Digital Technologies in Cardiac Rehabilitation: A Science Advisory From the American Heart Association.

Cardiac rehabilitation has strong evidence of benefit across many cardiovascular conditions but is underused. Even for those patients who participate in cardiac rehabilitation, there is the potential to better support them in improving behaviors known to promote optimal cardiovascular health and in sustaining those behaviors over time. Digital technology has the potential to address many of the challenges of traditional center-based cardiac rehabilitation and to augment care delivery. This American Heart Association science advisory was assembled to guide the development and implementation of digital cardiac rehabilitation interventions that can be translated effectively into clinical care, improve health outcomes, and promote health equity. This advisory thus describes the individual digital components that can be delivered in isolation or as part of a larger cardiac rehabilitation telehealth program and highlights challenges and future directions for digital technology generally and when used in cardiac rehabilitation specifically. It is also intended to provide guidance to researchers reporting digital interventions and clinicians implementing these interventions in practice and to advance a framework for equity-centered digital health in cardiac rehabilitation.

Increasing Equity of Physical Activity Promotion for Optimal Cardiovascular Health in Adults: A Scientific Statement From the American Heart Association.

Fewer than 1 in 4 adults achieves the recommended amount of physical activity, with lower activity levels reported among some groups. Addressing low levels of physical activity among underresourced groups provides a modifiable target with the potential to improve equity in cardiovascular health. This article (1) examines physical activity levels across strata of cardiovascular disease risk factors, individual level characteristics, and environmental factors; (2) reviews strategies for increasing physical activity in groups who are underresourced or at risk for poor cardiovascular health; and (3) provides practical suggestions for physical activity promotion to increase equity of risk reduction and to improve cardiovascular health. Physical activity levels are lower among those with elevated cardiovascular disease risk factors, among certain groups (eg, older age, female, Black race, lower socioeconomic status), and in some environments (eg, rural). There are strategies for physical activity promotion that can specifically support underresourced groups such as engaging the target community in designing and implementing interventions, developing culturally appropriate study materials, identifying culturally tailored physical activity options and leaders, building social support, and developing materials for those with low literacy. Although addressing low physical activity levels will not address the underlying structural inequities that deserve attention, promoting physical activity among adults, especially those with both low physical activity levels and poor cardiovascular health, is a promising and underused strategy to reduce cardiovascular health inequalities.

Artificial intelligence of arterial Doppler waveforms to predict major adverse outcomes among patients with diabetes mellitus.

OBJECTIVE: Patients with diabetes mellitus (DM) are at increased risk for peripheral artery disease (PAD) and its complications. Arterial calcification and non-compressibility may limit test interpretation in this population. Developing tools capable of identifying PAD and predicting major adverse cardiac event (MACE) and limb event (MALE) outcomes among patients with DM would be clinically useful. Deep neural network analysis of resting Doppler arterial waveforms was used to detect PAD among patients with DM and to identify those at greatest risk for major adverse outcome events. METHODS: Consecutive patients with DM undergoing lower limb arterial testing (April 1, 2015-December 30, 2020) were randomly allocated to training, validation, and testing subsets (60%, 20%, and 20%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict all-cause mortality, MACE, and MALE at 5 years using quartiles based on the distribution of the prediction score. RESULTS: Among 11,384 total patients, 4211 patients with DM met study criteria (mean age, 68.6 ± 11.9 years; 32.0% female). After allocating the training and validation subsets, the final test subset included 856 patients. During follow-up, there were 262 deaths, 319 MACE, and 99 MALE. Patients in the upper quartile of prediction based on deep neural network analysis of the posterior tibial artery waveform provided independent prediction of death (hazard ratio [HR], 3.58; 95% confidence interval [CI], 2.31-5.56), MACE (HR, 2.06; 95% CI, 1.49-2.91), and MALE (HR, 13.50; 95% CI, 5.83-31.27). CONCLUSIONS: An artificial intelligence enabled analysis of a resting Doppler arterial waveform permits identification of major adverse outcomes including all-cause mortality, MACE, and MALE among patients with DM.

