Explore the vast range of titles available.

Traditional statistical models allow population based inferences and comparisons. Machine learning (ML) explores datasets to develop algorithms that do not assume linear relationships between variables and outcomes and that may account for higher order interactions to make individualized outcome predictions. To evaluate the performance of machine learning models compared to traditional risk stratification methods for the prediction of major adverse cardiovascular events (MACE) and bleeding in patients with acute coronary syndrome (ACS) that are treated with antithrombotic therapy. Data on 24,178 ACS patients were pooled from four randomized controlled trials. The super learner ensemble algorithm selected weights for 23 machine learning models and was compared to traditional models. The efficacy endpoint was a composite of cardiovascular death, myocardial infarction, or stroke. The safety endpoint was a composite of TIMI major and minor bleeding or bleeding requiring medical attention. For the MACE outcome, the super learner model produced a higher c-statistic (0.734) than logistic regression (0.714), the TIMI risk score (0.489), and a new cardiovascular risk score developed in the dataset (0.644). For the bleeding outcome, the super learner demonstrated a similar c-statistic as the logistic regression model (0.670 vs. 0.671). The machine learning risk estimates were highly calibrated with observed efficacy and bleeding outcomes (Hosmer–Lemeshow p value = 0.692 and 0.970, respectively). The super learner algorithm was highly calibrated on both efficacy and safety outcomes and produced the highest c-statistic for prediction of MACE compared to traditional risk stratification methods. This analysis demonstrates a contemporary application of machine learning to guide patient-level antithrombotic therapy treatment decisions.Clinical Trial Registration ATLAS ACS-2 TIMI 46: https://clinicaltrials.gov/ct2/show/NCT00402597. Unique Identifier: NCT00402597. ATLAS ACS-2 TIMI 51: https://clinicaltrials.gov/ct2/show/NCT00809965. Unique Identifier: NCT00809965. GEMINI ACS-1: https://clinicaltrials.gov/ct2/show/NCT02293395. Unique Identifier: NCT02293395. PIONEER-AF PCI: https://clinicaltrials.gov/ct2/show/NCT01830543. Unique Identifier: NCT01830543.

Background As cardiovascular disease is a leading cause of death in cancer survivors, the new subspecialty of Cardio-Oncology has emerged to address prevention, monitoring, and management of cardiovascular toxicities to cancer therapies. During the coronavirus disease of 2019 (COVID-19) pandemic, we developed a Virtual-Hybrid Approach to build a de novo Cardio-Oncology Clinic. Methods We conceptualized a Virtual-Hybrid Approach including three arms: information seeking in locations with existing Cardio-Oncology clinics, information gathering at the location for a new clinic, and information sharing to report clinic-building outcomes. A retrospective review of outcomes included collection and synthesis of data from our first 3 months (at pandemic peak) on types of appointments, cancers, drugs, and cardiotoxicities. Data were presented using descriptive statistics. Results A de-novo Cardio-Oncology clinic was developed structured from the ground up to integrate virtual and in-person care in a hybrid and innovative model, using the three arms of the Virtual-Hybrid Approach. First, we garnered in-person and virtual preparation through hands-on experiences, training, and discussions in existing Cardio-Oncology Clinics and conferences. Next, we gleaned information through virtual inquiry and niche-building. With partners throughout the institution, a virtual referral process was established for outpatient referrals and inpatient e-consult referrals to actualize a hybrid care spectrum for our patients administered by a multidisciplinary hybrid care team of clinicians, ancillary support staff, and clinical pharmacists. Among the multi-subspecialty clinic sessions, approximately 50% were in Cardio-Oncology, 20% in Preventive Cardiology, and 30% in General Cardiology. In the hybrid model, the Heart & Vascular Center had started to re-open, allowing for 65% of our visits to be in person. In additional analyses, the most frequent cardiovascular diagnosis was cardiomyopathy (34%), the most common cancer drug leading to referral was trastuzumab (29%), and the most prevalent cancer type was breast cancer (42%). Conclusion This Virtual-Hybrid Approach and retrospective review provides guidance and information regarding initiating a brand-new Cardio-Oncology Clinic during the pandemic for cancer patients/survivors. This report also furnishes virtual resources for patients, virtual tools for oncologists, cardiologists, and administrators tasked with starting new clinics during the pandemic, and innovative future directions for this digital pandemic to post-pandemic era.

