Search

Abstract Accurately predicting patients' risk for specific medical outcomes is paramount for effective healthcare management and personalized medicine. While a substantial body of literature addresses the prediction of diverse medical conditions, existing models predominantly focus on singular outcomes, limiting their scope to one disease at a time. However, clinical reality often entails patients concurrently facing multiple health risks across various medical domains. In response to this gap, our study proposes a novel multi-risk framework adept at simultaneous risk prediction for multiple clinical outcomes, including diabetes, mortality, and hypertension. Leveraging a concise set of features extracted from patients' cardiorespiratory fitness data, our framework minimizes computational complexity while maximizing predictive accuracy. Moreover, we integrate a state-of-the-art instance-based interpretability technique into our framework, providing users with comprehensive explanations for each prediction. These explanations afford medical practitioners invaluable insights into the primary health factors influencing individual predictions, fostering greater trust and utility in the underlying prediction models. Our approach thus stands to significantly enhance healthcare decision-making processes, facilitating more targeted interventions and improving patient outcomes in clinical practice. Our prediction framework utilizes an automated machine learning framework, Auto-Weka, to optimize machine learning models and hyper-parameter configurations for the simultaneous prediction of three medical outcomes: diabetes, mortality, and hypertension. Additionally, we employ a local interpretability technique to elucidate predictions generated by our framework. These explanations manifest visually, highlighting key attributes contributing to each instance's prediction for enhanced interpretability. Using automated machine learning techniques, the models simultaneously predict hypertension, mortality, and diabetes risks, utilizing only nine patient features. They achieved an average AUC of 0.90 ± 0.001 on the hypertension dataset, 0.90 ± 0.002 on the mortality dataset, and 0.89 ± 0.001 on the diabetes dataset through tenfold cross-validation. Additionally, the models demonstrated strong performance with an average AUC of 0.89 ± 0.001 on the hypertension dataset, 0.90 ± 0.001 on the mortality dataset, and 0.89 ± 0.001 on the diabetes dataset using bootstrap evaluation with 1000 resamples.

Chest pain, a common symptom in cardiovascular care, often leads to the investigation of obstructive coronary artery disease (CAD). However, many patients experience chest pain without obstructive CAD, termed INOCA (Ischemia with Non-Obstructive Coronary Arteries) or CMD (Coronary Microvascular Dysfunction). INOCA can be attributed to endothelial dysfunction, vascular smooth muscle dysfunction, or both, affecting about 20–30 % of patients with nonobstructive CAD. The diagnostic approach for INOCA includes both invasive and non-invasive methods, with cardiac PET (Positron Emission Tomography) playing a significant role in risk stratification and management. PET evaluates various parameters like myocardial blood flow under stress and rest, myocardial flow reserve, and myocardial ischemia. Such comprehensive assessment is essential in accurately diagnosing and managing INOCA, considering the complexity of this condition.

Background Coronary microvascular function and hemodynamics may play a role in coronary circulation and myocardial remodeling in patients with aortic stenosis (AS). We aimed to evaluate the relationship between myocardial blood flow and myocardial function in patients with AS, no AS, and aortic valve sclerosis. Methods and Results We included consecutive patients who had resting transthoracic echocardiography and clinically indicated positron emission tomography myocardial perfusion imaging to capture their left ventricular ejection fraction, global longitudinal strain (GLS), and myocardial flow reserve (MFR). The primary outcome was major adverse cardiovascular event (all‐cause mortality, myocardial infarction, or late revascularization). There were 2778 patients (208 with aortic sclerosis, 39 with prosthetic aortic valve, 2406 with no AS, and 54, 49, and 22 with mild, moderate, and severe AS, respectively). Increasing AS severity was associated with impaired MFR (P

Abstract Background Diabetes Mellitus (DM) is a fast-growing health problem that imposes an enormous economic burden. Several studies demonstrated the association between physical inactivity and predicting the incidence of diabetes. However, these prediction models have limited validation locally. Therefore, we aim to explore the predictive value of exercise capacity in the incidence of diabetes within a high diabetes prevalence population. Methodology A retrospective cohort study including consecutive patients free of diabetes who underwent clinically indicated treadmill stress testing. Diabetic patients at baseline or patients younger than 18 years of age were excluded. Incident diabetes was defined as an established clinical diagnosis post-exercise testing date. The predictive value of exercise capacity was examined using Harrell’s c-index, net reclassification index (NRI), and integrated discrimination index (IDI). Results A total of 8,722 participants (mean age 46 ± 12 years, 66.3% were men) were free of diabetes at baseline. Over a median follow-up period of 5.24 (2.17–8.78) years, there were 2,280 (≈ 26%) new cases of diabetes. In a multivariate model adjusted for conventional risk factors, we found a 12% reduction in the risk of incident diabetes for each METs achieved (HR, 0.9; 95% CI, 0.88–0.92; P

Transthyretin amyloid cardiomyopathy (ATTR-CM) is a complex and serious form of heart failure caused by the accumulation of transthyretin amyloid protein in the heart muscle. Variable symptoms of ATTR-CM can lead to a delayed diagnosis. Recognizing the diagnostic indicators is crucial to promptly detect this condition. A targeted literature review was conducted to examine the latest international consensus recommendations on a comprehensive diagnosis of ATTR-CM. Additionally, a panel consisting of nuclear medicine expert consultants (n = 10) and nuclear imaging technicians (n = 2) convened virtually from the Kingdom of Saudi Arabia (KSA) to formulate best practices for ATTR-CM diagnosis. The panel reached a consensus on a standard diagnostic pathway for ATTR-CM, which commences by evaluating the presence of clinical red flags and initiating a cardiac workup to assess the patient’s echocardiogram. Cardiac magnetic resonance imaging may be needed, in uncertain cases. When there is a high suspicion of ATTR-CM, patients undergo nuclear scintigraphy and hematologic tests to rule out primary or light-chain amyloidosis. The expert panel emphasized that implementing best practices will support healthcare professionals in KSA to improve their ability to detect and diagnose ATTR-CM more accurately and promptly. Diagnosing ATTR-CM accurately and early can reduce morbidity and mortality rates through appropriate treatment.

Abstract Coronary computed tomography angiography (CCTA) derived machine learning fractional flow reserve (ML-FFRCT) can assess the hemodynamic significance of coronary artery stenoses. We aimed to assess sex differences in the association of ML-FFRCT and incident cardiovascular outcomes. We studied a retrospective cohort of consecutive patients who underwent clinically indicated CCTA and single photon emission computed tomography (SPECT). Obstructive stenosis was defined as ≥ 70% stenosis severity in non-left main vessels or ≥ 50% in the left main coronary. ML-FFRCT was computed using a machine learning algorithm with significant stenosis defined as ML-FFRCT

Abstract Patient-specific phenotyping of coronary atherosclerosis would facilitate personalized risk assessment and preventive treatment. We explored whether unsupervised cluster analysis can categorize patients with coronary atherosclerosis according to their plaque composition, and determined how these differing plaque composition profiles impact plaque progression. Patients with coronary atherosclerotic plaque (n = 947; median age, 62 years; 59% male) were enrolled from a prospective multi-national registry of consecutive patients who underwent serial coronary computed tomography angiography (median inter-scan duration, 3.3 years). K-means clustering applied to the percent volume of each plaque component and identified 4 clusters of patients with distinct plaque composition. Cluster 1 (n = 52), which comprised mainly fibro-fatty plaque with a significant necrotic core (median, 55.7% and 16.0% of the total plaque volume, respectively), showed the least total plaque volume (PV) progression (+ 23.3 mm3), with necrotic core and fibro-fatty PV regression (− 5.7 mm3 and − 5.6 mm3, respectively). Cluster 2 (n = 219), which contained largely fibro-fatty (39.2%) and fibrous plaque (46.8%), showed fibro-fatty PV regression (− 2.4 mm3). Cluster 3 (n = 376), which comprised mostly fibrous (62.7%) and calcified plaque (23.6%), showed increasingly prominent calcified PV progression (+ 21.4 mm3). Cluster 4 (n = 300), which comprised mostly calcified plaque (58.7%), demonstrated the greatest total PV increase (+ 50.7mm3), predominantly increasing in calcified PV (+ 35.9 mm3). Multivariable analysis showed higher risk for plaque progression in Clusters 3 and 4, and higher risk for adverse cardiac events in Clusters 2, 3, and 4 compared to that in Cluster 1. Unsupervised clustering algorithms may uniquely characterize patient phenotypes with varied atherosclerotic plaque profiles, yielding distinct patterns of progressive disease and outcome.

Since 1990, the U.S. News and World Report (USNWR) has been publishing rankings of US adult and children’s hospitals. The aim of this study was to analyze the association between hospital Twitter metrics and the 2020 USNWR hospital cardiology and heart surgery ranking. We collected data on the cardiology and heart surgery overall ranking score and expert opinion. Twitter metrics were obtained on October 20, 2020, and included time on Twitter, number of followers, accounts being followed, total tweets, reach score (difference between followers and followed), and annual tweet rate (total tweets divided by time on Twitter). The final cohort consisted of 463 hospitals (48 of which were top-ranking hospitals). A significant positive relation was observed with Twitter metrics and hospital ranking. On multivariable regression after adjusting for time on Twitter, the overall score was independently associated with annual tweet rate and reach score (β=12.45% and β=0.34% for each 1,000 tweets per year and 10,000 reach score accounts; P

Objective: To systematically review the literature and to estimate the risk of chloroquine (CQ) and hydroxychloroquine (HCQ) cardiac toxicity in patients with coronavirus disease 2019 (COVID-19). Methods: We searched multiple data sources including PubMed/MEDLINE, Ovid Embase, Ovid EBM Reviews, Scopus, and Web of Science and medrxiv.org from November 2019 through May 27, 2020. We included studies that enrolled patients with COVID-19 treated with CQ or HCQ, with or without azithromycin, and reported on cardiac toxic effects. We performed a meta-analysis using the arcsine transformation of the different incidences. Results: A total of 19 studies with a total of 5652 patients were included. The pooled incidence of torsades de pointes arrhythmia, ventricular tachycardia, or cardiac arrest was 3 per 1000 (95% CI, 0-21; I2=96%) in 18 studies with 3725 patients. Among 13 studies of 4334 patients, the pooled incidence of discontinuation of CQ or HCQ due to prolonged QTc or arrhythmias was 5% (95% CI, 1-11; I2=98%). The pooled incidence of change in QTc from baseline of 60 milliseconds or more or QTc of 500 milliseconds or more was 9% (95% CI, 3-17; I2=97%). Mean or median age, coronary artery disease, hypertension, diabetes, concomitant QT-prolonging medications, intensive care unit admission, and severity of illness in the study populations explained between-studies heterogeneity. Conclusion: Treatment of patients with COVID-19 with CQ or HCQ is associated with an important risk of drug-induced QT prolongation and relatively higher incidence of torsades de pointes, ventricular tachycardia, or cardiac arrest. Therefore, these agents should not be used routinely in the management of COVID-19 disease. Patients with COVID-19 who are treated with antimalarials for other indications should be adequately monitored.

Background: Middle Eastern (ME) immigrants are one of the fastest-growing groups in the US. Although ME countries have a high burden of atherosclerotic cardiovascular disease (ASCVD), the cardiovascular health status among ME immigrants in the US has not been studied in detail. This study aims to characterize the cardiovascular health status (CVD risk factors and ASCVD burden) among ME immigrants in the US. Methods: We used 2012–2018 data from the National Health Interview Survey, a US nationally representative survey. ME origin, CVD risk factors, and ASCVD status were self-reported. We compared these to US-born non-Hispanic white (NHW) individuals in the US. Results: Among 139,778 adults included, 886 (representing 1.3 million individuals, mean age 46.8) were of ME origin, and 138,892 were US-born NHWs (representing 150 million US adults, mean age 49.3). ME participants were more likely to have higher education, lower income and be uninsured. The age-adjusted prevalence of hypertension (22.4% vs 27.4%) and obesity (21.4% vs 31.4%) were significantly lower in ME vs NHW participants, respectively. There were no significant differences between the groups in the age-adjusted prevalence of ASCVD, diabetes, hyperlipidemia, and smoking. Only insufficient physical activity was higher among ME individuals. ME immigrants living in the US for 10 years or more reported higher age-adjusted prevalence of hypertension, hyperlipidemia, and ASCVD. Conclusions: ME immigrants in the US have lower odds of hypertension and obesity, and of having a suboptimal CRF profile compared to US-born NHWs. Further studies are needed to determine whether these findings are related to lower risk, selection of a healthier ME subgroup in NHIS, or possible under-detection of cardiovascular risk factors in ME immigrants living in the US.

Heart failure (HF) is the leading cause of morbidity and mortality worldwide and negatively impacts quality of life, healthcare costs, and longevity. Although data on HF in the Arab population are scarce, recently developed regional registries are a step forward to evaluating the quality of current patient care and providing an overview of the clinical picture. Despite the burden of HF in Saudi Arabia, there are currently no standardized protocols or guidelines for the management of patients with acute or chronic heart failure. Therefore, the Heart Failure Expert Committee, comprising 13 local specialists representing both public and private sectors, has developed guidelines to address the needs and challenges for the diagnosis and treatment of HF in Saudi Arabia. The ultimate aim of these guidelines is to assist healthcare professionals in delivering optimal care and standardized clinical practice across Saudi Arabia. Keywords: Acute heart failure, Chronic heart failure, Heart failure recommendations, Multidisciplinary management, Saudi Arabia

Abstract Background Although complex machine learning models are commonly outperforming the traditional simple interpretable models, clinicians find it hard to understand and trust these complex models due to the lack of intuition and explanation of their predictions. The aim of this study to demonstrate the utility of various model-agnostic explanation techniques of machine learning models with a case study for analyzing the outcomes of the machine learning random forest model for predicting the individuals at risk of developing hypertension based on cardiorespiratory fitness data. Methods The dataset used in this study contains information of 23,095 patients who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems between 1991 and 2009 and had a complete 10-year follow-up. Five global interpretability techniques (Feature Importance, Partial Dependence Plot, Individual Conditional Expectation, Feature Interaction, Global Surrogate Models) and two local interpretability techniques (Local Surrogate Models, Shapley Value) have been applied to present the role of the interpretability techniques on assisting the clinical staff to get better understanding and more trust of the outcomes of the machine learning-based predictions. Results Several experiments have been conducted and reported. The results show that different interpretability techniques can shed light on different insights on the model behavior where global interpretations can enable clinicians to understand the entire conditional distribution modeled by the trained response function. In contrast, local interpretations promote the understanding of small parts of the conditional distribution for specific instances. Conclusions Various interpretability techniques can vary in their explanations for the behavior of the machine learning model. The global interpretability techniques have the advantage that it can generalize over the entire population while local interpretability techniques focus on giving explanations at the level of instances. Both methods can be equally valid depending on the application need. Both methods are effective methods for assisting clinicians on the medical decision process, however, the clinicians will always remain to hold the final say on accepting or rejecting the outcome of the machine learning models and their explanations based on their domain expertise.

Introduction Higher cardiorespiratory fitness (CRF) is associated with improved exercise capacity and quality of life in heart failure with preserved ejection fraction (HFpEF), but there are no large studies evaluating the association of HFpEF, CRF, and long-term survival. We therefore aimed to determine the association between CRF and all-cause mortality, in patients with HFpEF. Material and methods In the Henry Ford Exercise Testing (FIT) Project, 167 patients had baseline HFpEF, defined as a clinical diagnosis of heart failure with ejection fraction ≥ 50% on echocardiogram. The CRF was estimated from the peak workload (in METs) from a clinician-referred treadmill stress test and categorized as poor (1–4 METs), intermediate (5–6 METs), and moderate-high (≥ 7 METs). Additional analyses assessing the effect of HFpEF and CRF on mortality were also conducted, matching HFpEF patients to non-HFpEF patients using propensity scores. Results Mean age was 64 ±13 years, with 55% women, and 46% Black. Over a median follow-up of 9.7 (5.2–18.9) years, there were 103 deaths. In fully adjusted models, moderate-high CRF was associated with 63% lower mortality risk (HR = 0.37, 95% CI: 0.18–0.73) compared to the poor-CRF group. In the propensity-matched cohort, HFpEF was associated with a HR of 2.3 (95% CI: 1.7–3.2) for mortality compared to non-HFpEF patients, which was attenuated to 1.8 (95% CI: 1.3–2.5) after adjusting for CRF. Conclusions Moderate-high CRF in patients with HFpEF is associated with improved survival, and differences in CRF partly explain the intrinsic risk of HFpEF. Randomized trials of interventions aimed at improving CRF in HFpEF are needed.

Introduction: Image noise can negatively affect the overall quality of coronary computed tomography angiography (CCTA). Objectives: The purpose of this study was to evaluate the relationship between image noise and fat volumes in the chest wall. We also aimed to compare these with other patient-specific predictors of image noise, such as body weight (BW) and body mass index (BMI). Methods: We undertook a cross-sectional, single-center study. A tube voltage of 100 kV was used for patients with BW 30 HU had significantly higher SFV (75 ± 33 vs. 51 ± 24, p

Background Coronary artery calcium (CAC) is a predictor for the development of cardiovascular disease (CVD) and to a lesser extent cancer. The age‐ and sex‐specific relationship of CAC with CVD and cancer mortality is unknown. Methods and Results Asymptomatic patients aged 40 to 75 years old without known CVD were included from the CAC Consortium. We calculated sex‐specific mortality rates per 1000 person‐years’ follow‐up. Using parametric survival regression modeling, we determined the age‐ and sex‐specific CAC score at which the risk of death from CVD and cancer were equal. Among the 59 502 patients included in this analysis, the mean age was 54.9 (±8.5) years, 34% were women, and 89% were white. There were 671 deaths attributable to CVD and 954 deaths attributable to cancer over a mean follow‐up of 12±3 years. Among patients with CAC=0, cancer was the leading cause of death, the total mortality rate was low (women, 1.8; men, 1.5), and the CVD mortality rate was exceedingly low for women (0.3) and men (0.3). The age‐specific CAC score at which the risk of CVD and cancer mortality were equal had a U‐shaped relationship for women, while the relationship was exponential for men. Conclusions The age‐ and sex‐specific relationship of CAC with CVD and cancer mortality differed significantly for women and men. Our age‐ and sex‐specific CAC score provides a more precise estimate and further facilitates the use of CAC as a synergistic tool in strategies for the prediction and prevention of CVD and cancer mortality.

Abstract Background Prior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardiovascular health. Machine learning (ML) can enhance the prediction of outcomes through classification techniques that classify the data into predetermined categories. The aim of this study is to present an evaluation and comparison of how machine learning techniques can be applied on medical records of cardiorespiratory fitness and how the various techniques differ in terms of capabilities of predicting medical outcomes (e.g. mortality). Methods We use data of 34,212 patients free of known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems Between 1991 and 2009 and had a complete 10-year follow-up. Seven machine learning classification techniques were evaluated: Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Networks (ANN), Naïve Bayesian Classifier (BC), Bayesian Network (BN), K-Nearest Neighbor (KNN) and Random Forest (RF). In order to handle the imbalanced dataset used, the Synthetic Minority Over-Sampling Technique (SMOTE) is used. Results Two set of experiments have been conducted with and without the SMOTE sampling technique. On average over different evaluation metrics, SVM Classifier has shown the lowest performance while other models like BN, BC and DT performed better. The RF classifier has shown the best performance (AUC = 0.97) among all models trained using the SMOTE sampling. Conclusions The results show that various ML techniques can significantly vary in terms of its performance for the different evaluation metrics. It is also not necessarily that the more complex the ML model, the more prediction accuracy can be achieved. The prediction performance of all models trained with SMOTE is much better than the performance of models trained without SMOTE. The study shows the potential of machine learning methods for predicting all-cause mortality using cardiorespiratory fitness data.

Background: Limited data exist on the epidemiology of cardiovascular risk factors in Saudi Arabia, particularly in relation to the differences between Saudi nationals and expatriates in Saudi Arabia. The aim of this analysis was to describe the current prevalence of cardiovascular risk factors among patients attending general practice clinics across Saudi Arabia. Methods: In this cross-sectional epidemiological analysis of the Africa Middle East Cardiovascular Epidemiological (ACE) study, the prevalence of cardiovascular risk factors (hypertension, diabetes, dyslipidemia, obesity, smoking, abdominal obesity) was evaluated in adults attending primary care clinics in Saudi Arabia. Group comparisons were made between patients of Saudi ethnicity (SA nationals) and patients who were not of Saudi ethnicity (expatriates). Results: A total of 550 participants were enrolled from different clinics across Saudi Arabia [aged (mean ± standard deviation) 43 ± 11 years; 71% male]. Nearly half of the study cohort (49.8%) had more than three cardiovascular risk factors. Dyslipidemia was the most prevalent risk factor (68.6%). The prevalence of hypertension (47.5%) and dyslipidemia (75.5%) was higher among expatriates when compared with SA nationals (31.4% vs. 55.1%, p = 0.0003 vs. p

