Shafqat, Areez

Abstract: Cardiovascular disease (CVD) remains the leading cause of death worldwide. While advances in treatment have improved outcomes, the greatest gains in public health will come from primary prevention. Risk stratification is the foundation of CVD prevention. Traditional tools, such as pooled cohort equations (PCEs) and SCORE2, do not capture non-traditional risk factors and individual variability, driving efforts to refine existing approaches. We critically discuss emerging risk determinants for primary CVD prevention. Coronary artery calcium scoring can reclassify CVD risk but has limitations related to cost, access, and unvalidated improvements in clinical endpoints. Biomarkers such as apolipoprotein B and lipoprotein(a) may identify residual risk beyond LDL-C, particularly in patients with lipid discordance, but remain underused due to uncertain thresholds and the lack of prospective triallevel outcome data. Trials of colchicine in primary prevention have yielded mixed results, making the role of targeting inflammation unclear in CVD prevention. Polygenic risk scores can stratify genetic risk but face challenges in sensitivity, specificity, and generalizability. Multiomics approaches, while offering the promise of deeper phenotyping, lack established clinical applications and consensus on when their use is appropriate. Artificial intelligence may allow better prediction across cohorts but requires broader validation. Clonal hematopoiesis of indeterminate potential, a marker of inflammation and age-related CVD risk, lacks evidence supporting routine screening or intervention in younger, asymptomatic individuals. The proliferation of new risk stratification tools poses a key challenge: determining when additional data meaningfully alter clinical decisions. Until robust outcome-based evidence emerges, risk enhancers should guide, but not dictate, therapy in selected patients.

Despite advances in ablative therapies, outcomes remain less favorable for persistent atrial fibrillation often due to presence of non-pulmonary vein triggers and abnormal atrial substrates. This review highlights advances in ablation technologies and notable scientific literature on clinical outcomes associated with pursuing adjunctive ablation targets and substrate modification during persistent atrial fibrillation ablation, while also highlighting notable future directions.

Purpose of review This review delves into the potential of artificial intelligence (AI), particularly machine learning (ML), in enhancing graft-versus-host disease (GVHD) risk assessment, diagnosis, and personalized treatment. Recent findings Recent studies have demonstrated the superiority of ML algorithms over traditional multivariate statistical models in donor selection for allogeneic hematopoietic stem cell transplantation. ML has recently enabled dynamic risk assessment by modeling time-series data, an upgrade from the static, “snapshot” assessment of patients that conventional statistical models and older ML algorithms offer. Regarding diagnosis, a deep learning model, a subset of ML, can accurately identify skin segments affected with chronic GVHD with satisfactory results. ML methods such as Q-learning and deep reinforcement learning have been utilized to develop adaptive treatment strategies (ATS) for the personalized prevention and treatment of acute and chronic GVHD. Summary To capitalize on these promising advancements, there is a need for large-scale, multicenter collaborations to develop generalizable ML models. Furthermore, addressing pertinent issues such as the implementation of stringent ethical guidelines is crucial before the widespread introduction of AI into GVHD care.