The identification of acutely ill patients at high risk for venous thromboembolism (VTE) may be determined clinically or by use of integer‐based scoring systems. These scores demonstrated modest performance in external data sets. To evaluate the performance of machine learning models compared to the IMPROVE score. The APEX trial randomized 7513 acutely medically ill patients to extended duration betrixaban vs. enoxaparin. Including 68 variables, a super learner model (ML) was built to predict VTE by combining estimates from 5 families of candidate models. A “reduced” model (rML) was also developed using 16 variables that were thought, a priori, to be associated with VTE. The IMPROVE score was calculated for each patient. Model performance was assessed by discrimination and calibration to predict a composite VTE end point. The frequency of predicted risks of VTE were plotted and divided into tertiles. VTE risks were compared across tertiles. The ML and rML algorithms outperformed the IMPROVE score in predicting VTE (c‐statistic: 0.69, 0.68 and 0.59, respectively). The Hosmer‐Lemeshow goodness‐of‐fit P‐value was 0.06 for ML, 0.44 for rML, and <0.001 for the IMPROVE score. The observed event rate in the lowest tertile was 2.5%, 4.8% in tertile 2, and 11.4% in the highest tertile. Patients in the highest tertile of VTE risk had a 5‐fold increase in odds of VTE compared to the lowest tertile. The super learner algorithms improved discrimination and calibration compared to the IMPROVE score for predicting VTE in acute medically ill patients.

D-dimer has been used as both a diagnostic and prognostic biomarker in the assessment of patients with venous thromboembolism, but its prognostic value in the setting of arterial acute coronary syndromes (ACS) and the ability of pharmacotherapy to reduce D-dimer in ACS is less well characterized. It was hypothesized that elevated baseline D-dimer would be associated with poor clinical outcomes in ACS, and that Factor Xa inhibition with Rivaroxaban would reduce D-dimer acutely and chronically. The ATLAS ACS TIMI-46 trial assessed the safety and efficacy of rivaroxaban compared with placebo in ACS patients. A subset of subjects had a D-dimer measured at baseline (n = 1,834, 52.5%). A univariate and multivariable logistic regression assessed the relation between baseline D-dimer and a composite end point of cardiovascular death, myocardial infarction, or stroke through 6 months. The Wilcoxon rank sum test was used to compare change in D-dimer level between the treatment groups from baseline. Baseline D-dimer was associated with the composite efficacy outcome in a univariate logistic regression (odds ratio 1.15, 95% confidence interval 1.03 to 1.29, p = 0.015) and a multivariable logistic regression (odds ratio 1.13, 95% confidence interval 1.00 to 1.28, p = 0.048). Rivaroxaban administration lowered D-dimer levels compared wth placebo after administration of the first dose of study drug (p = 0.026), at day 30 (p < 0.001) and day 180 (p < 0.001). In conclusion, elevated baseline D-dimer was associated with an increased risk of the composite outcome within 6 months of the ACS event and administration of the Factor Xa inhibitor rivaroxaban was associated with lower D-dimer levels compared with placebo after the first dose, at day 30 and day 180.

An elevated white blood cell (WBC) count is associated with an increased risk of ischemic events among acute coronary syndrome (ACS) patients, but the association between WBC count and bleeding in ACS patients is not well established. The aim of this analysis was to assess and compare the association between WBC count and the occurrence of short- and long-term bleeding and ischemic events. This was a post hoc analysis of the ATLAS ACS2-TIMI 51 trial. A subset of patients had a WBC count measurement at baseline (n = 14,231, 91.6%). Univariate and multivariable Cox proportional hazard models were constructed to determine if there is an association between WBC count at baseline and a composite outcome of Thrombolysis in Myocardial Infarction (TIMI) major and minor bleeds at 30 days and 1 year. Variables with a p <0.2 in the univariate analysis were included as potential parameters in the backward selection process A similar multivariable model was constructed to assess the association between WBC count and a composite ischemic endpoint of cardiovascular death, myocardial infarction and stroke. An increased risk of bleeding per a 1 × 109/L increase in WBC at baseline was observed at 30 days (Adjusted hazard ratio [HR] 1.08 95% confidence interval [CI] 1.01 to 1.17, p = 0.019) but not at 1 year (Adjusted HR 1.02 95% CI 0.97 to 1.08, p = 0.409). Additionally, an increased risk of ischemia per a 1 × 109/L increase in WBC at baseline was observed at 30 days (Adjusted HR 1.07, 95% CI: 1.03 to 1.12, p = 0.002) and at 1 year (Adjusted HR 1.05 95% CI 1.02 to 1.08, p = 0.001 at 1 year). In conclusion, a higher WBC count at baseline was associated with an increased risk of the composite bleeding endpoint by 30 days but not at 1 year. The association between WBC count and the risk of the composite ischemic endpoint was significant at 30 days and 1 year.

