FIT calculator: a multi-risk prediction framework for medical outcomes using cardiorespiratory fitness data.

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.

An interpretable semi-supervised framework for patch-based classification of breast cancer.

Developing effective invasive Ductal Carcinoma (IDC) detection methods remains a challenging problem for breast cancer diagnosis. Recently, there has been notable success in utilizing deep neural networks in various application domains; however, it is well-known that deep neural networks require a large amount of labelled training data to achieve high accuracy. Such amounts of manually labelled data are time-consuming and expensive, especially when domain expertise is required. To this end, we present a novel semi-supervised learning framework for IDC detection using small amounts of labelled training examples to take advantage of cheap available unlabeled data. To gain trust in the prediction of the framework, we explain the prediction globally. Our proposed framework consists of five main stages: data augmentation, feature selection, dividing co-training data labelling, deep neural network modelling, and the interpretability of neural network prediction. The data cohort used in this study contains digitized BCa histopathology slides from 162 women with IDC at the Hospital of the University of Pennsylvania and the Cancer Institute of New Jersey. To evaluate the effectiveness of the deep neural network model used by the proposed approach, we compare it to different state-of-the-art network architectures; AlexNet and a shallow VGG network trained only on the labelled data. The results show that the deep neural network used in our proposed approach outperforms the state-of-the-art techniques achieving balanced accuracy of 0.73 and F-measure of 0.843. In addition, we compare the performance of the proposed semi-supervised approach to state-of-the-art semi-supervised DCGAN technique and self-learning technique. The experimental evaluation shows that our framework outperforms both semi-supervised techniques and detects IDC with an accuracy of 85.75%, a balanced accuracy of 0.865, and an F-measure of 0.773 using only 10% labelled instances from the training dataset while the rest of the training dataset is treated as unlabeled.

Exploiting time series of Sentinel-1 and Sentinel-2 to detect grassland mowing events using deep learning with reject region.

Governments pay agencies to control the activities of farmers who receive governmental support. Field visits are costly and highly time-consuming; hence remote sensing is widely used for monitoring farmers' activities. Nowadays, a vast amount of available data from the Sentinel mission significantly boosted research in agriculture. Estonia is among the first countries to take advantage of this data source to automate mowing and ploughing events detection across the country. Although techniques that rely on optical data for monitoring agriculture events are favourable, the availability of such data during the growing season is limited. Thus, alternative data sources have to be evaluated. In this paper, we developed a deep learning model with an integrated reject option for detecting grassland mowing events using time series of Sentinel-1 and Sentinel-2 optical images acquired from 2000 fields in Estonia in 2018 during the vegetative season. The rejection mechanism is based on a threshold over the prediction confidence of the proposed model. The proposed model significantly outperforms the state-of-the-art technique and achieves event accuracy of 73.3% and end of season accuracy of 94.8%.

Cardiorespiratory Fitness and Incident Stroke Types: The FIT (Henry Ford ExercIse Testing) Project.

OBJECTIVE: To study the association between cardiorespiratory fitness (CRF) and incident stroke types. PATIENTS AND METHODS: We studied a retrospective cohort of patients referred for treadmill stress testing in the Henry Ford Health System (Henry Ford ExercIse Testing Project) without history of stroke. CRF was expressed by metabolic equivalents of task (METs). Using appropriate International Classification of Diseases, Ninth Revision codes, incident stroke was ascertained through linkage with administrative claims files and classified as ischemic, hemorrhagic, and subarachnoid hemorrhage (SAH). Multivariable-adjusted Cox proportional hazards models examined the association between CRF and incident stroke. RESULTS: Among 67,550 patients, mean ± SD age was 54±13 years, 46% (n=31,089) were women, and 64% (n=43,274) were white. After a median follow-up of 5.4 (interquartile range 2.7-8.5) years, a total of 7512 incident strokes occurred (6320 ischemic, 2481 hemorrhagic, and 275 SAH). Overall, there was a graded lower incidence of stroke with higher MET categories. Patients with METs of 12 or more had lower risk of overall stroke [0.42 (95% CI, 0.36-0.49)], ischemic stroke [0.69 (95% CI, 0.58-0.82)], and hemorrhagic stroke [0.71 (95% CI, 0.52-0.95)]. CONCLUSION: In a large ethnically diverse cohort of patients referred for treadmill stress testing, CRF is inversely associated with risk for ischemic and hemorrhagic stroke.

Cardiac magnetic resonance imaging for assessment of mitral stenosis before and after percutaneous balloon valvuloplasty in comparison to two- and three-dimensional echocardiography.

BACKGROUND: The experience with cardiac magnetic resonance (CMR) in mitral stenosis (MS) is limited in contrast to mitral regurgitation. PURPOSE: To compare CMR versus 2D and 3D transthoracic (TTE) and 3D transesophgeal (TEE) echocardiography in assessment of rheumatic MS before and after percutaneous balloon mitral valvuloplasty (PBMV). MATERIAL AND METHODS: Twenty consecutive symptomatic patients with MS were evaluated prospectively and independently by CMR, TTE, and TEE pre-PBMV, and by CMR and TTE post-PBMV. Mitral valve area (MVA) was assessed by CMR planimetry, TTE and TEE planimetry, and pressure half time (PHT). Further assessment included trans-mitral velocity, mitral regurgitation (MR), and left atrial (LA) volume. RESULTS: PBMV was successful in 18 patients and failed in two patients (one with MVA <1.5 cm2, one developed severe MR). Pre-PBMV and MVA by CMR, 2D TTE, biplane, 3D TTE, 3D TEE, and PHT were 1.16, 1.16, 1.10, 1.02, 1.05, and 0.99 cm2, respectively. Post-PBMV, a significant increase in MVA was observed (2.15, 2.06, 2.07, 2.04, and 2.03 cm2, respectively). High agreement was observed between CMR and echocardiography before and after PBMV, except for PHT method. CMR significantly underestimated trans-mitral velocity and gradients compared to echocardiography (P<0.001). Before PBMV, mild MR was observed in 11, 12, and 19 patients by 2D TTE, 3D TTE, and CMR. After PBMV, MR was observed in all patients (19 mild, one severe) by all modalities. Echocardiography significantly underestimated LA volume compared to CMR (P<0.001). LA volume decreased significantly after PBMV (P<0.001). CONCLUSION: CMR provides comprehensive assessment of several parameters in MS patients before and after intervention. Agreement with echocardiography is acceptable.

On the interpretability of machine learning-based model for predicting hypertension.

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.

The Interplay of the Global Atherosclerotic Cardiovascular Disease Risk Scoring and Cardiorespiratory Fitness for the Prediction of All-Cause Mortality and Myocardial Infarction: The Henry Ford ExercIse Testing Project (The FIT Project).

Cardiorespiratory fitness (CRF) is inversely associated with atherosclerotic cardiovascular disease (ASCVD) risk. It is unclear whether the prognostic value of CRF differs by baseline estimated ASCVD risk. We studied a retrospective cohort of patients without known heart failure or myocardial infarction (MI) who underwent treadmill stress testing. CRF was measured by metabolic equivalents of task (METs) and ASCVD risk was calculated using the Pooled Cohorts Equations. Multivariable-adjusted Cox regressions analyses examined the association between METs and incident all-cause mortality and MI outcomes stratified by baseline ASCVD risk. The C-index evaluated risk discrimination while net reclassification improvement evaluated reclassification with CRF added to the ASCVD risk score. Our study population consisted of 57,999 patients of mean age 53 (13) years, 49% women, 64% white, 29% black. Over a median follow-up 11 years (interquartile range 8 to 14 years) there were 6,670 (11%) deaths, while there were 1,757 (3.0%) MIs over a median follow-up of 6 years (interquartile range 3 to 8 years). Among patients with ASCVD risk ≥20%, those with METs ≥12 had a 77% lower risk of all-cause mortality (Hazard ratio 0.23 95% confidence interval = 0.20, 0.27) and 67% lower risk of MI (Hazard ratio 0.33 95% confidence interval = 0.24, 0.46) compared to METs <6. Similar results were obtained for those with ASCVD risk <5%. Addition of METs to ASCVD risk score improved the C-statistic from 0.778 to 0.798 for all-cause mortality and 0.726 to 0.733 for MI (both p <0.001). Addition of METs to ASCVD risk score significantly reclassified risk of all-cause mortality (p <0.001) but not MI (p = 0.052). In conclusion, CRF is inversely associated with risk of all-cause mortality and MI at all levels of ASCVD risk, and provides incremental risk discrimination and reclassification beyond the ASCVD risk score.

