Search

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

Background Recent evidence suggests the need to reframe healthcare delivery for patients with chronic conditions, with emphasis on minimizing healthcare footprint/workload on patients, caregivers, clinicians and health systems through the proposed Minimally Disruptive Medicine (MDM) care model named. HIV care models have evolved to further focus on understanding barriers and facilitators to care delivery while improving patient-centered outcomes (e.g., disease progression, adherence, access, quality of life). It is hypothesized that these models may provide an example of MDM care model in clinic practice. Therefore, this study aimed to observe and ascertain MDM-concordant and discordant elements that may exist within a tertiary-setting HIV clinic care model for patients living with HIV or AIDS (PLWHA). We also aimed to identify lessons learned from this setting to inform improving the feasibility and usefulness of MDM care model. Methods This qualitative case study occurred in multidisciplinary HIV comprehensive-care clinic within an urban tertiary-medical center. Participants included Adult PLWHA and informal caregivers (e.g. family/friends) attending the clinic for regular appointments were recruited. All clinic staff were eligible for recruitment. Measurements included; semi-guided interviews with patients, caregivers, or both; semi-guided interviews with varied clinicians (individually); and direct observations of clinical encounters (patient-clinicians), as well as staff daily operations in 2015–2017. The qualitative-data synthesis used iterative, mainly inductive thematic coding. Results Researcher interviews and observations data included 28 patients, 5 caregivers, and 14 care-team members. With few exceptions, the clinic care model elements aligned closely to the MDM model of care through supporting patient capacity/abilities (with some patients receiving minimal social support and limited assistance with reframing their biography) and minimizing workload/demands (with some patients challenged by the clinic hours of operation). Conclusions The studied HIV clinic incorporated many of the MDM tenants, contributing to its validation, and informing gaps in knowledge. While these findings may support the design and implementation of care that is both minimally disruptive and maximally supportive, the impact of MDM on patient-important outcomes and different care settings require further studying.

Background Guidelines promote shared decision‐making (SDM) for anticoagulation in patients with atrial fibrillation. We recently showed that adding a within‐encounter SDM tool to usual care (UC) increases patient involvement in decision‐making and clinician satisfaction, without affecting encounter length. We aimed to estimate the extent to which use of an SDM tool changed adherence to the decided care plan and clinical safety end points. Methods and Results We conducted a multicenter, encounter‐level, randomized trial assessing the efficacy of UC with versus without an SDM conversation tool for use during the clinical encounter (Anticoagulation Choice) in patients with nonvalvular atrial fibrillation considering starting or reviewing anticoagulation treatment. We conducted a chart and pharmacy review, blinded to randomization status, at 10 months after enrollment to assess primary adherence (proportion of patients who were prescribed an anticoagulant who filled their first prescription) and secondary adherence (estimated using the proportion of days for which treatment was supplied and filled for direct oral anticoagulant, and as time in therapeutic range for warfarin). We also noted any strokes, transient ischemic attacks, major bleeding, or deaths as safety end points. We enrolled 922 evaluable patient encounters (Anticoagulation Choice=463, and UC=459), of which 814 (88%) had pharmacy and clinical follow‐up. We found no differences between arms in either primary adherence (78% of patients in the SDM arm filled their first prescription versus 81% in UC arm) or secondary adherence to anticoagulation (percentage days covered of the direct oral anticoagulant was 74.1% in SDM versus 71.6% in UC; time in therapeutic range for warfarin was 66.6% in SDM versus 64.4% in UC). Safety outcomes, mostly bleeds, occurred in 13% of participants in the SDM arm and 14% in the UC arm. Conclusions In this large, randomized trial comparing UC with a tool to promote SDM against UC alone, we found no significant differences between arms in primary or secondary adherence to anticoagulation or in clinical safety outcomes. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: clinicaltrials.gov. Identifier: NCT02905032.

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.

