Coronary microvascular dysfunction (CMD) has emerged as a crucial contributor to cardiovascular morbidity and mortality, particularly in patients with ischemia and non-obstructive coronary arteries (INOCA). The condition arises from a complex interplay of structural and functional abnormalities within the small coronary vessels, driven by underlying molecular mechanisms including endothelial nitric oxide synthase (eNOS) uncoupling, oxidative stress, and chronic inflammation. Lipid metabolism plays a central role in this pathology, especially in the setting of elevated low-density lipoprotein cholesterol (LDL-C). Furthermore, the protective capacity of high-density lipoprotein (HDL) is increasingly understood to depend on its functionality rather than absolute levels, as it can become dysfunctional and pro-inflammatory in pathological states. Emerging evidence has identified lipoprotein(a) [Lp(a)] and triglyceride-rich lipoproteins as significant, independent contributors to microvascular injury. Comprehensive clinical assessment of microvascular dysfunction therefore requires integration of advanced lipid profiling, including apolipoprotein B (ApoB), [Lp(a)], and the triglyceride-glucose (TyG) index with invasive and non-invasive measures of coronary flow reserve to more precisely stratify risk. In this narrative review, we synthesize current observational, mechanistic, and early interventional data linking diverse lipid phenotypes to coronary microvascular dysfunction. We propose a concept of lipid-driven CMD endotypes, such as ApoB-/particle overload, dysfunctional HDL, Lp(a)-mediated risk, and metabolic/TyG-high states, and map these to a practical, mechanism-informed management framework. While intensive LDL-C lowering with high-intensity statins and combination therapy remains guideline-directed care for high-risk patients, evidence for dedicated microvascular benefit from newer lipid and cardiometabolic agents is still largely hypothesis-generating. A personalized approach that aligns lipid phenotyping, CMD endotyping, and existing guideline-based therapies may help refine risk assessment and inform future trials.

Coronary artery disease (CAD) remains a leading cause of global morbidity and mortality. Accurate diagnosis of ischemia-causing coronary stenoses is essential for guiding revascularization and improving outcomes. Although invasive fractional flow reserve (FFR) remains the gold standard for functional lesion assessment, its use is limited by procedural invasiveness, cost, and complexity. CT-derived FFR (FFRct), based on computational fluid dynamics (CFD), was the first major advance in noninvasive physiological assessment, but its adoption has been hindered by intensive off-site computation and dependence on high-quality imaging. This review summarizes the evolution from invasive FFR to AI-driven functional assessment of coronary lesions. We examine the principles and validation of CFD-based FFRct and then focus on the shift toward artificial intelligence, including both machine learning (ML) and deep learning (DL) approaches. These methods range from models using engineered geometric and plaque features trained on large synthetic datasets to end-to-end systems that learn directly from imaging data. We discuss key validation studies evaluating diagnostic accuracy, prognostic value, and clinical utility, with attention to performance in challenging settings such as intermediate stenoses, heavy calcification, and patients with comorbidities. We also highlight major barriers to widespread adoption, including dependence on input data quality, limited explainability, regulatory hurdles, and integration into clinical workflows. Finally, we outline future directions, including AI-enabled virtual PCI planning, multimodal risk stratification, and broader access to functional cardiac assessment. AI has the potential to transform noninvasive coronary imaging by enabling a single CCTA scan to provide rapid, integrated evaluation of anatomy, plaque characteristics, and physiological significance, supporting more personalized care and better clinical outcomes.

Aims: The aims of this study were to evaluate the association between the red cell distribution width (RDW)–albumin ratio (RAR) and subclinical myocardial impairment, as assessed by left ventricular global longitudinal strain (LVGLS), and to examine the relationships between the RAR, heart failure (HF) hospitalization, and all-cause mortality. Methods: We conducted a retrospective cohort study on adults who underwent transthoracic echocardiography (TTE) with LVGLS assessment across three Mayo Clinic centers (2017–2024) and who had RDW and serum albumin measured on the same day or within seven days. The RAR was calculated as RDW/albumin and categorized into the following tertiles: 3.48. Impaired LVGLS was defined as >−18%. Associations between the RAR and outcomes were assessed using multivariable logistic regression (LVGLS) and Cox models (HF and mortality), adjusting for demographics and comorbidities. Results: Among 5069 patients, 39.7% had impaired LVGLS, and its prevalence increased across RAR tertiles (26.8%, 41.9%, and 51.1%). Adjusted odds ratios for impaired LVGLS were 1.74 and 2.30 for tertiles 2 and 3, respectively. A higher RAR was associated with increased risk of HF hospitalization (aHR 2.54 and 4.48) and all-cause mortality (aHR 2.39 and 7.30). These associations persisted after adjusting for LVGLS. The effect of the RAR on mortality was stronger in patients with normal LVGLS compared to those with impaired LVGLS (p for interaction = 0.0004). Conclusions: A higher RAR was associated with abnormal LVGLS, HF hospitalization, and all-cause mortality after adjustment for clinical risk factors. However, the RAR did not provide discriminative value beyond its individual components.