Predictors of in-hospital length of stay among cardiac patients: A machine learning approach.

OBJECTIVE: The In-hospital length of stay (LOS) is expected to increase as cardiovascular diseases complexity increases and the population ages. This will affect healthcare systems especially with the current situation of decreased bed capacity and increasing costs. Therefore, accurately predicting LOS would have a positive impact on healthcare metrics. The aim of this study is to develop a machine learning-based model approach for predicting in-hospital LOS for cardiac patients. DESIGN: Using electronic medical records, we retrospectively extracted all records of patients' visits that were admitted under adult cardiology service. Admission diagnosis and primary treating physician were reviewed to verify selection criteria. A predictive machine learning-based model approach was applied to incorporate simple baseline health data at admission time to predict LOS. Patients were divided into three groups based on their LOS: short (<3 days), intermediate (3-5 days) and long (>5 days). Information gain algorithm was utilized to select the most relevant attributes. Only attributes with information gain of more than zero were used in model building. Four different machine learning techniques were evaluated and their diagnostic accuracy measures were compared. SETTING: The dataset of this study included adult patients who were admitted between 2008 and 2016 in King Abdulaziz Cardiac Center (KACC). The center is located in King Abdulaziz Medical City Complex in Riyadh, the capital of Saudi Arabia. PARTICIPANTS (DATASET): A total of 16,414 consecutive inpatient visits for 12,769 unique patients (mean age of 58.8 ±â€¯16 years of which 68.2% were males) between 2008 and 2016 were included. The study cohort had a high prevalence of cardiovascular risk factors (hypertension 56%, diabetes 56%, dyslipidemia 52%, obesity 33% and smoking 24%). The most common admitting diagnosis was acute coronary syndrome (36%). RESULTS: The variables with highest impact on the prediction of in-hospital LOS were on admission heart rate, on admission systolic and diastolic blood pressure, age and insurance status (eligibility). Using machine learning models; Random Forest (RF) model outperformed among all other models (sensitivity (0.80), accuracy (0.80), and AUROC (0.94)). CONCLUSION: We showed that machine learning methods provide accurate prediction of LOS for cardiac patients. This is can be used in clinical bed management and resources allocation.

Prognostic value of exercise capacity among patients with treated depression: The Henry Ford Exercise Testing (FIT) Project.

BACKGROUND: Exercise capacity is associated with survival in the general population. Whether this applies to patients with treated depression is not clear. HYPOTHESIS: High exercise capacity remains associated with lower risk of all-cause mortality (ACM) and nonfatal myocardial infraction (MI) among patients with treated depression. METHODS: We included 5128 patients on antidepressant medications who completed a clinically indicated exercise stress test between 1991 and 2009. Patients were followed for a median duration of 9.4 years for ACM and 4.5 years for MI. Exercise capacity was estimated in metabolic equivalents of tasks (METs). Cox proportional hazards regression models were used. RESULTS: Patients with treated depression who achieved ≥12 METs (vs those achieving <6 METs) were younger (age 46 ± 9 vs 61 ± 12 years), more often male (60% vs 23%), less often black (10% vs 27%), and less likely to be hypertensive (51% vs 86%), have DM (9% vs 38%), or be obese (11% vs 36%) or dyslipidemic (45% vs 54%). In the fully adjusted Cox proportional hazard regression model, exercise capacity was associated with a lower ACM (HR per 1-MET increase in exercise capacity: 0.82, 95% CI: 0.79-0.85, P < 0.001) and nonfatal MI (HR: 0.92, 95% CI: 0.87-0.97, P = 0.004). CONCLUSIONS: Exercise capacity had an inverse association with both ACM and nonfatal MI in patients with treated depression, independent of cardiovascular risk factors. These results highlight the potential impact of assessing exercise capacity to identify risk, as well as promoting an active lifestyle among treated depression patients.

Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford ExercIse Testing (FIT) Project.

