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.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Atrial fibrillation (AF) is a significant health care problem for patients with obstructive sleep apnea (OSA). Continuous positive airway pressure (CPAP) as a therapy for OSA is underused, and it is ...unknown if CPAP might reduce rates of AF. We systematically reviewed the published reports on CPAP use and risk of AF. MEDLINE, EMBASE, CINAHL, Web of Science, meeting abstracts, and Cochrane databases were searched from inception to June 2015. Studies needed to report the rates of AF in participants who were and were not on CPAP. Data were extracted by 2 authors. A total of 8 studies on OSA were identified (1 randomized controlled trial) with 698 CPAP users and 549 non-CPAP users. In a random effects model, patients treated with CPAP had a 42% decreased risk of AF (pooled risk ratio, 0.58; 95% confidence interval, 0.47 to 0.70; p <0.001). There was low heterogeneity in the results ( I2 = 30%). In metaregression analysis, benefits of CPAP were stronger for younger, obese, and male patients (p <0.05). An inverse relationship between CPAP therapy and AF recurrence was observed. Results suggest that more patients with AF also should be tested for OSA.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Data regarding the outcomes of restarting anticoagulation in patients who develop gastrointestinal bleeding (GIB) while anticoagulated are sparse. We hypothesized that restarting anticoagulation in ...these patients is associated with better outcomes. This is a retrospective cohort study that enrolled subjects who developed GIB while on anticoagulation from 2005 to 2010. Atrial fibrillation was defined by history and electrocardiography on presentation. GIB was defined as a decrease in hemoglobin by 2 g, visible bleeding, or positive endoscopic evaluation. Time-to-event adjusted analyses were performed to find an association of restarting warfarin and recurrent GIB, arterial thromboembolism, and mortality. Stratified analysis by duration of interruption of warfarin was also performed. Overall, 1,329 patients (mean age 76 years, women 45%) developed major GIB. Warfarin was restarted in 653 cases (49.1%). Restarting warfarin was associated with decreased thromboembolism (hazard ratio HR 0.71, 95% confidence interval CI 0.54 to 0.93, p = 0.01) and reduced mortality (HR 0.67, 95% CI 0.56 to 0.81, p <0.0001) but not recurrent GIB (HR 1.18, 95% CI 0.94 to 1.10, p = 0.47). When the outcomes were stratified by duration of warfarin interruption, restarting warfarin after 7 days was not associated with increased risk of GIB but was associated with decreased risk of mortality and thromboembolism compared with resuming after 30 days of interruption. Decision to restart warfarin after an episode of major GIB is associated with improved survival and decreased thromboembolism without increased risk of GIB after 7 days of interruption.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
BACKGROUND—Poor cardiorespiratory fitness (CRF) is an independent risk factor for cardiovascular morbidity and mortality. However, the relationship between CRF and atrial fibrillation (AF) is less ...clear. The aim of this analysis was to investigate the association between CRF and incident AF in a large, multiracial cohort that underwent graded exercise treadmill testing.
METHODS AND RESULTS—From 1991 to 2009, a total of 64 561 adults (mean age, 54.5±12.7 years; 46% female; 64% white) without AF underwent exercise treadmill testing at a tertiary care center. Baseline demographic and clinical variables were collected. Incident AF was ascertained by use of International Classification of Diseases, Ninth Revision code 427.31 and confirmed by linkage to medical claim files. Nested, multivariable Cox proportional hazards models were used to estimate the independent association of CRF with incident AF. During a median follow-up of 5.4 years (interquartile range, 3–9 years), 4616 new cases of AF were diagnosed. After adjustment for potential confounders, 1 higher metabolic equivalent achieved during treadmill testing was associated with a 7% lower risk of incident AF (hazard ratio, 0.93; 95% confidence interval, 0.92–0.94; P<0.001). This relationship remained significant after adjustment for incident coronary artery disease (hazard ratio, 0.92; 95% confidence interval, 0.91–0.93; P<0.001). The magnitude of the inverse association between CRF and incident AF was greater among obese compared with nonobese individuals (P for interaction=0.02).
CONCLUSIONS—There is a graded, inverse relationship between cardiorespiratory fitness and incident AF, especially among obese patients. Future studies should examine whether changes in fitness increase or decrease risk of atrial fibrillation. This association was stronger for obese compared with nonobese, especially among obese patients.
