Daily Cardiology Research Analysis

Background Multimodality imaging is essential for personalized prognostic stratification in suspected coronary artery disease (CAD). Machine learning (ML) methods can help address this complexity by incorporating a broader spectrum of variables. Purpose To investigate the performance of an ML model that uses both stress cardiac MRI and coronary CT angiography (CCTA) data to predict major adverse cardiovascular events (MACE) in patients with newly diagnosed CAD. Materials and Methods This retrospective study included consecutive symptomatic patients without known CAD referred for CCTA between December 2008 and January 2020. Patients with obstructive CAD (at least one ≥50% stenosis at CCTA) underwent stress cardiac MRI for functional assessment. Eighteen clinical, two electrocardiogram, nine CCTA, and 12 cardiac MRI parameters were evaluated as inputs for the ML model, which involved automated feature selection with the least absolute shrinkage and selection operator algorithm and model building with an XGBoost algorithm. The primary outcome was MACE, defined as a composite of cardiovascular death and nonfatal myocardial infarction. External testing was performed using two independent datasets. Performance was compared between the ML model and existing scores and other approaches using the area under the receiver operating characteristic curve (AUC). Results Of 2210 patients who completed cardiac MRI, 2038 (mean age, 70 years ± 12 [SD]; 1091 [53.5%] female participants) completed follow-up (median duration, 7 years [IQR, 6-9 years]); 281 experienced MACE (13.8%). The ML model exhibited a higher AUC (0.86) for MACE prediction than the European Society of Cardiology score (0.55), QRISK3 score (0.60), Framingham Risk Score (0.50), segment involvement score (0.71), CCTA data alone (0.76), or stress cardiac MRI data alone (0.83) (

AIMS: To examine the association of a remote monitoring programme (RMP) with all-cause mortality and hospital admissions for heart failure (HF) within the French healthcare system. METHODS AND RESULTS: A national-scale, real-world, propensity-weighted cohort study was conducted using the SNDS French database from August 2018 to December 2022 (NCT06312501). Patients receiving standard of care (SoC) were compared with those receiving RMP (Satelia® Cardio, NP Medical). The Satelia® Cardio algorithm adjusted the monitoring frequency based on symptom and weight changes, and provided tailored web-based patient education. The RMP included a digital interface for proficient patients and phone monitoring by nurses for those uncomfortable with digital technology. Data were sourced from over 300 healthcare centres across France. A propensity-weighted Cox regression model was used, supplemented by sensitivity analyses across subgroups. In total, 5357 RMP patients and 13 525 SoC patients were included after weighting. Weighted/adjusted analyses showed lower all-cause mortality for RMP patients (hazard ratio [HR] 0.64; 95% confidence interval [CI] 0.59-0.70; p < 0.0001), persisting across hospitalization and/or long-term illness status subgroups (HR 0.52 to 0.75). RMP was neutrally associated with HF hospitalization rates (rate ratio [RR] 0.95; 95% CI 0.89-1.02) but linked to less time in hospital (-2.1%, p < 0.0001) and fewer emergency visits (RR 0.83; 95% CI 0.75-0.92; p = 0.001). CONCLUSION: In France, RMP with customized monitoring frequencies and educational strategies was associated with lower all-cause mortality, emergency visits, and time spent in hospital in patients with HF which may enhance nationwide HF management.

This appropriate use criteria (AUC) document is developed by the American College of Cardiology along with key specialty and subspecialty societies. It provides a comprehensive review of common clinical scenarios where implantable cardioverter-defibrillator (ICD), cardiac resynchronization therapy (CRT), cardiac contractility modulation, leadless pacing, and conduction system pacing therapies are frequently considered. The 335 clinical scenarios covered in this document address ICD indications including those related to secondary prevention, primary prevention, comorbidities, generator replacement at elective replacement indicator, dual-chamber, and totally subcutaneous ICDs, as well as device indications related to CRT, conduction system pacing, leadless pacing, cardiac contractility modulation, and ICD therapy in the setting of left ventricular assist devices (LVADs). The indications (clinical scenarios) were derived from common applications or anticipated uses, as well as from current clinical practice guidelines and results of studies examining device implantation. The indications in this document were developed by a multidisciplinary writing group and scored by a separate independent rating panel on a scale of 1 to 9 to designate care that is considered “Appropriate” (median 7 to 9), “May Be Appropriate” (median 4 to 6), and “Rarely Appropriate” (median 1 to 3). The final ratings reflect the median score of the 17 rating panel members. In general, Appropriate designations were assigned to scenarios for which clinical trial evidence and/or clinical experience was available that supported device implantation. In contrast, scenarios for which clinical trial evidence was limited or device implantation seemed reasonable for extenuating or practical reasons were categorized as May Be Appropriate. Scenarios for which there were data showing harm, or no data were available, and medical judgment deemed device therapy was illadvised were categorized as Rarely Appropriate. For example, comorbidities including reduced life expectancy related to noncardiac conditions or severe cognitive dysfunction would negatively impact appropriateness ratings. The appropriate use criteria for ICD, CRT, and pacing have the potential to enhance clinician decision making, healthcare delivery, and payment policy. Furthermore, recognition of clinical scenarios rated as May Be Appropriate facilitates the identification of areas where there may be gaps in evidence that would benefit from future research. The American College of Cardiology (ACC) has a long history of developing documents (eg, expert consensus decision pathways, health policy statements, AUC documents) to provide members with guidance on both clinical and nonclinical topics relevant to cardiovascular care. In most circumstances, these documents have been created to complement clinical practice guidelines and to inform clinicians about areas where evidence is new and evolving or where sufficient data are more limited. Despite this, numerous gaps persist, highlighting the need for more streamlined and efficient processes to implement best practices in patient care. Central to the ACC’s strategic plan is the generation of