Citations

The advent of high-throughput sequencing technologies has revolutionized cardiovascular genetics, generating vast amounts of data. A major challenge in the genomic era is the efficient and accurate identification of causative genetic variants associated with cardiovascular disease. Artificial intelligence (AI)-driven computational approaches offer a powerful solution by enabling the automation of variant classification, improving consistency and reproducibility, and enhancing predictive accuracy. These methods may guide not only variant classification, variant effect prediction, and clinical prioritization, but also open the door to data-driven precision medicine, enabling more accurate and individualized diagnoses and targeted therapeutic strategies tailored to each patient’s unique genetic and clinical profile. This state-of-the-art review provides a structured overview of AI methodologies applied to cardiovascular genomics, beginning with rule-based expert systems that encode standardized guidelines for consistent variant interpretation. Next, we examine machine learning approaches capable of identifying complex patterns in annotated multimodal clinical and multi-omic datasets. The role of deep learning algorithms is highlighted for their ability to extract features from high-dimensional, unstructured data relevant to cardiovascular disease. In addition, the potential of generative AI is explored, including applications in synthetic data generation, variant impact prediction, and automated summarization of biomedical literature. Despite advances, several challenges remain, including data heterogeneity, the need for explainable AI models to elucidate the decision mechanisms, and the complexity linked to the integration of AI-based tools into clinical workflows. Addressing these issues requires interdisciplinary collaboration among clinicians, geneticists, data scientists, and bioinformaticians to ensure the effective translation of AI-generated insights into clinical practice. This review aims to provide a comprehensive perspective on the evolving role of AI in cardiovascular genomics and its implications for advancing precision medicine.

Abstract Background In patients with suspected amyloid cardiomyopathy (CM) and a monoclonal protein, tissue biopsy is mandatory to exclude amyloid light-chain CM (AL-CM), the subtype requiring urgent therapy. We aimed to develop a pragmatic approach to estimate the most likely final diagnosis before biopsy. Methods We studied a multicenter cohort of adults referred for biopsy because of suspected amyloid CM. Clinical, laboratory, ECG/echocardiographic and bone-tracer scintigraphy data were collected at initial suspicion. In patients with a monoclonal protein, we derived age cut-offs overall and by carpal tunnel syndrome (CTS), defined an age-based "gray zone" (74–83 years), and evaluated risk modifiers for AL-CM and transthyretin CM (ATTR-CM). We built a points-based algorithm for "gray-zone" patients. Clinical utility was assessed using decision-curve analysis. Results Among 602 patients (median age 76 years; 81% male), 524 (87%) had a monoclonal protein. In the monoclonal-protein subgroup, ATTR-CM accounted for 49%, AL-CM for 30%, and neither ATTR- nor AL-CM for 21%. Age ≤73 years was the Youden-optimal threshold favoring AL-CM (sensitivity 66%, specificity 78%), whereas age >84 years made AL-CM unlikely (sensitivity 98%, negative predictive value 94%), defining a "gray zone" (n=261; ATTR-CM 63%, AL-CM 18%, no amyloid CM 20%). Within the gray zone, abnormal free light-chain ratio, positive urine immunofixation, proteinuria, and higher troponin T and N-terminal pro-B-type natriuretic peptide (NT-proBNP) favored AL-CM, while higher Perugini grade, male sex, greater interventricular septal thickness, and higher NT-proBNP favored ATTR-CM. Penalized models achieved cross-validated area under the curves of 0.87 (AL-CM) and 0.94 (ATTR-CM). A two-score algorithm identified small gray-zone subsets enriched for AL-CM (positive predictive value 81.5%, specificity 98%) or ATTR-CM (positive predictive value 95.2%, specificity 94%). DCA showed higher net benefit for score- and model-based strategies versus treat-all/treat-none across clinically relevant threshold probabilities, with consistent patterns across regions. Conclusions In patients with suspected amyloid CM and a monoclonal protein, age- and CTS-anchored stratification refined by a compact set of routine laboratory and imaging features provides actionable pre-biopsy probabilities and may help prioritize urgent biopsy and AL-directed work-up while definitive tissue typing is pursued.For image description, please refer to the figure legend and surrounding text.