Patient-centered care requires that treatments respond to the problematic situation of each patient in a manner that makes intellectual, emotional, and practical sense, an achievement that requires shared decision making (SDM). To implement SDM in practice, tools – sometimes called conversation aids or decision aids – are prepared by collating, curating, and presenting high quality, comprehensive, and up-to-date evidence. Yet, the literature offers limited guidance for how to make evidence support SDM. Here, we describe our approach and the challenges encountered during the development of Anticoagulation Choice, a conversation aid to help patients with atrial fibrillation and their clinicians jointly consider the risk of thromboembolic stroke and decide whether and how to respond to this risk with anticoagulation.

Key Points Question What factors contribute to cost conversations about anticoagulation treatment between patients with atrial fibrillation and their clinicians, and what outcomes are associated with these conversations? Findings In this cohort study of 830 audiovisual recordings of encounters and participant surveys from a randomized trial comparing atrial fibrillation care with and without a shared decision-making (SDM) tool, cost conversations were associated with the use of an SDM tool, with middle-income patients, and with consultations conducted by female primary care staff clinicians. Cost conversations were associated with patients’ decision-making processes but not final treatment choice. Meaning These findings suggest that SDM tools may inform efforts to promote cost conversations in practice, an important consideration when increasing costs of care are being passed on to patients., This cohort study, a secondary analysis of a randomized clinical trial, assesses factors contributing to cost conversations about care plans between clinicians and patients with atrial fibrillation., Importance How patients with atrial fibrillation (AF) and their clinicians consider cost in forming care plans remains unknown. Objective To identify factors that inform conversations regarding costs of anticoagulants for treatment of AF between patients and clinicians and outcomes associated with these conversations. Design, Setting, and Participants This cohort study of recorded encounters and participant surveys at 5 US medical centers (including academic, community, and safety-net centers) from the SDM4AFib randomized trial compared standard AF care with and without use of a shared decision-making (SDM) tool. Included patients were considering anticoagulation treatment and were recruited by their clinicians between January 30, 2017, and June 27, 2019. Data were analyzed between August and November 2019. Main Outcomes and Measures The incidence of and factors associated with cost conversations, and the association of cost conversations with patients’ consideration of treatment cost burden and their choice of anticoagulation. Results A total of 830 encounters (out of 922 enrolled participants) were recorded. Patients’ mean (SD) age was 71.0 (10.4) years; 511 patients (61.6%) were men, 704 (86.0%) were White, 303 (40.9%) earned between $40 000 and $99 999 in annual income, and 657 (79.2%) were receiving anticoagulants. Clinicians’ mean (SD) age was 44.8 (13.2) years; 75 clinicians (53.2%) were men, and 111 (76%) practiced as physicians, with approximately half (69 [48.9%]) specializing in either internal medicine or cardiology. Cost conversations occurred in 639 encounters (77.0%) and were more likely in the SDM arm (378 [90%] vs 261 [64%]; OR, 9.69; 95% CI, 5.77-16.29). In multivariable analysis, cost conversations were more likely to occur with female clinicians (66 [47%]; OR, 2.85; 95% CI, 1.21-6.71); consultants vs in-training clinicians (113 [75%]; OR, 4.0; 95% CI, 1.4-11.1); clinicians practicing family medicine (24 [16%]; OR, 12.12; 95% CI, 2.75-53.38]), internal medicine (35 [23%]; OR, 3.82; 95% CI, 1.25-11.70), or other clinicians (21 [14%]; OR, 4.90; 95% CI, 1.32-18.16) when compared with cardiologists; and for patients with an annual household income between $40 000 and $99 999 (249 [82.2%]; OR, 1.86; 95% CI, 1.05-3.29) compared with income below $40 000 or above $99 999. More patients who had cost conversations reported cost as a factor in their decision (244 [89.1%] vs 327 [69.0%]; OR 3.66; 95% CI, 2.43-5.50), but cost conversations were not associated with the choice of anticoagulation agent. Conclusions and Relevance Cost conversations were common, particularly for middle-income patients and with female and consultant-level primary care clinicians, as well as in encounters using an SDM tool; they were associated with patients’ consideration of treatment cost burden but not final treatment choice. With increasing costs of care passed on to patients, these findings can inform efforts to promote cost conversations in practice. Trial Registration ClinicalTrials.gov Identifier: NCT02905032

Background The primary prevention of cardiovascular (CV) events is often less intense in persons at higher CV risk and vice versa. Clinical practice guidelines recommend that clinicians and patients use shared decision making (SDM) to arrive at an effective and feasible prevention plan that is congruent with each person’s CV risk and informed preferences. However, SDM does not routinely happen in practice. This study aims to integrate into routine care an SDM decision tool (CV Prevention Choice) at three diverse healthcare systems in the USA and study strategies that foster its adoption and routine use. Methods This is a mixed method, hybrid type III stepped wedge cluster randomized study to estimate (a) the effectiveness of implementation strategies on SDM uptake and utilization and (b) the extent to which SDM results in prevention plans that are risk-congruent. Formative evaluation methods, including clinician and stakeholder interviews and surveys, will identify factors likely to impact feasibility, acceptability, and adoption of CV Prevention Choice as well as normalization of CV Prevention Choice in routine care. Implementation facilitation will be used to tailor implementation strategies to local needs, and implementation strategies will be systematically adjusted and tracked for assessment and refinement. Electronic health record data will be used to assess implementation and effectiveness outcomes, including CV Prevention Choice reach, adoption, implementation, maintenance, and effectiveness (measured as risk-concordant care plans). A sample of video-recorded clinical encounters and patient surveys will be used to assess fidelity. The study employs three theoretical approaches: a determinant framework that calls attention to categories of factors that may foster or inhibit implementation outcomes (the Consolidated Framework for Implementation Research), an implementation theory that guides explanation or understanding of causal influences on implementation outcomes (Normalization Process Theory), and an evaluation framework (RE-AIM). Discussion By the project’s end, we expect to have (a) identified the most effective implementation strategies to embed SDM in routine practice and (b) estimated the effectiveness of SDM to achieve feasible and risk-concordant CV prevention in primary care. Trial registration ClinicalTrials.gov, NCT04450914. Posted June 30, 2020 Trial status This study received ethics approval on April 17, 2020. The current trial protocol is version 2 (approved February 17, 2021). The first subject had not yet been enrolled at the time of submission.

Background Clinical trials are a fundamental tool to evaluate medical interventions but are time-consuming and resource-intensive. Objectives To build infrastructure for digital trials to improve efficiency and generalizability and test it using a study to validate an artificial intelligence algorithm to detect atrial fibrillation (AF). Design We will prospectively enroll 1,000 patients who underwent an electrocardiogram for any clinical reason in routine practice, do not have a previous diagnosis of AF or atrial flutter and would be eligible for anticoagulation if AF is detected. Eligible patients will be identified using digital phenotyping algorithms, including natural language processing that runs on the electronic health records. Study invitations will be sent in batches via patient portal or letter, which will direct patients to a website to verify eligibility, learn about the study (including video-based informed consent), and consent electronically. The method aims to enroll participants representative of the general patient population, rather than a convenience sample of patients presenting to clinic. A device will be mailed to patients to continuously monitor for up to 30 days. The primary outcome is AF diagnosis and burden; secondary outcomes include patients’ experience with the trial conduct methods and the monitoring device. The enrollment, intervention, and follow-up will be conducted remotely, ie, a patient-centered site-less trial. Summary This is among the first wave of trials to adopt digital technologies, artificial intelligence, and other pragmatic features to create efficiencies, which will pave the way for future trials in a broad range of disease and treatment areas. Clinicaltrials.gov: NCT04208971

