Citations

Background: Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm designed to detect low left ventricular ejection fraction using the 12-lead ECG varies by race/ethnicity and to (2) determine whether its performance is determined by the derivation population or by racial variation in the ECG. Methods: We performed a retrospective cohort analysis that included 97 829 patients with paired ECGs and echocardiograms. We tested the model performance by race/ethnicity for convolutional neural network designed to identify patients with a left ventricular ejection fraction ≤35% from the 12-lead ECG. Results: The convolutional neural network that was previously derived in a homogeneous population (derivation cohort, n=44 959; 96.2% non-Hispanic white) demonstrated consistent performance to detect low left ventricular ejection fraction across a range of racial/ethnic subgroups in a separate testing cohort (n=52 870): non-Hispanic white (n=44 524; area under the curve [AUC], 0.931), Asian (n=557; AUC, 0.961), black/African American (n=651; AUC, 0.937), Hispanic/Latino (n=331; AUC, 0.937), and American Indian/Native Alaskan (n=223; AUC, 0.938). In secondary analyses, a separate neural network was able to discern racial subgroup category (black/African American [AUC, 0.84], and white, non-Hispanic [AUC, 0.76] in a 5-class classifier), and a network trained only in non-Hispanic whites from the original derivation cohort performed similarly well across a range of racial/ethnic subgroups in the testing cohort with an AUC of at least 0.930 in all racial/ethnic subgroups. Conclusions: Our study demonstrates that while ECG characteristics vary by race, this did not impact the ability of a convolutional neural network to predict low left ventricular ejection fraction from the ECG. We recommend reporting of performance among diverse ethnic, racial, age, and sex groups for all new artificial intelligence tools to ensure responsible use of artificial intelligence in medicine.

Despite its rank as the fourth healthiest state in the United States, Minnesota has clear cardiovascular disease disparities between African-Americans and whites. Culturally-tailored interventions implemented using community-based participatory research (CBPR) principles have been vital to improving health and wellness among African-Americans. This paper delineates the establishment, impact, and lessons learned from the formation of a community steering committee (CSC) to guide the Fostering African-American Improvement in Total Health (FAITH!) Program, a CBPR cardiovascular health promotion initiative among African-Americans in Minnesota. The theory-informed CSC implementation process included three phases: (1) Membership Formation and Recruitment, (2) Engagement, and (3) Covenant Development and Empowerment. The CSC is comprised of ten diverse community members guided by mutually agreed upon bylaws in their commitment to FAITH!. Overall, members considered the CSC implementation process effective and productive. A CBPR conceptual model provided an outline of proximal and distal goals for the CSC and FAITH!. The CSC implementation process yielded four lessons learned: (1) Have clarity of purpose and vision, (2) cultivate group cohesion, (3) employ consistent review of CBPR tenets, and (4) expect the unexpected. A robust CSC was established and was instrumental to the success and impact of FAITH! within African-American communities in Minnesota.

Introduction: African American women are 5 times less likely than white women to meet at least 5 or more ideal cardiovascular health metrics as defined by the American Heart Association Life’s Simple 7 (LS7) components (smoking, diet, physical activity, BMI, blood pressure, total cholesterol, and glucose). There are few studies probing the influence of sociocultural factors, such as body image dissatisfaction (BID), on these disparities. A better understanding of the impact of BID on cardiovascular health could assist in the design of more effective behavior change interventions for African American women. Hypothesis: We hypothesized that BID would have a negative association with cardiovascular health in overweight and obese African American women. Methods: We enrolled 32 women (mean age 49 years [SD 12.9]), from 5 predominantly African American churches participating in a larger community-based participatory study (FAITH! App Pilot Study) of a mobile health lifestyle intervention among African American women and men. We conducted a cross-sectional analysis of baseline data to evaluate the association between BID and both cardiovascular health and select psychosocial factors (e.g. motivation for healthy eating, diet self-regulation). A LS7 composite score was calculated as a measure of overall cardiovascular health (range 0-14). The Pulvers scale, consisting of images of women across the BMI spectrum, was used to measure perceived current and goal body size (rating of figures, 1-9; underweight to very obese). A BID score was calculated as the difference between perceived current and desired body image (range -8-8; BID < 0 [desire to be heavier], BID > 0 [desire to be thinner], BID = 0 [no dissatisfaction]). The BID score range for our cohort was 0-4. Thus, we categorized BID as no/low BID (BID score 0-1) or high BID (BID score 2-4). Results: Twenty-two percent (7/32) of women were overweight (BMI 25-29.9) and 78% (25/32) were obese (BMI (≥ 30). Forty-four percent (14/32) had no/low BID and 56% (18/32) had high BID. Those with high BID were more likely to be obese as compared to no/low BID (94% (17/18) versus 57% (8/14), p=0.03). Although not statistically significant, the mean LS7 composite score was 1 point higher among those with no/low BID, versus high BID (8.83 versus 7.76, p=0.25). Compared to women with high BID, those with no/low BID were more likely to have greater: intrinsic motivation (P=0.01) and integrated regulation for healthy eating (P=0.007), and self-regulation to reduce fat and caloric intake (P=0.01). Conclusion: Ultimately, although small, our study suggests that African-American women with obesity are more likely to have high BID. High BID was associated with lower motivation and self-regulation, which predict cardiovascular health. BID and other psychosocial factors for behavior change are potential targets for culturally-tailored lifestyle interventions in this group.