Leveraging Implementation Science for Cardiovascular Health Equity: A Scientific Statement From the American Heart Association.

Reducing cardiovascular disease disparities will require a concerted, focused effort to better adopt evidence-based interventions, in particular, those that address social determinants of health, in historically marginalized populations (ie, communities excluded on the basis of social identifiers like race, ethnicity, and social class and subject to inequitable distribution of social, economic, physical, and psychological resources). Implementation science is centered around stakeholder engagement and, by virtue of its reliance on theoretical frameworks, is custom built for addressing research-to-practice gaps. However, little guidance exists for how best to leverage implementation science to promote cardiovascular health equity. This American Heart Association scientific statement was commissioned to define implementation science with a cardiovascular health equity lens and to evaluate implementation research that targets cardiovascular inequities. We provide a 4-step roadmap and checklist with critical equity considerations for selecting/adapting evidence-based practices, assessing barriers and facilitators to implementation, selecting/using/adapting implementation strategies, and evaluating implementation success. Informed by our roadmap, we examine several organizational, community, policy, and multisetting interventions and implementation strategies developed to reduce cardiovascular disparities. We highlight gaps in implementation science research to date aimed at achieving cardiovascular health equity, including lack of stakeholder engagement, rigorous mixed methods, and equity-informed theoretical frameworks. We provide several key suggestions, including the need for improved conceptualization and inclusion of social and structural determinants of health in implementation science, and the use of adaptive, hybrid effectiveness designs. In addition, we call for more rigorous examination of multilevel interventions and implementation strategies with the greatest potential for reducing both primary and secondary cardiovascular disparities.

Screening for peripartum cardiomyopathies using artificial intelligence in Nigeria (SPEC-AI Nigeria): Clinical trial rationale and design.

BACKGROUND: Artificial intelligence (AI), and more specifically deep learning, models have demonstrated the potential to augment physician diagnostic capabilities and improve cardiovascular health if incorporated into routine clinical practice. However, many of these tools are yet to be evaluated prospectively in the setting of a rigorous clinical trial-a critical step prior to implementing broadly in routine clinical practice. OBJECTIVES: To describe the rationale and design of a proposed clinical trial aimed at evaluating an AI-enabled electrocardiogram (AI-ECG) for cardiomyopathy detection in an obstetric population in Nigeria. DESIGN: The protocol will enroll 1,000 pregnant and postpartum women who reside in Nigeria in a prospective randomized clinical trial. Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. Women aged 18 and older, seen for routine obstetric care at 6 sites (2 Northern and 4 Southern) in Nigeria will be included. Participants will be randomized to the study intervention or control arm in a 1:1 fashion. This study aims to enroll participants representative of the general obstetric population at each site. The primary outcome is a new diagnosis of cardiomyopathy, defined as left ventricular ejection fraction (LVEF) < 50% during pregnancy or within 12 months postpartum. Secondary outcomes will include the detection of impaired left ventricular function (at different LVEF cut-offs), and exploratory outcomes will include the effectiveness of AI-ECG tools for cardiomyopathy detection, new diagnosis of cardiovascular disease, and the development of composite adverse maternal cardiovascular outcomes. SUMMARY: This clinical trial focuses on the emerging field of cardio-obstetrics and will serve as foundational data for the use of AI-ECG tools in an obstetric population in Nigeria. This study will gather essential data regarding the utility of the AI-ECG for cardiomyopathy detection in a predominantly Black population of women and pave the way for clinical implementation of these models in routine practice. TRIAL REGISTRATION: Clinicaltrials.gov: NCT05438576.

Prediction of blood volume to be processed to achieve a target number of CD34+ cells: Development, validation and implementation of a formula.

