Collier, Patrick

Background Cardiovascular disease (CVD) is a leading cause of death in cancer survivors. Predicting CVD risk in this population remains challenging. Risk prediction models that use machine learning algorithms could provide an objective method for accurate risk prediction to facilitate the prevention and management of CVD in cancer survivors. We evaluated previously tested machine learning algorithms and logistic regression (regularized by machine learning methods), in addition to testing and validating newer, more complex machine learning algorithms, for CVD prediction in cancer survivors. Methods This multicenter study used a database of 3835 multiracial cancer survivors with 89 clinical, laboratory, and echocardiographic features over 20 years. Models were trained using repeated random and time‐split samples and tested on a separate cohort of 329 patients. Model performance was assessed using the area under the receiver operating characteristic curve. Results Regularized logistic regression achieved an area under the receiver operating characteristic curve of 0.845 (heart failure), 0.783 (atrial fibrillation), 0.792 (coronary artery disease), and 0.806 (composite CVD). These are comparable to 0.837 and 0.848 for heart failure, using Bayesian additive regression tree and random forest as more advanced machine learning models, respectively. De novo composite CVD (post‐cancer diagnosis) was also predicted with an area under the receiver operating characteristic curve of 0.826 using regularized logistic regression, compared with 0.735 and 0.802 using decision tree and random forest, respectively. Conclusions Regularized logistic regression and advanced machine learning models demonstrated similar predictive performance, with institutional transferability. These tools may support risk stratification and prevention strategies in cardio‐oncology using longitudinal data. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: NCT05377320.

BACKGROUND: Global collaboration in cardio-oncology is needed to understand the prevalence of cancer therapy-related cardiovascular toxicity in different risk groups, practice settings, and geographic locations. There are limited data on the socioeconomic and racial/ethnic disparities that may impact access to care and outcomes. To address these gaps, we established the Global Cardio-Oncology Registry, a multinational, multicenter prospective registry. METHODS: We assembled cardiologists and oncologists from academic and community settings to collaborate in the first Global Cardio-Oncology Registry. Subsequently, a survey for site resources, demographics, and intention to participate was conducted. We designed an online data platform to facilitate this global initiative. RESULTS: A total of 119 sites responded to an online questionnaire on their practices and main goals of the registry: 49 US sites from 23 states and 70 international sites from 5 continents indicated a willingness to participate in the Global Cardio-Oncology Registry. Sites were more commonly led by cardiologists (85/119; 72%) and were more often university/teaching (81/119; 68%) than community based (38/119; 32%). The average number of cardio-oncology patients treated per month was 80 per site. The top 3 Global Cardio-Oncology Registry priorities in cardio-oncology care were breast cancer, hematologic malignancies, and patients treated with immune checkpoint inhibitors. Executive and scientific committees and specific committees were established. A pilot phase for breast cancer using Research Electronic Data Capture Cloud platform recently started patient enrollment. CONCLUSIONS: We present the structure for a global collaboration. Information derived from the Global Cardio-Oncology Registry will help understand the risk factors impacting cancer therapy-related cardiovascular toxicity in different geographic locations and therefore contribute to reduce access gaps in cardio-oncology care. Risk calculators will be prospectively derived and validated.

Introduction: Global collaboration in cardio-oncology (CO) is needed to understand the prevalence of cancer treatment related cardiovascular disease (CTRCD) in different risk groups, practice settings and geographic locations. Furthermore, socio-economic and ethnic disparities may impact access to care. Methods: We assembled cardiologists (CA) and oncologists from academic and community settings to collaborate in the first global cardio-oncology registry (G-COR). US and international CO physicians participated in the first global virtual meeting to assess feasibility and structure for G-COR. Subsequently, a survey for sites resources, demographics and intention to participate was conducted. Results: Responses with sites demographics from 104/140 sites invited: 43 US sites from 23 states and 61 international sites from 5 continents indicated decision to participate in G-COR. Sites were more commonly led by CA (74/99) than CA and oncologists (25/99) and were more often University/teaching (68/101) than community based (33/101). Significant minorities/disadvantaged CO patient population were reported by 32/43 US sites versus 16/60 international sites. Average number CO patients treated per month was 83, range (5-1,000). Breast cancer was the first or second G-COR priority for 84 centers, hematological malignancies (HEM) for 66 centers, and immune check point inhibitors (ICI) for 36 centers. Echocardiography with strain imaging is available in 92/95 participating sites and cardiac MRI in 80/86 sites. Biomarkers are used only in suspected or confirmed CTRCD in 56/96 sites and for risk stratification in high risk patients in 40/96 sites. Subsequently, scientific committee and topic committees for breast cancer, HEM, ICI, and disparities in CO were established. A pilot phase utilizing a RedCap Cloud platform will start enrolling patients in the last quarter of 2021 and the registry for all main pillars will launch in early 2022. Conclusions: We present a global initiative for conducting collaborative research. Information learned G-COR will help understanding risk factors impacting CTRCD in different geographic locations and therefore help reducing access gaps in CO care. Additionally, mitigating strategies can be devised for the future.

Abstract Background: Previous studies have found various incidences of right ventricular dysfunction (RVD) and its association with clinical outcome. In this systematic review and meta-analysis, we aimed to investigate the impact of the presence of RVD on mortality in patients with ARDS.Method: We searched Medline, Embase, and the Cochrane Central Register of Controlled Trials for studies investigating the association between RVD and mortality. Two authors independently evaluated whether studies meet eligibility criteria and extracted the selected patients’ and studies’ characteristics and outcomes. The primary outcome was the association between mortality and the presence of RVD in patients with ARDS. Results: We included 9 studies (N = 1,861 patients) in this meta-analysis. RVD was present in 21.0% (391/1,861). In the pooled meta-analysis, the presence of RVD in patients with ARDS was associated with significantly higher overall mortality (OR: 1.45, 95%CI: 1.13-1.86, p-value = 0.003, I2 = 0%), as well as short-term mortality (OR: 1.48, 95%CI: 1.14-1.93, p-value = 0.003, I2 = 0%).Conclusion: In this systematic review and meta-analysis including 1,861 patients with ARDS, the presence of RVD was significantly associated with increased overall and short-term mortality.Trial registration: The protocol was registered at PROSPERO (CRD42020206521).