Whether very young patients (≤35-year-old) differ in the prevalence, presentation and prognosis of ACS is not well known. Of 43,446 patients who were referred to a tertiary care cardiac ...catheterization laboratory between January 1, 2006 and June 30, 2017, 26,545 patients were ACS (defined as ST Elevation MI, Non-ST Elevation MI or unstable angina pectoris). Detailed chart review was performed and characteristics at baseline were compared for ages ≤35 years, ages 36 to 54 years and ages ≥55 years. A total of 291 (1.1%) were ≤35-year-old, 7,649 (28.8) were 36 to 54-year-old and 18,605 (70.1%) were ≥55-year-old. ACS patients aged ≤35-year-old, were more likely to be men, Caucasian white, smoker, obese, and have family history of coronary artery disease and less likely to have comorbidities such as hypertension, diabetes mellitus, and hyperlipidemia compared with older patients. They were also more likely to present with elevated troponin levels than other groups. They also tended to present with late ST elevation myocardial infarction and were more likely to receive bare metal stents than older patients. The prevalence of 2- and 3-vessel disease was lower compared with older patients. They also had higher prevalence of cardiogenic shock. Compared with 36 to 54-year-old patients, ≤35-year-old were at significant higher risk of 30-day mortality in a multivariable adjusted regression model (Odds ratio 5.65, 95% confidence interval 2.49 to 12.82, p <0.001). Very young patients comprised ∼1% of all ACS cases but had much more prevalence of modifiable risk factors and significantly worse mortality. Modifying these risk factors may mitigate the risk in these patients and should be studied in the future.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Atrial fibrillation (AF) is common in patients with life-threatening cancer and those undergoing active cancer treatment. However, data from subjects with a history of non–life-threatening cancer and ...those who do not require active cancer treatment are lacking. A total of 15,428 (mean age 66 ± 8.9 years; 47% women; 45% blacks) participants from the REasons for Geographic And Racial Differences in Stroke (REGARDS) study with baseline data on previous cancer diagnosis and AF were included. Participants with life-threatening cancer and active cancer treatment within 2 years of study enrollment were excluded. History of cancer was identified using computer-assisted telephone interviews. AF cases were identified from baseline electrocardiogram data and by a self-reported history of a previous diagnosis. Logistic regression was used to examine the cross-sectional association between cancer diagnosis and AF. A total of 2,248 (15%) participants had a diagnosis of cancer and 1,295 (8.4%) had AF. In a multivariable logistic regression model adjusted for sociodemographic characteristics (age, gender, race, education, income, and region of residence) and cardiovascular risk factors (systolic blood pressure, high-density lipoprotein cholesterol, total cholesterol, C-reactive protein, body mass index, smoking, diabetes, antihypertensive and lipid-lowering agents, left ventricular hypertrophy, and cardiovascular disease), those with cancer were more likely to have prevalent AF than those without cancer (odds ratio 1.19, 95% confidence interval 1.02 to 1.38). Subgroup analyses by age, sex, race, cardiovascular disease, and C-reactive protein yielded similar results. In conclusion, AF was more prevalent in participants with a history of non–life-threatening cancer and those who did not require active cancer treatment in REGARDS.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
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).
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.
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.
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.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Background
Limited epidemiological data are available on the outcomes of in‐hospital cardiac arrest (CA) in COVID‐19 patients.
Methods
We performed literature search of PubMed, EMBASE, Cochrane, and ...Ovid to identify research articles that studied outcomes of in‐hospital cardiac arrest in COVID‐19 patients. The primary outcome was survival at discharge. Secondary outcomes included return of spontaneous circulation (ROSC) and types of cardiac arrest. Pooled percentages with a 95% confidence interval (CI) were calculated for the prevalence of outcomes.
Results
A total of 7,891 COVID patients were included in the study. There were 621 (pooled prevalence 8%, 95% CI 4–13%) cardiac arrest patients. There were 52 (pooled prevalence 3.0%; 95% CI 0.0–10.0%) patients that survived at the time of discharge. ROSC was achieved in 202 (pooled prevalence 39%;95% CI 21.0–59.0%) patients. Mean time to ROSC was 7.74 (95% CI 7.51–7.98) min. The commonest rhythm at the time of cardiac arrest was pulseless electrical activity (pooled prevalence 46%; 95% 13–80%), followed by asystole (pooled prevalence 40%; 95% CI 6–80%). Unstable ventricular arrhythmia occurred in a minority of patients (pooled prevalence 8%; 95% CI 4–13%).
Conclusion
This pooled analysis of studies showed that the survival post in‐hospital cardiac arrest in COVID patients is dismal despite adequate ROSC obtained at the time of resuscitation. Nonshockable rhythm cardiac arrest is commoner suggesting a non‐cardiac cause while cardiac related etiology is uncommon. Future studies are needed to improve the survival in these patients.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Transcatheter aortic valve replacement (TAVR) for transcatheter heart valve failure has been suggested for high‐risk patients. TAVR‐in‐TAVR, however, may lead to complex leaflet interactions causing ...coronary ostial obstruction, which is a devastating complication. Coronary protection with provisional stent placement may be challenging. We describe the first percutaneous transaxillary case of TAVR‐in‐TAVR with Bioprosthetic Aortic Scallop Intentional Laceration to prevent Iatrogenic Coronary Artery obstruction (BASILICA) where guide catheters used for coronary protection were entrapped between the valve frames. We describe anatomical predictors and management considerations. Operators should be aware of this important complication during TAVR‐in‐TAVR valve placement.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK