an artificial intelligence (AI)-enabled electrocardiogram (ECG) algorithm that alerted for possible low left ventricular ejection fraction (EF) and the subsequent effectiveness of detecting patients with low EF. METHODS: Clinicians in 48 practice sites of a US Midwest health system were cluster-randomized by the care team to usual care or to receive a notification that suggested ordering an echocardiogram in patients flagged as potentially having low EF based on an AI-ECG algorithm. Enrollment was between June 26, 2019, and July 30, 2019; participation concluded on March 31, 2020. This report is focused on those clinicians randomized to receive the notification of the AI-ECG algorithm. At the patient level, data were analyzed for the proportion of patients with positive AI-ECG results. Adoption was defined as the clinician order of an echocardiogram after prompted by the alert. RESULTS: A total of 165 clinicians and 11,573 patients were included in this analysis. Among patients with positive AI-ECG, high adopters (n=41) were twice as likely to diagnose patients with low EF (33.9%) vs low adopters, n=124, (16.9%); odds ratio, 1.62; 95% CI, 1.21 to 2.17). High adopters were more often advanced practice providers (eg, nurse practitioners and physician assistants) vs physicians, Family Medicine vs Internal Medicine specialty, and tended to have less complex patients. CONCLUSION: Clinicians who most frequently followed the recommendations of an AI tool were twice as likely to diagnose low EF. Those clinicians with less complex patients were more likely to be high adopters. TRIAL REGISTRATION: Clinicaltrials.gov Identifier: NCT04000087.

Sociotechnical Intervention for Improved Delivery of Preventive Cardiovascular Care to Rural Communities: Participatory Design Approach.

BACKGROUND: Clinical practice guidelines recommend antiplatelet and statin therapies as well as blood pressure control and tobacco cessation for secondary prevention in patients with established atherosclerotic cardiovascular diseases (ASCVDs). However, these strategies for risk modification are underused, especially in rural communities. Moreover, resources to support the delivery of preventive care to rural patients are fewer than those for their urban counterparts. Transformative interventions for the delivery of tailored preventive cardiovascular care to rural patients are needed. OBJECTIVE: A multidisciplinary team developed a rural-specific, team-based model of care intervention assisted by clinical decision support (CDS) technology using participatory design in a sociotechnical conceptual framework. The model of care intervention included redesigned workflows and a novel CDS technology for the coordination and delivery of guideline recommendations by primary care teams in a rural clinic. METHODS: The design of the model of care intervention comprised 3 phases: problem identification, experimentation, and testing. Input from team members (n=35) required 150 hours, including observations of clinical encounters, provider workshops, and interviews with patients and health care professionals. The intervention was prototyped, iteratively refined, and tested with user feedback. In a 3-month pilot trial, 369 patients with ASCVDs were randomized into the control or intervention arm. RESULTS: New workflows and a novel CDS tool were created to identify patients with ASCVDs who had gaps in preventive care and assign the right care team member for delivery of tailored recommendations. During the pilot, the intervention prototype was iteratively refined and tested. The pilot demonstrated feasibility for successful implementation of the sociotechnical intervention as the proportion of patients who had encounters with advanced practice providers (nurse practitioners and physician assistants), pharmacists, or tobacco cessation coaches for the delivery of guideline recommendations in the intervention arm was greater than that in the control arm. CONCLUSIONS: Participatory design and a sociotechnical conceptual framework enabled the development of a rural-specific, team-based model of care intervention assisted by CDS technology for the transformation of preventive health care delivery for ASCVDs.

Association of Patient and System-Level Factors With Social Determinants of Health Screening.

BACKGROUND: Health systems are increasingly recognizing the importance of collecting social determinants of health (SDoH) data. However, gaps remain in our understanding of facilitators or barriers to collection. To address these gaps, we evaluated a real-world implementation of a SDoH screening tool. METHODS: We conducted a retrospective analysis of the implementation of the SDoH screening tool at Mayo Clinic in 2019. The outcomes are: (1) completion of screening and (2) the modality used (MyChart: filled out on patient portal; WelcomeTablet: filled out by patient on a PC-tablet; EpicCare: data obtained directly by provider and entered in chart). We conducted logistic regression for completion and multinomial logistic regression for modality. The factors of interest included race and ethnicity, use of an interpreter, and whether the visit was for primary care. RESULTS: Overall, 58.7% (293,668/499,931) of screenings were completed. Patients using interpreters and racial/ethnic minorities were less likely to complete the screening. Primary care visits were associated with an increase in completion compared with specialty care visits. Patients who used an interpreter, racial and ethnic minorities, and primary care visits were all associated with greater WelcomeTablet and lower MyChart use. CONCLUSION: Patient and system-level factors were associated with completion and modality. The lower completion and greater WelcomeTablet use among patients who use interpreters and racial and ethnic minorities points to the need to improve screening in these groups and that the availability of the WelcomeTablet may have prevented greater differences. The higher completion in primary care visits may mean more outreach is needed for specialists.

Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial.