Background Ideal cardiovascular health metrics (defined by the American Heart Association Life's Simple 7 [LS7]) are suboptimal among blacks, which results in high risk of cardiovascular disease. We examined the association of multiple stressors with LS7 components among blacks. Methods and Results Using a community‐based cohort of blacks (N=4383), we examined associations of chronic stress, minor stressors, major life events, and a cumulative stress score with LS7 components (smoking, diet, physical activity, body mass index, blood pressure, total cholesterol, and fasting plasma glucose) and an LS7 composite score. Multivariable logistic regression assessed the odds of achieving intermediate/ideal levels of cardiovascular health adjusted for demographic, socioeconomic, behavioral, and biomedical factors. The LS7 components with the lowest percentages of intermediate/ideal cardiovascular health levels were diet (39%), body mass index (47%), and physical activity (51%). Higher chronic, minor, and cumulative stress scores were associated with decreased odds (odds ratio [OR]) of achieving intermediate/ideal levels for smoking (OR [95% confidence interval], 0.80 [0.73–0.88], 0.84 [0.75–0.94], and 0.81 [0.74–0.90], respectively). Participants with more major life events had decreased odds of achieving intermediate/ideal levels for smoking (OR, 0.84; 95% confidence interval, 0.76–0.92) and fasting plasma glucose (OR, 0.90; 95% confidence interval, 0.82–0.98). Those with higher scores for minor stressors and major life events were less likely to achieve intermediate or ideal LS7 composite scores (OR [95% confidence interval], 0.89 [0.81–0.97] and 0.91 [0.84–0.98], respectively). Conclusions Blacks with higher levels of multiple stress measures are less likely to achieve intermediate or ideal levels of overall cardiovascular health (LS7 composite score), specific behaviors (smoking), and biological factors (fasting plasma glucose).

Background Despite its benefits, cardiac rehabilitation (CR) participation rates remain subpar. Telehealth lifestyle interventions have emerged as modalities to enhance CR accessibility. Virtual-world (VW) technology may provide a means to increase CR use. Objectives This pilot study assessed the feasibility and acceptability of a VW-based CR program as an extension to medical center-based CR. Our goal is to apply the study results toward the design of a patient-centered VW platform prototype with high usability, understandability, and credibility. Methods Patients ( n = 8, 25% women) recently enrolled in outpatient CR at Mayo Clinic, Rochester, Minnesota participated in a 12-week, VW health education program and provided feedback on the usability, design and satisfaction of the intervention at baseline and completion. A mixed-methods approach was used to analyze the participant perceptions of the intervention. Results Overall, there were positive participant perceptions of the VW experience. There was unanimous high satisfaction with the graphical interface appearance and ease of use. Participants placed value on the convenience, accessibility, and social connectivity of the remote program as well as the novelty of the simulation platform presentations, which aided in memorability of key concepts. Greater than 80% of participants reported that the program improved their health knowledge and helped to maintain better health habits. Conclusions Our pilot study revealed the feasibility and acceptability of an innovative VW-based CR program among cardiac patients. This novel delivery method for CR has the potential to influence healthy lifestyle change and to increase accessibility to vulnerable populations with higher cardiovascular disease burdens.

Striking cardiovascular health disparities exist among African-Americans in Minnesota compared to Whites; however, community-based interventions to address cardiovascular disease risk are lacking. This study explored participant perceptions of a culturally tailored, cardiovascular disease prevention program developed using a community-based participatory research process. Research participation perceptions, program benefits, and program satisfaction/acceptability were analyzed using a mixed-methods approach. Overall, acceptability was high. Findings highlight the favorable inclusion of African-Americans (research perception), knowledge gained about healthy lifestyle practices (benefits), and quality of the curriculum/speakers (satisfaction). Community-based participatory research may be useful in fostering the acceptability of behavior change interventions among marginalized African-American communities.

Objective: To examine perceptions and attitudes toward health-related research participation among professional African American women. Methods: Participants were members of an African American women's service organization, The Links, Incorporated. Data were collected via self-administered questionnaires at The Links, Incorporated 2012 National Assembly. Sociodemographics, prior research experience, intention to participate (ITP), willingness to participate (WTP) in a variety of research studies and attitudes about research participation were measured. Results: A total of 381 surveys were analyzed. A majority of respondents were married (66%), employed (69%), and college educated (96%). Median age was 59; 38% reported prior research participation. Overall, 78% agreed with the statement, “Participation in research will mean better care,” 24% agreed “Participation in research is risky” and 3% agreed “Scientists cannot be trusted.” Fifty-two percent agreed with the statement, “Research conducted in the U.S. is ethical.” Mean ITP in research was 4.9±1.7 on a rating scale of 1 (“definitely no”) to 7 (“definitely yes”). WTP was highest for an interview study and providing a blood sample, and lowest for clinical trial and medical record review. Conclusion: Attitudes toward research participation were generally favorable among professional African American women; many expressed WTP in a variety of research study types.