Patients who are hospitalized for acute medical illness are at an increased risk of both venous and arterial thrombosis. Several large randomized clinical trials have established the efficacy of anticoagulation for the in-hospital duration, in the prevention of venous thromboembolism (VTE). These studies have led the American College of Chest Physicians to recommend administration of low molecular weight heparin or low dose unfractionated heparin for a duration of 6 to 14 days to acute medically ill patients who are at a high risk for VTE and are not at high risk of major bleeding. This guideline recommends using the Padua Prediction score to evaluate patient’s risk of VTE though it does acknowledge that this score lacks prospective validation and generalizability, among other limitations. Subsequent studies have demonstrated that these patients’ risk of thrombosis extends beyond the in-hospital period. Approximately 60% of VTE occurred after hospital discharge and 53% had occurred within 30 days of the index hospitalization. Five large randomized trials have since evaluated the efficacy and safety of extended-duration thromboprophylaxis (for 28 to 47 days) with enoxaparin, rivaroxaban, apixaban and betrixaban in hospitalized acutely medically ill patients. Of these agents, betrixaban, a novel factor Xa inhibitor, was the only one to demonstrate a significantly reduced risk of VTE coupled with no significant difference in major bleeding. Following the release of the results of the APEX trial, the FDA licensed betrixaban for extended duration thromboprophylaxis in acute medically ill patients at high risk for VTE. Much attention is given to the prevention of venous thrombosis in acutely medically ill patients; however, despite sharing common risk factors with arterial thrombotic events, little is done in the way of prophylaxis against ischemic cardiovascular events in these patients. Hypercoagulability and inflammation are known mechanisms that contribute to both pathologies; yet little has been done to explore the efficacy of anticoagulation in reducing the incidence of arterial thrombotic events in this patient population. We hypothesized that, by upstream inhibition of the prothrombinase complex with factor Xa inhibitors, acutely ill patients would not only experience less venous thrombosis but also reduced major adverse cardiovascular events. Despite successes in the development of novel therapeutic agents and regimens that have prevented thrombosis in patients enrolled in clinical trials, the question of how to identify high thrombotic risk (and low bleeding risk) patients in a clinical setting remains unanswered. Risk scores have known limitations that have prevented their widespread use in this setting. In fact, the most recent extended-duration thromboprophylaxis randomized trial enriched for high-risk patients using a popular risk score as a screening tool yet failed to demonstrate statistical significance in 12,000 patients despite a 23% relative risk reduction in the primary endpoint. This suggests a lack of sensitivity of the risk score in identifying truly high-risk patients. Machine learning algorithms are constructed to search for patterns in data that provide maximum predictive ability. These learning methods have demonstrated superiority to traditional diagnostic and prognostic tools in various domains. However, the performance of machine learning methods in the prediction of the occurrence of thrombosis has not been previously explored. We sought to explore the utility of this novel methodology in predicting thrombotic events in acutely medically ill patients enrolled in the APEX trial.