BackgroundSeveral markers detected on the routine 12‐lead ECG are associated with future heart failure events. We examined whether these markers are able to separate the risk of heart failure with reduced ejection fraction (HFrEF) from heart failure with preserved ejection fraction (HFpEF). Methods and ResultsWe analyzed data of 6664 participants (53% female; mean age 62±10 years) from MESA (Multi‐Ethnic Study of Atherosclerosis) who were free of cardiovascular disease at baseline (2000–2002). A competing risks analysis was used to compare the association of several baseline ECG predictors with HFrEF and HFpEF detected during a median follow‐up of 12.1 years. A total of 127 HFrEF and 117 HFpEF events were detected during follow‐up. In a multivariable adjusted model, prolonged QRS duration, delayed intrinsicoid deflection, left‐axis deviation, right‐axis deviation, prolonged QT interval, abnormal QRS‐T axis, left ventricular hypertrophy, ST/T‐wave abnormalities, and left bundle‐branch block were associated with HFrEF. In contrast, higher resting heart rate, abnormal P‐wave axis, and abnormal QRS‐T axis were associated with HFpEF. The risk of HFrEF versus HFpEF was significantly differently for delayed intrinsicoid deflection (hazard ratio: 4.90 [95% confidence interval (CI), 2.77–8.68] versus 0.94 [95% CI, 0.29–2.97]; comparison P=0.013), prolonged QT interval (hazard ratio: 2.39 [95% CI, 1.55–3.68] versus 0.52 [95% CI, 0.23–1.19]; comparison P

Background The prognostic significance of modest elevations in exercise systolic blood pressure response has not been extensively examined. Methods and Results We examined the association between systolic blood pressure response and all‐cause death and incident myocardial infarction (MI) in 44 089 (mean age 53±13 years, 45% female, 26% black) patients who underwent exercise treadmill stress testing from the Henry Ford ExercIse Testing (FIT) Project (1991–2010). Exercise systolic blood pressure response was examined as a categorical variable (>20 mm Hg: referent; 1 to 20 mm Hg, and ≤0 mm Hg) and per 1 SD decrease. Cox regression was used to compute hazard ratios (HR) and 95% CI for the association between systolic blood pressure response and all‐cause death and incident MI. Over a median follow‐up of 10 years, a total of 4782 (11%) deaths occurred and over 5.2 years, a total of 1188 (2.7%) MIs occurred. In a Cox regression analysis adjusted for demographics, physical fitness, and cardiovascular risk factors, an increased risk of death was observed with decreasing systolic blood pressure response (>20 mm Hg: HR=1.0, referent; 1 to 20 mm Hg: HR=1.13, 95% CI=1.05, 1.22; ≤0 mm Hg: HR=1.21, 95% CI=1.09, 1.34). A trend for increased MI risk was observed (>20 mm Hg: HR=1.0, referent; 1 to 20 mm Hg: HR=1.09, 95% CI=0.93, 1.27; ≤0 mm Hg: HR=1.19, 95% CI=0.95, 1.50). Decreases in systolic blood pressure response per 1 SD were associated with an increased risk for all‐cause death (HR=1.08, 95% CI=1.05, 1.11) and incident MI (HR=1.09, 95% CI=1.03, 1.16). Conclusions Our results suggest that modest increases in exercise systolic blood pressure response are associated with adverse outcomes.

Clinical Research. Presentation type: Oral Presentation. Introduction: Frailty is a state of vulnerability and decreased physiological response to stressors. Saudi vision 2030 stated a goal to increase Saudi life expectancy by 5 years. As the population ages, the prevalence of frailty is expected to increase. Thus, identifying tools and resources that efficiently reduces frailty among elderly patients is important. We aim to describe the prevalence and predictors of frailty among Saudi patients referred for stress testing with nuclear imaging. Methodology: We included 876 patients (mean age 60.28 ± 11, females 48.29%) who underwent clinically indicated nuclear myocardial perfusion imaging using PET between January and October 2016. The Canadian Study of Health and Ageing Clinical Frailty Scale was used to assess frailty. Patients were considered frail if they had a score of four or higher. Multivariate adjusted logistic regression model was used to determine the independent predictors of elderly frail patients. Results: In this cohort, the median age of the included patients was 61 years and the prevalence of the frailty was 40%. The frail patients were older, more frequently females and had a higher body mass index. Additionally, frailty was associated with higher prevalence of cardiovascular risk factors: hypertension, diabetes and dyslipidaemia (85%, 75%, and 46%, respectively). In fully adjusted logistic regression model, female gender, high body mass index (⩾30 kg/m2), hypertension and reduced coronary flow reserve were independent predictors of elderly frail patients. Conclusion: With the aging of the Saudi population, frailty prevalence is expected to increase. Elderly obese hypertensive females have the highest risk of developing frailty. Interventions to reduce frailty should be focused on this high-risk population.