This study evaluates and compares the performance of different machine learning techniques on predicting the individuals at risk of developing hypertension, and who are likely to benefit most from interventions, using the cardiorespiratory fitness data. The dataset of 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. The variables of the dataset include information on vital signs, diagnosis and clinical laboratory measurements. Six machine learning techniques were investigated: LogitBoost (LB), Bayesian Network classifier (BN), Locally Weighted Naive Bayes (LWB), Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Tree Forest (RTF). Using different validation methods, the RTF model has shown the best performance (AUC = 0.93) and outperformed all other machine learning techniques examined in this study. The results have also shown that it is critical to carefully explore and evaluate the performance of the machine learning models using various model evaluation methods as the prediction accuracy can significantly differ.

Cardiorespiratory Fitness and Cardiovascular Disease Prevention: an Update.

PURPOSE OF REVIEW: Cardiovascular diseases account for nearly one third of all deaths globally. Improving exercise capacity and cardiorespiratory fitness (CRF) has been an important target to reduce cardiovascular events. In addition, the American Heart Association defined decreased physical activity as the fourth risk factor for coronary artery disease. Multiple large cohort studies have evaluated the impact of CRF on outcomes. In this review, we will discuss the role of CRF in reducing cardiovascular morbidity and mortality. RECENT FINDINGS: Recent data suggest that CRF has an important role in reducing not only cardiovascular and all-cause mortality, but also incident myocardial infarction, hypertension, diabetes, atrial fibrillation, heart failure, and stroke. Most recently, its role in cancer prevention started to emerge. CRF protective effects have also been seen in patients with prior comorbidities like prior coronary artery disease, heart failure, depression, end-stage renal disease, and stroke. The prognostic value of CRF has been demonstrated in various patient populations and cardiovascular conditions. Higher CRF is associated with improved survival and decreased incidence of cardiovascular diseases (CVD) and other comorbidities including hypertension, diabetes, heart failure, and atrial fibrillation.

Comparison of machine learning techniques to predict all-cause mortality using fitness data: the Henry ford exercIse testing (FIT) project.

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.

Using Machine Learning to Define the Association between Cardiorespiratory Fitness and All-Cause Mortality (from the Henry Ford Exercise Testing Project).

Previous studies have demonstrated that cardiorespiratory fitness 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 the analysis is to compare the prediction of 10 years of all-cause mortality (ACM) using statistical logistic regression (LR) and ML approaches in a cohort of patients who underwent exercise stress testing. We included 34,212 patients (55% males, mean age 54 ± 13 years) free of coronary artery disease or heart failure who underwent exercise treadmill stress testing between 1991 and 2009 and had complete 10-year follow-up. The primary outcome of this analysis was ACM at 10 years. The probability of 10-years ACM was calculated using statistical LR and ML, and the accuracy of these methods was calculated and compared. A total of 3,921 patients died at 10 years. Using statistical LR, the sensitivity to predict ACM was 44.9% (95% confidence interval [CI] 43.3% to 46.5%), whereas the specificity was 93.4% (95% CI 93.1% to 93.7%). The sensitivity of ML to predict ACM was 87.4% (95% CI 86.3% to 88.4%), whereas the specificity was 97.2% (95% CI 97.0% to 97.4%). The ML approach was associated with improved model discrimination (area under the curve for ML [0.923 (95% CI 0.917 to 0.928)]) compared with statistical LR (0.836 [95% CI 0.829 to 0.846], p<0.0001). In conclusion, our analysis demonstrates that ML provides better accuracy and discrimination of the prediction of ACM among patients undergoing stress testing.

Predicting diabetes mellitus using SMOTE and ensemble machine learning approach: The Henry Ford ExercIse Testing (FIT) project.

Machine learning is becoming a popular and important approach in the field of medical research. In this study, we investigate the relative performance of various machine learning methods such as Decision Tree, Naïve Bayes, Logistic Regression, Logistic Model Tree and Random Forests for predicting incident diabetes using medical records of cardiorespiratory fitness. In addition, we apply different techniques to uncover potential predictors of diabetes. This FIT project study used data of 32,555 patients who are free of any 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 5-year follow-up. At the completion of the fifth year, 5,099 of those patients have developed diabetes. The dataset contained 62 attributes classified into four categories: demographic characteristics, disease history, medication use history, and stress test vital signs. We developed an Ensembling-based predictive model using 13 attributes that were selected based on their clinical importance, Multiple Linear Regression, and Information Gain Ranking methods. The negative effect of the imbalance class of the constructed model was handled by Synthetic Minority Oversampling Technique (SMOTE). The overall performance of the predictive model classifier was improved by the Ensemble machine learning approach using the Vote method with three Decision Trees (Naïve Bayes Tree, Random Forest, and Logistic Model Tree) and achieved high accuracy of prediction (AUC = 0.92). The study shows the potential of ensembling and SMOTE approaches for predicting incident diabetes using cardiorespiratory fitness data.

Cardiorespiratory fitness and incident heart failure: The Henry Ford ExercIse Testing (FIT) Project.

BACKGROUND: Prior studies have demonstrated cardiorespiratory fitness (CRF) to be a strong marker of cardiovascular health. However, there are limited data investigating the association between CRF and risk of progression to heart failure (HF). The purpose of this study was to determine the relationship between CRF and incident HF. METHODS: We included 66,329 patients (53.8% men, mean age 55 years) free of HF who underwent exercise treadmill stress testing at Henry Ford Health Systems between 1991 and 2009. Incident HF was determined using International Classification of Diseases, Ninth Revision codes from electronic medical records or administrative claim files. Cox proportional hazards models were performed to determine the association between CRF and incident HF. RESULTS: A total of 4,652 patients developed HF after a median follow-up duration of 6.8 (±3) years. Patients with incident HF were older (63 vs 54 years, P<.001) and had higher prevalence of known coronary artery disease (42.3% vs 11%, P<.001). Peak metabolic equivalents (METs) of task were 6.3 (±2.9) and 9.1 (±3) in the HF and non-HF groups, respectively. After adjustment for potential confounders, patients able to achieve ≥12 METs had an 81% lower risk of incident HF compared with those achieving <6 METs (hazard ratio 0.19 [95% CI 0.14-0.29], P for trend < .001). Each 1 MET achieved was associated with a 16% lower risk (hazard ratio 0.84 [95% CI 0.82-0.86], P<.001) of incident HF. CONCLUSIONS: Our analysis demonstrates that higher level of fitness is associated with a lower incidence of HF independent of HF risk factors.

Higher Fitness Is Strongly Protective in Patients with Family History of Heart Disease: The FIT Project.

BACKGROUND: Cardiorespiratory fitness protects against mortality; however, little is known about the benefits of improved fitness in individuals with a family history of coronary heart disease. We studied the association between cardiorespiratory fitness and risk of incident coronary heart disease and all-cause mortality, hypothesizing an inverse relationship similar to individuals without a family history of coronary heart disease. METHODS: We included 57,999 patients (aged 53 ± 13 years; 49% were female; 29% were black) from the Henry Ford Exercise Testing (FIT) Project. Cardiorespiratory fitness was expressed in metabolic equivalents of task based on exercise stress testing. Family history was determined as self-reported coronary heart disease in a first-degree relative at any age. We used Cox proportional hazards models adjusted for demographics and cardiovascular disease risk factors to examine the association between cardiorespiratory fitness and risk of incident coronary heart disease and mortality over a median (interquartile range) follow-up of 5.5 (5.6) and 10.4 (6.8) years, respectively. RESULTS: Overall, 51% reported a positive family history. Each 1-unit metabolic equivalent increase was associated with lower incident coronary heart disease and mortality risk regardless of family history status. The hazard ratio and 95% confidence interval for a negative family history and a positive family history were 0.87 (0.84-0.89) and 0.87 (0.85-0.89) for incident coronary heart disease and 0.83 (0.82-0.84) and 0.83 (0.82-0.85) for mortality, respectively. There was no significant interaction between family history and categoric cardiorespiratory fitness, sex, or age (P >.05 for all). CONCLUSIONS: Higher cardiorespiratory fitness is strongly protective in all patients regardless of family history status, supporting recommendations for regular exercise in those with a family history.

The impact of digoxin on mortality in patients with chronic systolic heart failure: A propensity-matched cohort study.