Context Current evidence on determinants of adverse health outcomes in patients with adrenal insufficiency (AI) is scarce, especially in regards to AI subtypes. Objective To determine predictors of adverse outcomes in different subtypes of AI. Design and Setting Cross-sectional survey study at 2 tertiary centers. Participants A total of 696 patients with AI: primary AI (PAI, 42%), secondary AI (SAI, 32%), and glucocorticoid-induced AI (GIAI, 26%). Intervention Patient-centered questionnaire. Main Outcome Measures Patients’ knowledge, self-management of AI, self-perceived health, and adverse outcomes. Results The incidence rate of adrenal crisis was 24/100 patient-years with 44% experiencing at least 1 adrenal crisis since diagnosis (59% in PAI vs 31% in SAI vs 37% in GIAI, P < .0001). All patients described high degrees of discomfort with self-management and receiving prompt treatment. Patients with PAI were most likely to develop adrenal crises (adjusted OR 2.8, 95% CI 1.9-4.0) despite reporting better self-perceived health (adjusted OR 3.3, 95% CI 2.1-5.3), understanding of their diagnosis (89% vs 74-81% in other subtypes, P = .002), higher comfort with self-management (62% vs 52-61% in other sub types, P = .005), and higher likelihood to receive prompt treatment for adrenal crises in the emergency department (42% vs 19-30% in other subtypes, P < .0001). Conclusions Patients with AI reported high degrees of discomfort with self-management and treatment delays when presenting with adrenal crises. Despite better self-perceived health and understanding of diagnosis, patients with PAI experienced the highest frequency of adrenal crises. A multidimensional educational effort is needed for patients and providers to improve the outcomes of all subtypes of AI.

Background: Patients with primary adrenal insufficiency (PAI) and secondary adrenal insufficiency (SAI) report impaired quality of life. Predictors of adverse outcomes include duration of disease, supraphysiologic glucocorticoid (GC) use, and presence of other comorbidities. There is limited evidence to suggest that quality of life is disproportionately affected in one subtype of adrenal insufficiency. Objective: To identify determinants of quality of life in patients with PAI vs SAI. Method: Survey study of patients with the diagnosis of AI between 2015 and 2019 was evaluated at two large tertiary medical centers in the United States. Collected variables included data on circumstances of AI diagnosis, symptoms, management, burden of disease, and overall well-being. Patients with AI due to exogenous glucocorticoid use were excluded. Results: Patients with PAI (n=310, 65% women) were diagnosed at a younger age (37 ± 19 vs 48 ± 16 years, p 25 mg/day (33% vs 15%, p Conclusions: Patients with PAI receive higher daily GC and experience a higher number of adrenal crises when compared to patients with SAI. However, patients with PAI report a better general perception of health, possibly due to a more robust knowledge of their disease and higher comfort level managing AI. More effort is needed to ensure patients with AI are appropriately educated regarding their medical condition and therapy.

Background: Adrenal insufficiency (AI) is a chronic disorder necessitating life-long replacement. Patients’ quality of life and health outcomes depend on knowledge and comfort level with self-management. Objective: To determine patients’ knowledge in regards to diagnosis and management, estimate burden of disease and to identify predictors of adverse outcomes in patients with AI Methods: Survey study of patients with AI evaluated at two tertiary medical centers between 2015 and 2019. Collected variables included data on circumstances of AI diagnosis, symptoms, management, burden of disease, and overall well-being. Results: Among 785 patients (mean age at diagnosis 44.2 ± 18.0, 64% women, and 92% Caucasian), 310 (40%) had primary AI (PAI), 255 (33%) had secondary AI (SAI) not related to glucocorticoid use, and 211 (27%) had steroid-induced AI (SIAI). Patients were diagnosed with AI after presenting with symptoms for a median of 1 year (0-6), 28% with symptoms lasting >2 years, 44% visiting emergency room (ER) at least once prior to diagnosis. A third of patients reported a discordant diagnosis from their medical record. Baseline glucocorticoid replacement therapy included hydrocortisone (HC) in 447 (59%), median of 20 mg (IQR 15 - 25mg), prednisone in 190 (25%), median of 5 mg (IQR 4 - 7.5mg), other regimens in 38 (5%), and no steroids in the remainder (85, 11%); 197 (26%) patients reported daily equivalent HC dose of >25 mg. Overall, 549 (73%) of patients reported use of stress dose steroids at least once per year, higher in patients taking HC >25 mg/day (3.2 vs 2.7 times per year if HC25 mg /day reported a higher number of adrenal crises (1.6 vs 1.3 in patients on HC One third of patients described their general health as fair or poor. Predictors of negative perceptions of overall health included SIAI (OR 6.2 and 2.5, vs PAI and SAI respectively), poor understanding of diagnosis (OR 2.6), daily HC>25 mg (OR 2.1), and presence of at least one adrenal crisis (OR 2.3) (p Conclusion: Patients with AI experience delay in diagnosis, and a third do not fully understand their diagnosis. In addition to patient education, interventions to improve general health and outcomes may include selecting a physiological glucocorticoid replacement therapy, prevention of adrenal crisis, and improving ER care.