BACKGROUND AND OBJECTIVES: Calculation of blood volume (BV) to be processed to achieve the target number of CD34+ cells can be accomplished by using collection efficiency 2 (CE2) formula. Our aim was to develop a BV web formula. MATERIALS AND METHODS: We calculated CE2 from aphereses performed between January 2015 and March 2020 in allogeneic donors and patients. From May 2020 to May 2021, we validated a formula: BV = ((Target CD34+ cells in the product)/(CD34+ pre-apheresis cells × CE2)) × 100. Subsequently, we compared the outcome of the procedures carried out before formula implementation (pre-formula), when standard three total BV collection was performed. RESULTS: CE2 was assessed in 384 apheresis procedures before formula implementation. CE2 was higher in allogeneic donors than in patients (53% ± 17% vs. 48% ± 15%, p = 0.008). CE2 was higher in multiple myeloma and non-Hodgkin lymphoma than Hodgkin's lymphoma (48% ± 15%, 48% ± 15% and 42% ± 13%, respectively; p = 0.008). Our formula (available on a website: Publisheet) was prospectively used in 54 individuals. The formula was very accurate: predicted versus observed CD34 + cells/kg collected had an r-value of 0.89 (p < 0.0001). We compared their results with 78 pre-formula individuals. In the post-formula group, a greater BV was processed in patients and less BV in allogeneic donors. Among individuals under 60 years of age, it was significantly less frequent than the need for more than one apheresis in the post-formula group. CONCLUSION: Formula calculations were accurate. Formula implementation allowed the optimization of the procedures and reduced the rate of individuals in need of apheresis for more than 1 day.

Machine-learning-derived heart and brain age are independently associated with cognition.

BACKGROUND AND PURPOSE: A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. METHODS: Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40-85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. RESULTS: Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3-36) of the HDA effect on the tapping test score was mediated through BDA. DISCUSSION: Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

Association of Bipolar Disorder With Major Adverse Cardiovascular Events: A Population-Based Historical Cohort Study.

OBJECTIVE: This study aimed to assess the association of bipolar disorder (BD) with risk of major adverse cardiac events (MACEs) after adjusting for established cardiovascular disease (CVD) risk factors. METHODS: We conducted a population-based historical cohort study using the Rochester Epidemiology Project. Patients older than 30 years with a clinical encounter from 1998 to 2000 with no prior MACE, atrial fibrillation, or heart failure were followed up through March 1, 2016. BD diagnosis was validated by chart review. Cox proportional hazards regression models were adjusted for established CVD risk factors, alcohol use disorder, other substance use disorders (SUDs), and major depressive disorder (MDD). RESULTS: The cohort included 288 individuals with BD (0.81%) and 35,326 individuals without BD as the reference group (Ref). Median (interquartile range) follow-up was 16.5 (14.6-17.5) years. A total of 5636 MACE events occurred (BD, 59; Ref, 5577). Survival analysis showed an association between BD and MACE (median event-free-survival rates: BD, 0.80; Ref, 0.86; log-rank p = .018). Multivariate regression adjusting for age and sex also yielded an association between BD and MACE (hazard ratio [HR] = 1.93; 95% confidence interval [CI] = 1.43-2.52; p < .001). The association remained significant after further adjusting for smoking, diabetes mellitus, hypertension, high-density lipoprotein cholesterol, and body mass index (HR = 1.66; 95% CI = 1.17-2.28; p = .006), and for alcohol use disorder, SUD, and MDD (HR = 1.56; 95% CI = 1.09-2.14; p = .010). CONCLUSIONS: In this study, BD was associated with an increased risk of MACE, which persisted after adjusting for established CVD risk factors, SUDs, and MDD. These results suggest that BD is an independent risk factor for major clinical cardiac disease outcomes.

Ceramide Scores Predict Cardiovascular Risk in the Community.

[Figure: see text].

Artificial intelligence for the evaluation of peripheral artery disease using arterial Doppler waveforms to predict abnormal ankle-brachial index.

BACKGROUND: Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD. METHODS: Consecutive patients (4/8/2015 - 12/31/2020) undergoing rest and postexercise ankle-brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 - 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance. RESULTS: Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92-0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91-0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison). CONCLUSION: An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.

Electrocardiogram screening for aortic valve stenosis using artificial intelligence.

AIMS: Early detection of aortic stenosis (AS) is becoming increasingly important with a better outcome after aortic valve replacement in asymptomatic severe AS patients and a poor outcome in moderate AS. We aimed to develop artificial intelligence-enabled electrocardiogram (AI-ECG) using a convolutional neural network to identify patients with moderate to severe AS. METHODS AND RESULTS: Between 1989 and 2019, 258 607 adults [mean age 63 ± 16.3 years; women 122 790 (48%)] with an echocardiography and an ECG performed within 180 days were identified from the Mayo Clinic database. Moderate to severe AS by echocardiography was present in 9723 (3.7%) patients. Artificial intelligence training was performed in 129 788 (50%), validation in 25 893 (10%), and testing in 102 926 (40%) randomly selected subjects. In the test group, the AI-ECG labelled 3833 (3.7%) patients as positive with the area under the curve (AUC) of 0.85. The sensitivity, specificity, and accuracy were 78%, 74%, and 74%, respectively. The sensitivity increased and the specificity decreased as age increased. Women had lower sensitivity but higher specificity compared with men at any age groups. The model performance increased when age and sex were added to the model (AUC 0.87), which further increased to 0.90 in patients without hypertension. Patients with false-positive AI-ECGs had twice the risk for developing moderate or severe AS in 15 years compared with true negative AI-ECGs (hazard ratio 2.18, 95% confidence interval 1.90-2.50). CONCLUSION: An AI-ECG can identify patients with moderate or severe AS and may serve as a powerful screening tool for AS in the community.

Utilizing Conversational Artificial Intelligence, Voice, and Phonocardiography Analytics in Heart Failure Care.

Conversational artificial intelligence involves the ability of computers, voice-enabled devices to interact intelligently with the user through voice. This can be leveraged in heart failure care delivery, benefiting the patients, providers, and payers, by providing timely access to care, filling the gaps in care, optimizing management, improving quality of care, and reducing cost. Introduction of machine learning to phonocardiography has potential to achieve outstanding diagnostic and prognostic performances in heart failure patients. There is ongoing research to use voice as a biomarker in heart failure patients. If successful, this may facilitate the screening, diagnosis, and clinical assessment of heart failure.

Cardiac rehabilitation availability and characteristics in Latin America and the Caribbean: A Global Comparison.

BACKGROUND: This study aimed to establish availability and characteristics of cardiac rehabilitation (CR) in Latin America and the Caribbean (LAC), where cardiovascular disease is highly prevalent. METHODS: In this cross-sectional sub-analysis focusing on the 35 LAC countries, local cardiovascular societies identified CR programs globally. An online survey was administered to identified programs, assessing capacity and characteristics. CR need was computed relative to ischemic heart disease (IHD) incidence from the Global Burden of Disease study. RESULTS: ≥1 CR program was identified in 24 LAC countries (68.5% availability; median = 3 programs/country). Data were collected in 20/24 countries (83.3%); 139/255 programs responded (54.5%), and compared to responses from 1082 programs in 111 countries. LAC density was 1 CR spot per 24 IHD patients/year (vs 18 globally). Greatest need was observed in Brazil, Dominican Republic and Mexico (all with >150,000 spots needed/year). In 62.8% (vs 37.2% globally P < .001) of CR programs, patients pay out-of-pocket for some or all of CR. CR teams were comprised of a mean of 5.0 ± 2.3 staff (vs 6.0 ± 2.8 globally; P < .001); Social workers, dietitians, kinesiologists, and nurses were significantly less common on CR teams than globally. Median number of core components offered was 8 (vs 9 globally; P < .001). Median dose of CR was 36 sessions (vs 24 globally; P < .001). Only 27 (20.9%) programs offered alternative CR models (vs 31.1% globally; P < .01). CONCLUSION: In LAC countries, there is very limited CR capacity in relation to need. CR dose is high, but comprehensiveness low, which could be rectified with a more multidisciplinary team.

Transfusion support in COVID-19 patients: Impact on hospital blood component supply during the outbreak.

BACKGROUND: During the COVID-19 outbreak, most hospitals deferred elective surgical procedures to allow space for the overwhelming number of COVID-19 patient admissions, expecting a decrease in routine blood component requirements. However, because transfusion support needs of COVID-19 patients are not well known, its impact on hospital blood supply is uncertain. The objective of this study was to assess the effect of the COVID-19 pandemic on transfusion demand. STUDY DESIGN AND METHODS: Transfusion records during the peak of the COVID-19 pandemic (March 1-April 30, 2020) were reviewed in our center to assess changes in blood requirements. RESULTS: During this period 636 patients received a total of 2934 blood components, which reflects a 17.6% reduction in transfusion requirements with regard to the same period of 2019, and blood donations in Madrid dropped by 45%. The surgical blood demand decreased significantly during the outbreak (50.2%). Blood usage in the hematology and oncology departments remained unchanged, while the day ward demand halved, and intensive care unit transfusion needs increased by 116%. A total of 6.2% of all COVID inpatients required transfusion support. COVID-19 inpatients consumed 19% of all blood components, which counterbalanced the savings owed to the reduction in elective procedures. CONCLUSION: Although only a minority of COVID-19 inpatients required transfusion, the expected reduction in transfusion needs caused by the lack of elective surgical procedures is partially offset by the large number of admitted patients during the peak of the pandemic. This fact must be taken into account when planning hospital blood supply.

Demographic characteristics associated with circadian rest-activity rhythm patterns: a cross-sectional study.

BACKGROUND: Rest-activity rhythm (RAR), a manifestation of circadian rhythms, has been associated with morbidity and mortality risk. However, RAR patterns in the general population and specifically the role of demographic characteristics in RAR pattern have not been comprehensively assessed. Therefore, we aimed to describe RAR patterns among non-institutionalized US adults and age, sex, and race/ethnicity variation using accelerometry data from a nationally representative population. METHODS: This cross-sectional study was conducted using the US National Health and Nutrition Examination Survey (NHANES) 2011-2014. Participants aged ≥20 years who were enrolled in the physical activity monitoring examination and had at least four 24-h periods of valid wrist accelerometer data were included in the present analysis. 24-h RAR metrics were generated using both extended cosinor model (amplitude, mesor, acrophase and pseudo-F statistic) and nonparametric methods (interdaily stability [IS] and intradaily variability [IV]). Multivariable linear regression was used to assess the association between RAR and age, sex, and race/ethnicity. RESULTS: Eight thousand two hundred participants (mean [SE] age, 49.1 [0.5] years) were included, of whom 52.2% were women and 67.3% Whites. Women had higher RAR amplitude and mesor, and also more robust (pseudo-F statistic), more stable (higher IS) and less fragmented (lower IV) RAR (all P trend < 0.001) than men. Compared with younger adults (20-39 years), older adults (≥ 60 years) exhibited reduced RAR amplitude and mesor, but more stable and less fragmented RAR, and also reached their peak activity earlier (advanced acrophase) (all P trend < 0.001). Relative to other racial/ethnic groups, Hispanics had the highest amplitude and mesor level, and most stable (highest IS) and least fragmented (lowest IV) RAR pattern (P trend < 0.001). Conversely, non-Hispanic blacks had the lowest peak activity level (lowest amplitude) and least stable (lowest IS) RAR pattern (all P trend < 0.001). CONCLUSIONS: In the general adult population, RAR patterns vary significantly according to sex, age and race/ethnicity. These results may reflect demographic-dependent differences in intrinsic circadian rhythms and may have important implications for understanding racial, ethnic, sex and other disparities in morbidity and mortality risk.

The Prevalence of Dysglycemia-Based Chronic Disease in a European Population - a New Paradigm to Address Diabetes Burden: A Kardiovize Study.