BACKGROUND: Prior Studies showed mixed results in association of digoxin use with all-cause mortality (ACM). The aim of this analysis is to identify the impact of digoxin use on ACM in a contemporary heart failure (HF) cohort treated with guideline based therapy. METHODS: We included 2298 consecutive patients seen in an HF clinic between 2000 and 2015. Patients were considered to be a digoxin user if he/she received digoxin at any point during the enrollment period in the HF clinic. Patients were matched based on digoxin utility using propensity matching in 2-3:1 fashion. The primary outcome was ACM. RESULT: Of 2298 patients, 325 digoxin users were matched with 750 non-digoxin users. The Matched cohort did not have differences among demographics and clinical variables except for worse HF symptomatology and increased prevalence of atrial fibrillation. Overall, the prevalence of the use of guideline suggested therapies was 96%. After a median follow-up duration of 4years (IQR 2-6years), digoxin use was associated with increased ACM (21.8% versus 12.9%, unadjusted HR=1.81; 95% CI=1.33 to 2.45; p=0.001). This association remained significant after adjusting for the propensity score, atrial fibrillation, ejection fraction, and New York HF Class (HR=1.74; 95% CI=1.20 to 2.38; p<0.0001). CONCLUSION: In this analysis of well-treated HF patients, digoxin was associated with increased ACM. Further randomized controlled trials are needed to determine whether digoxin therapy should be used in well-treated HF patients. Until then, routine use of digoxin in clinical practice should be discouraged.

A distributed query execution engine of big attributed graphs.

A graph is a popular data model that has become pervasively used for modeling structural relationships between objects. In practice, in many real-world graphs, the graph vertices and edges need to be associated with descriptive attributes. Such type of graphs are referred to as attributed graphs. G-SPARQL has been proposed as an expressive language, with a centralized execution engine, for querying attributed graphs. G-SPARQL supports various types of graph querying operations including reachability, pattern matching and shortest path where any G-SPARQL query may include value-based predicates on the descriptive information (attributes) of the graph edges/vertices in addition to the structural predicates. In general, a main limitation of centralized systems is that their vertical scalability is always restricted by the physical limits of computer systems. This article describes the design, implementation in addition to the performance evaluation of DG-SPARQL, a distributed, hybrid and adaptive parallel execution engine of G-SPARQL queries. In this engine, the topology of the graph is distributed over the main memory of the underlying nodes while the graph data are maintained in a relational store which is replicated on the disk of each of the underlying nodes. DG-SPARQL evaluates parts of the query plan via SQL queries which are pushed to the underlying relational stores while other parts of the query plan, as necessary, are evaluated via indexless memory-based graph traversal algorithms. Our experimental evaluation shows the efficiency and the scalability of DG-SPARQL on querying massive attributed graph datasets in addition to its ability to outperform the performance of Apache Giraph, a popular distributed graph processing system, by orders of magnitudes.

Association between left atrial appendage morphology evaluated by trans-esophageal echocardiography and ischemic cerebral stroke in patients with atrial fibrillation.

The left atrial appendage (LAA) represents one of the major sources of cardiac thrombi responsible for embolic stroke in patients with atrial fibrillation (AF). The aim of the present study was to evaluate LAA structure and functions by transesophageal echocardiography (TEE) in patients with AF to investigate the possible association between the different LAA morphologies and the patients' history of ischemic cerebral stroke. We included 50 patients with non-valvular AF (29 chronic, 21 paroxysmal), 24 patients (13 men) without stroke; and 26 patients (9 men) with a history of ischemic stroke. All patients underwent TEE evaluation of LAA morphology and functions. Compared to patients without stroke, patients with ischemic stroke had significantly higher CHADS2 scores (4.19 ± 0.89 versus 1.67 ± 1.13; P < 0.001) and C-reactive protein levels (8.3 ± 1.6 versus 7.6 ± 0.83 mg/L; P = 0.023), and lower peak filling (21.7 ± 11.3 versus 31.2 ± 9.5 cm/second; P = 0.033) and emptying (22.2 ± 9.7 versus 33.4 ± 13.4 cm/second, P = 0.030) velocities. Triangular LAA morphology had a higher prevalence in patients with stroke (36% versus 12% in non-stroke group); and in half of them an LAA thrombus was present. LAA thrombi were detected in 9 patients (18%) with stroke and in 5 patients (10%) without stroke. On multivariate logistic regression analysis, age (OR = 1.202 [1.042-1.585]; P = 0.041), LAA orifice diameter (OR = 1.275 [1.102-1.748]; P = 0.028), and triangular LAA morphology (OR = 4.53 [1.629-8.381]; P = 0.011) were significantly and independently associated with ischemic stroke in AF patients. LAA morphology evaluated by TEE may be useful for predicting ischemic cerebral stroke in patients with non-valvular AF, especially in those with a low CHADS2 score.