BACKGROUND: Bicuspid aortic valve (BAV) is a frequent congenital heart defect with a high heritability. Despite this, only a limited number of genes have been associated with the disease, and the molecular mechanisms remain unexplained in most cases. This study aimed to further understand the genetic architecture of BAV. METHODS: A genome-wide association study meta-analysis including 9631 cases among 65 677 participants was performed. Genes were prioritized using transcriptomic analyses based on RNA sequencing in relevant tissues, including human fetal and adult aortic valves. The impact of the knockdown or knockout of 4 candidate genes on cardiac development was verified in zebrafish. A polygenic risk score was developed, its association with BAV was evaluated in an independent cohort, and its association with a wide range of phenotypes (n=976) was evaluated in UK Biobank (n=355 618 individuals). RESULTS: Thirty-six genomic loci were identified, including 32 that were not described previously. Among the prioritized genes, KANK2 and ERBB4 were identified as potentially causal through transcriptomic analyses, colocalization, and Mendelian randomization based on gene expression in human aortic valves (n=484), whereas PRDM6 and STRN were prioritized using similar analyses from aortic (n=326) and left ventricular tissues (n=326), respectively. Targeting 4 candidate genes ( WNT4 , LEF1 , STRN , and KANK2 ) in zebrafish led to disruption in cardiac development. A polygenic risk score was associated with an odds ratio of 2.07 (95% CI, 1.90–2.25; P =5.43×10 -62 ) per SD for BAV and significantly associated with thoracic aortic aneurysm and atrial fibrillation in UK Biobank. CONCLUSIONS: This study supports a significant polygenic contribution to BAV, where the combination of multiple common variants in genes involved in heart morphogenesis disrupts aortic valve development.

Introduction: The prevalence of bicuspid aortic valves (BAV) is enriched thirty-fold in women with Turner Syndrome (TS) in comparison with the general population. Hypothesis: Common autosomal variants influence the development of BAV in TS women, who may be uniquely sensitized to these variants by the loss of one X chromosome. We sought to identify autosomal BAV susceptibility genes in a cohort of TS women (average age 30 years, 38% BAV, 18% coarctation). Methods: A total of 106 TS women of European ancestry with BAV and 173 TS women with tricuspid aortic valves were genotyped on Illumina Omni-Express arrays. Valve phenotypes were determined by independent review of echocardiograms from the enrolling sites. Tests of association were performed using logistic regression without adjustment for covariates and were summarized in a meta-analysis. Results: Xp dosage was inversely and quantitatively associated with BAV status (P=0.02). Large, recurrent copy number variants in 1p36.13, 3q29, 8p23.1 and 9p24.3 were significantly enriched in BAV cases. After exclusion of 26 outlier samples in multidimensional scaling analysis, there was no significant genomic inflation (lambda= 1.02). The strongest genome-wide association signals were observed in 1p36.23, 3q23, 12q21.2, 18q21 and 22q13.31, and did not overlap with previously reported loci for BAV. A total of 13 SNPs in 18q21 were positively associated with BAV (OR=2.5-4.3) with a minimum P value of 1x10-7. Replication of these regions in independent groups of cases is ongoing. Conclusion: Our results demonstrate that autosomal variants with large magnitudes of effect contribute to BAV in TS women, confirming our hypothesis, and provide evidence for gene-gene interactions in BAV formation.

Turner Syndrome (TS) is a developmental disorder caused by partial or complete loss of one sex chromosome. Bicuspid aortic valve and other left‐sided congenital heart lesions (LSL), including thoracic aortic aneurysms and acute aortic dissections, are 30–50 times more frequent in TS than in the general population. In 454 TS subjects, we found that LSL are significantly associated with reduced dosage of Xp genes and increased dosage of Xq genes. We also showed that genome‐wide copy number variation is increased in TS and identify a common copy number variant (CNV) in chromosome 12p13.31 that is associated with LSL with an odds ratio of 3.7. This CNV contains three protein‐coding genes (SLC2A3, SLC2A14, and NANOGP1) and was previously implicated in congenital heart defects in the 22q11 deletion syndrome. In addition, we identified a subset of rare and recurrent CNVs that are also enriched in non‐syndromic BAV cases. These observations support our hypothesis that X chromosome and autosomal variants affecting cardiac developmental genes may interact to cause the increased prevalence of LSL in TS. © 2016 Wiley Periodicals, Inc.

AbstractBicuspid aortic valve is the most prevalent cardiac valvular malformation. It is associated with a high rate of long‐term morbidity including development of calcific aortic valve disease, aortic regurgitation and concomitant thoracic aortic aneurysm and dissection. Recently, basic and translational studies have identified some key processes involved in the development of bicuspid aortic valve and its morbidity. The development of aortic valve disease and thoracic aortic aneurysm and dissection is the result of complex interactions between genotypes, environmental risk factors and specific haemodynamic conditions created by bicuspid aortic valve anatomy. Herein, we review the pathobiology of bicuspid aortic valve with a special emphasis on translational aspects of these basic findings. Important but unresolved problems in the pathology of bicuspid aortic valve and thoracic aortic aneurysm and dissection are discussed, along with the molecular processes involved.