PurposeTo pilot test the impact of the ICAN Discussion Aid on clinical encounters.MethodsA pre–post study involving 11 clinicians and 100 patients was conducted at two primary care clinics within a single health system in the Midwest. The study examined clinicians’ perceptions about ICAN feasibility, patients’ and clinicians’ perceptions about encounter success, videographic differences in encounter topics, and medication adherence 6 months after an ICAN encounter.Results39/40 control encounters and 45/60 ICAN encounters yielded usable data. Clinicians reported ICAN use was feasible. In ICAN encounters, patients discussed diet, being active and taking medications more. Clinicians scored themselves poorer regarding visit success than their patients scored them; this effect was more pronounced in ICAN encounters. ICAN did not improve 6-month medication adherence or lengthen visits.ConclusionThis pilot study suggests that using ICAN in primary care is feasible, efficient and capable of modifying conversations. With lessons learned in this pilot, we are conducting a randomised trial of ICAN versus usual care in diverse clinical settings.Trial registration numberNCT02390570.

Background Reflecting (“stop‐and‐think”) before rating may help patients consider the quality of shared decision making (SDM) and mitigate ceiling/halo effects that limit the performance of self‐reported SDM measures. Methods We asked a diverse patient sample from the United States to reflect on their care before completing the 3‐item CollaboRATE SDM measure. Study 1 focused on rephrasing CollaboRATE items to promote reflection before each item. Study 2 used 5 open‐ended questions (about what went well and what could be improved upon, signs that the clinician understood the patient's situation, how the situation will be addressed, and why this treatment plan makes sense) to invite reflection before using the whole scale. A linear analogue scale assessed the extent to which the plan of care made sense to the patient. Results In Study 1, 107 participants completed surveys (84% response rate), 43 (40%) rated a clinical decision of which 27 (63%) after responding to reflection questions. Adding reflection lowered CollaboRATE scores (“less” SDM) and reduced the proportion of patients giving maximum (ceiling) scores (not statistically significant). In Study 2, 103 of 212 responders (49%) fully completed the version containing reflection questions. Reflection did not significantly change the distribution of CollaboRATE scores or of top scores. Participants indicated high scores on the sense of their care plan (mean 9.7 out of 10, SD 0.79). This rating was weakly correlated with total CollaboRATE scores (rho = .4, P = .0001). Conclusion Reflection‐before‐quantification interventions may not improve the performance of patient‐reported measures of SDM with substantial ceiling/halo effects.

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.

Whether disclosure of genetic risk for coronary heart disease (CHD) influences shared decision-making (SDM) regarding use of statins to reduce CHD risk is unknown. We randomized 207 patients, age 45–65 years, at intermediate CHD risk, and not on statins, to receive the 10-year risk of CHD based on conventional risk factors alone (n=103) or in combination with a genetic risk score (n=104). A genetic counselor disclosed this information followed by a physician visit for SDM regarding statin therapy. A novel decision aid was used in both encounters to disclose the CHD risk estimates and facilitate SDM regarding statin use. Patients reported their decision quality and physician visit satisfaction using validated surveys. There were no statistically significant differences between the two groups in the SDM score, satisfaction with the clinical encounter, perception of the quality of the discussion or of participation in decision-making and physician visit satisfaction scores. Quantitative analyses of a random subset of 80 video-recorded encounters using the OPTION5 scale also showed no significant difference in SDM between the two groups. Disclosure of CHD genetic risk using an electronic health record-linked decision aid did not adversely affect SDM or patients’ satisfaction with the clinical encounter. Trial registration number NCT01936675; Results.