OBJECTIVE: To determine the prevalence rate and associated risk factors for each stage of the Dysglycemia-Based Chronic Disease (DBCD) model, which 4 distinct stages and prompts early prevention to avert Diabetes and cardiometabolic complications. METHODS: Subjects between 25 and 64 years old from a random population-based sample were evaluated in Czechia from 2013 to 2014 using a cross-sectional design. DBCD stages were: stage 1 "insulin resistance" (inferred risk from abdominal obesity or a family history of diabetes); stage 2 "prediabetes"(fasting glucose between 5.6 and 6.9 mmol/L); stage 3 "type 2 diabetes (T2D)" (self-report of T2D or fasting glucose ≥7 mmol/L); and stage 4 "vascular complications" (T2D with cardiovascular disease). RESULTS: A total of 2147 subjects were included (57.8% women) with a median age of 48 years. The prevalence of each DBCD stage were as follows: 54.2% (stage 1); 10.3% (stage 2), 3.7% (stage 3); and 1.2% (stage 4). Stages 2 to 4 were more frequent in men and stage 1 in women (P < .001). Using binary logistic regression analysis adjusting by age/sex, all DBCD stages were strongly associated with abnormal adiposity, hypertension, dyslipidemia, and smoking status. Subjects with lower educational levels and lower income were more likely to present DBCD. CONCLUSION: Using the new DBCD framework and available metrics, 69.4% of the population had DBCD, identifying far more people at risk than a simple prevalence rate for T2D (9.2% in Czechia, 2013-2014). All stages were associated with traditional cardiometabolic risk factors, implicating common pathophysiologic mechanisms and a potential for early preventive care. The social determinants of health were related with all DBCD stages in alarming proportions and will need to be further studied.

Arterial Stiffness and Cardiometabolic-Based Chronic Disease: The Kardiovize Study.

OBJECTIVE: Arterial stiffness (ArSt) describes a loss of arterial wall elasticity and is an independent predictor of cardiovascular events. A cardiometabolic-based chronic disease model integrates concepts of adiposity-based chronic disease (ABCD), dysglycemia-based chronic disease (DBCD), and cardiovascular disease. We assessed if ABCD and DBCD models detect more people with high ArSt compared with traditional adiposity and dysglycemia classifiers using the cardio-ankle vascular index (CAVI). METHODS: We evaluated 2070 subjects aged 25 to 64 years from a random population-based sample. Those with type 1 diabetes were excluded. ABCD and DBCD were defined, and ArSt risk was stratified based on the American Association of Clinical Endocrinologists criteria. RESULTS: The highest prevalence of a high CAVI was in stage 2 ABCD (18.5%) and stage 4 DBCD (31.8%), and the lowest prevalence was in stage 0 ABCD (2.2%). In univariate analysis, stage 2 ABCD and all DBCD stages increased the risk of having a high CAVI compared with traditional classifiers. After adjusting for age and gender, only an inverse association between obesity (body mass index ≥30 kg/m2) and CAVI remained significant. Nevertheless, body mass index was responsible for only 0.3% of CAVI variability. CONCLUSION: The ABCD and DBCD models showed better performance than traditional classifiers to detect subjects with ArSt; however, the variables were not independently associated with age and gender, which might be explained by the complexity and multifactoriality of the relationship of CAVI with the ABCD and DBCD models, mediated by insulin resistance.

Women-Only Cardiac Rehabilitation Delivery Around the World.

BACKGROUND: Women utilise cardiac rehabilitation (CR) significantly less than men. Gender-tailored CR improves adherence and mental health outcomes when compared to traditional programs. This study ascertained the availability of women-only (W-O) CR classes globally. METHODS: In this cross-sectional study, an online survey was administered to CR programs globally, assessing delivery of W-O classes, among other program characteristics. Univariate tests were performed to compare provision of W-O CR by program characteristics. RESULTS: Data were collected in 93/111 countries with CR (83.8% country response rate); 1,082 surveys (32.1% program response rate) were initiated. Globally, 38 (40.9%; range 1.2-100% of programs/country) countries and 110 (11.8%) programs offered W-O CR. Women-Only CR was offered in 55 (7.4%) programs in high-income countries, versus 55 (16.4%) programs in low- and middle-income countries (p<0.001); it was offered most commonly in the Eastern Mediterranean region (n=5, 55.6%; p=0.22). Programs that offered W-O CR were more often located in an academic or tertiary facility, served more patients/year, offered more components, treated more patients/session, offered alternative forms of exercise, had more staff (including cardiologists, dietitians, and administrative assistants, but not mental health care professionals), and perceived space and human resources to be less of a barrier to delivery than programs not offering W-O CR (all p<0.05). CONCLUSION: Women-Only CR was not commonly offered. Only larger, well-resourced programs seem to have the capacity to offer it, so expanding delivery may require exploiting low-cost, less human resource-intensive approaches such as online peer support.

An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction.

BACKGROUND: Atrial fibrillation is frequently asymptomatic and thus underdetected but is associated with stroke, heart failure, and death. Existing screening methods require prolonged monitoring and are limited by cost and low yield. We aimed to develop a rapid, inexpensive, point-of-care means of identifying patients with atrial fibrillation using machine learning. METHODS: We developed an artificial intelligence (AI)-enabled electrocardiograph (ECG) using a convolutional neural network to detect the electrocardiographic signature of atrial fibrillation present during normal sinus rhythm using standard 10-second, 12-lead ECGs. We included all patients aged 18 years or older with at least one digital, normal sinus rhythm, standard 10-second, 12-lead ECG acquired in the supine position at the Mayo Clinic ECG laboratory between Dec 31, 1993, and July 21, 2017, with rhythm labels validated by trained personnel under cardiologist supervision. We classified patients with at least one ECG with a rhythm of atrial fibrillation or atrial flutter as positive for atrial fibrillation. We allocated ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. We calculated the area under the curve (AUC) of the receiver operatoring characteristic curve for the internal validation dataset to select a probability threshold, which we applied to the testing dataset. We evaluated model performance on the testing dataset by calculating the AUC and the accuracy, sensitivity, specificity, and F1 score with two-sided 95% CIs. FINDINGS: We included 180 922 patients with 649 931 normal sinus rhythm ECGs for analysis: 454 789 ECGs recorded from 126 526 patients in the training dataset, 64 340 ECGs from 18 116 patients in the internal validation dataset, and 130 802 ECGs from 36 280 patients in the testing dataset. 3051 (8·4%) patients in the testing dataset had verified atrial fibrillation before the normal sinus rhythm ECG tested by the model. A single AI-enabled ECG identified atrial fibrillation with an AUC of 0·87 (95% CI 0·86-0·88), sensitivity of 79·0% (77·5-80·4), specificity of 79·5% (79·0-79·9), F1 score of 39·2% (38·1-40·3), and overall accuracy of 79·4% (79·0-79·9). Including all ECGs acquired during the first month of each patient's window of interest (ie, the study start date or 31 days before the first recorded atrial fibrillation ECG) increased the AUC to 0·90 (0·90-0·91), sensitivity to 82·3% (80·9-83·6), specificity to 83·4% (83·0-83·8), F1 score to 45·4% (44·2-46·5), and overall accuracy to 83·3% (83·0-83·7). INTERPRETATION: An AI-enabled ECG acquired during normal sinus rhythm permits identification at point of care of individuals with atrial fibrillation. FUNDING: None.

Localizing genesis in polydomain liquid crystal elastomers.

Programming the local orientation of liquid crystal elastomers (LCEs) is a differentiated approach to prepare monolithic material compositions with localized deformation. Our prior efforts prepared LCEs with surface-enforced spatial variations in orientation to localize deformation when the LCEs were subjected to directional load. However, because these surface alignment methods included regions of planar orientation, the deformation of these programmed LCEs is inherently directional. The absence of macroscopic orientation in polydomain LCEs results in uniform, nonlinear deformation in all axes (omnidirectional soft elasticity). Here, we exploit the distinct mechanical response of polydomain LCEs prepared with isotropic or nematic genesis. By localizing the polydomain genesis via masked photopolymerizations conducted at different temperatures, we detail the preparation of main-chain, polydomain LCEs that are homogeneous in composition but exhibit spatially localized programmability in their mechanical response that is uniform in all directions.