Approximately 15%-30% of patients in trials of medical thromboprophylaxis will have missing compression ultrasound (CUS) data. The goal of the present analysis was to perform analyses to minimize missing data. The APEX trial randomized 7,513 acutely medically ill hospitalized patients to thromboprophylaxis with either betrixaban for 35-42 days or enoxaparin for 6-14 days. A modified intent-to-treat (mITT) analysis was performed and included all subjects administered study drug, irrespective of CUS performance, and an analysis of symptomatic events which do not require performance of a CUS (symptomatic deep vein thrombosis, nonfatal pulmonary embolism, and venous thromboembolism (VTE)–related mortality). In the mITT population, betrixaban significantly reduced the primary end point (which included both symptomatic and CUS events) (165 [4.4%] vs 223 [6.0%]; relative risk = 0.75; 95% CI 0.61-0.91; P = .003; absolute risk reduction [ARR] = 1.6%; number needed to treat [NNT] = 63). Betrixaban also reduced symptomatic VTE through day 42 (35 [1.28%] vs 54 [1.88%], hazard ratio [HR] = 0.65; 95% CI 0.42-0.99; P = .044; ARR = 0.6%; NNT=167) as well as through day 77 (37 [1.02%] vs 67 [1.89%]; HR= 0.55; 95% CI 0.37-0.83; P = .003; ARR = 0.87%; NNT=115) as well as the individual end point of nonfatal pulmonary embolism (9 [0.25%] vs 20 [0.55%]; HR= 0.45; 95% CI 0.21-0.99; P = .041; ARR = 0.30%; NNT=334). On an “as-treated” basis, 80 mg of betrixaban reduced VTE-related mortality through day 77 (10 [0.34%] vs. 22 [0.79%]; HR=0.46; 95% CI 0.22-0.96; P = .035; ARR = 0.45%; NNT=223). In an mITT analysis of all patients administered study drug, extended-duration betrixaban reduced the primary end point as well as symptomatic events. In an as-treated analysis, 80 mg of betrixaban reduced VTE-related death.

Hospitalized acute medically ill patients with a history of venous thromboembolism (VTE) are at increased risk for recurrent VTE. We characterized the efficacy and safety of betrixaban for prevention of recurrent VTE in these high risk patients. The APEX trial randomized 7513 acutely ill hospitalized medical patients at risk for developing VTE to receive either betrixaban for 35–42 days or enoxaparin for 10 ± 4 days to prevent VTE. This exploratory post-hoc analysis assessed the efficacy and safety of betrixaban versus enoxaparin among subjects with and without prior VTE. Time-to-multiple symptomatic VTE events was also calculated. Approximately 8% of subjects in both arms had prior VTE, which was associated with a fourfold increase in adjusted risk of VTE [MV OR 4.03, 95% CI 3.06–5.30, p < 0.001]. Betrixaban reduced VTE compared with enoxaparin among subjects with prior VTE [32 (10.4%) vs. 55 (18.9%), RR 0.57, 95% CI 0.38–0.86, p = 0.006, ARR 8.5%, NNT 12] and without prior VTE [133 (3.9%) vs. 168 (4.9%), RR 0.79, 95% CI 0.64–0.99, p = 0.042, ARR 1.0%, NNT 100] (interaction p > 0.05). Additionally, four subjects in the enoxaparin arm and one subject in the betrixaban arm experienced a recurrent VTE. Compared with enoxaparin, betrixaban use was associated with reduction of recurrent VTE events through the active treatment period [36 vs. 57, HR 0.63, 95% CI 0.41–0.97, p = 0.045] and through the end of study [38 vs. 71, HR 0.54, 95% CI 0.36–0.81, p = 0.004]. Prior VTE is associated with a fourfold increase in the risk of VTE among hospitalized medically ill patients. Only 12 such patients would need to be treated with betrixaban versus enoxaparin to prevent an additional VTE endpoint. Betrixaban reduced not only the first but also all recurrent VTE events in a time-to-any-event analysis.Trial registration: http://www.clinicaltrials.gov, Unique identifier: NCT01583218

Total ischemic time, which specifies the time from the onset of chest pain to initiation of reperfusion during percutaneous coronary intervention, consists of two intervals: symptom to door time and door to balloon time. A door to balloon time of 90 mins or less has become a quality-of-care metric in the management of ST elevation myocardial infarction (STEMI). While national efforts made by the American College of Cardiology (ACC) and American Heart Association (AHA) have curtailed in-hospital door to balloon time over the years, a reduction in pre-hospital symptoms to door time presents a challenge in modern interventional Cardiology. Early and complete revascularization has been associated with improved clinical outcomes in MI and strategies that may help reduce symptom to door time, and thus the total ischemic time, are crucial. Rapidly evolving ST-segment changes commonly develop prior to ischemia-related symptom onset, and are detectable even in patients with clinically unrecognized silent MIs. Therefore, a highly intelligent ischemia detection system that alerts patients of ST segment deviation may allow for rapid identification of acute coronary occlusion. The AngelMed Guardian System is a cardiac activity monitoring and alerting system designed for rapid identification of intracardiac ST-segment changes among patients at a high risk for recurrent ACS events. This article reviews the clinical studies evaluating the design, safety and efficacy of the AngelMed Guardian System and discusses the clinical implications of the device.