We have conducted a pragmatic clinical trial aimed to assess whether an electrocardiogram (ECG)-based, artificial intelligence (AI)-powered clinical decision support tool enables early diagnosis of low ejection fraction (EF), a condition that is underdiagnosed but treatable. In this trial ( NCT04000087 ), 120 primary care teams from 45 clinics or hospitals were cluster-randomized to either the intervention arm (access to AI results; 181 clinicians) or the control arm (usual care; 177 clinicians). ECGs were obtained as part of routine care from a total of 22,641 adults (N = 11,573 intervention; N = 11,068 control) without prior heart failure. The primary outcome was a new diagnosis of low EF (≤50%) within 90 days of the ECG. The trial met the prespecified primary endpoint, demonstrating that the intervention increased the diagnosis of low EF in the overall cohort (1.6% in the control arm versus 2.1% in the intervention arm, odds ratio (OR) 1.32 (1.01-1.61), P = 0.007) and among those who were identified as having a high likelihood of low EF (that is, positive AI-ECG, 6% of the overall cohort) (14.5% in the control arm versus 19.5% in the intervention arm, OR 1.43 (1.08-1.91), P = 0.01). In the overall cohort, echocardiogram utilization was similar between the two arms (18.2% control versus 19.2% intervention, P = 0.17); for patients with positive AI-ECGs, more echocardiograms were obtained in the intervention compared to the control arm (38.1% control versus 49.6% intervention, P < 0.001). These results indicate that use of an AI algorithm based on ECGs can enable the early diagnosis of low EF in patients in the setting of routine primary care.

Changes in social relationships during an initial "stay-at-home" phase of the COVID-19 pandemic: A longitudinal survey study in the U.S.

RATIONALE: Severe acute respiratory syndrome Coronavirus 2 (SARS CoV-2), the virus that causes COVID-19, and consequent social distancing directives have been observed to negatively impact social relationships but the impact of these changes on the quality of social relationships at a population level has not been explored. OBJECTIVE: To evaluate changes in social relationships in a U.S. population sample during a time of social distancing. METHODS: We deployed a matched, longitudinal survey design of the National Institutes of Health Adult Social Relationship Scales to assess the social aspects of emotional support, instrumental support, friendship, loneliness, perceived hostility, and perceived rejection from a time without social distancing (February 2018) to a time where social distancing directives were active (May 2020). Changes in social relationships were compared using paired t-tests, and generalized linear regression models were constructed to identify subpopulations experiencing differential changes in each subdomain of social relationships during social distancing. RESULTS: Within our sample population, individuals experienced an increased sense of emotional support, instrumental support, and loneliness, and decreased feelings of friendship and perceived hostility during a period of social distancing. Individuals with low self-rated health experienced a decreased sense of emotional support, and females experienced increased feelings of loneliness compared with males. CONCLUSIONS: Social distancing measurably impacts social relationships and may have a disproportionate impact on females and individuals with lower self-rated health. If novel emergent infectious diseases become more commonplace, social interventions may be needed to mitigate the potential adverse impact of social distancing on social relationships.

ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): Rationale and design of a pragmatic cluster randomized trial.

BACKGROUND: A deep learning algorithm to detect low ejection fraction (EF) using routine 12-lead electrocardiogram (ECG) has recently been developed and validated. The algorithm was incorporated into the electronic health record (EHR) to automatically screen for low EF, encouraging clinicians to obtain a confirmatory transthoracic echocardiogram (TTE) for previously undiagnosed patients, thereby facilitating early diagnosis and treatment. OBJECTIVES: To prospectively evaluate a novel artificial intelligence (AI) screening tool for detecting low EF in primary care practices. DESIGN: The EAGLE trial is a pragmatic two-arm cluster randomized trial (NCT04000087) that will randomize >100 clinical teams (i.e., clusters) to either intervention (access to the new AI screening tool) or control (usual care) at 48 primary care practices across Minnesota and Wisconsin. The trial is expected to involve approximately 400 clinicians and 20,000 patients. The primary endpoint is newly discovered EF ≤50%. Eligible patients will include adults who undergo ECG for any reason and have not been previously diagnosed with low EF. Data will be pulled from the EHR, and no contact will be made with patients. A positive deviance qualitative study and a post-implementation survey will be conducted among select clinicians to identify facilitators and barriers to using the new screening report. SUMMARY: This trial will examine the effectiveness of the AI-enabled ECG for detection of asymptomatic low EF in routine primary care practices and will be among the first to prospectively evaluate the value of AI in real-world practice. Its findings will inform future implementation strategies for the translation of other AI-enabled algorithms.

Clinical trial design data for electrocardiogram artificial intelligence-guided screening for low ejection fraction (EAGLE).

The article details the materials that will be used in a clinical trial - ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): Rationale and design of a pragmatic cluster randomized trial [1]. It includes a clinician-facing action recommendation report that will translate an artificial intelligence algorithm to routine practice and an alert when a positive screening result is found. This report was developed using a user-centered approach via an iterative process with input from multiple physician groups. Such data can be reused and adapted to translate other artificial intelligence algorithms. This article also includes data collection forms we developed for the clinical trial aiming to evaluate the artificial intelligence algorithm. Such materials can be adapted for other clinical trials.

OB Nest: Reimagining Low-Risk Prenatal Care.

Using a human-centered design method, our team sought to envision a new model of care for women experiencing low-risk pregnancy. This model, called OB Nest, aimed to demedicalize the experience of pregnancy by providing a supportive and empowering experience that fits within patients' daily lives. To explore this topic, we invited women to use self-monitoring tools, a text-based smartphone application to communicate with their care team, and moderated online communities to connect with other pregnant women. Through observations of tool use and patient- and care team-provided feedback, we found that self-measurement and access to a fetal heart monitor provided women with confidence and joy in the progress of their pregnancies while shifting their position to being an active participant in their care. The smartphone application gave women direct access to their care team, provided continuity, and removed hurdles in establishing communication. The online community platform was a space where women in the same obstetric clinic could share nonmedical questions and advice with one another. This created a sense of community, leveraged the knowledge of women, and provided a venue beyond the clinic visit for information exchange. These findings were integrated into the design of the Mayo Clinic OB Nest model. This model redistributes care based on the individual needs of patients by providing self-measurement tools and continuous flexible access to their care team. By enabling women to meaningfully participate in their care, there is potential for cost savings and improved patient satisfaction.