Diastolic dysfunction (DD) is often associated with impaired relaxation, loss of restorative forces, reduced compliance during diastole, and elevated filling pressures within the left ventricular cavity. Various conditions have been linked to the development of DD, and evaluation for DD is most common during an evaluation of heart failure with preserved ejection fraction. Although the gold standard for assessing diastolic function is an invasive hemodynamic study, that is often inaccessible or unpragmatic in clinical settings. Therefore, sonography, specifically echocardiography, is the first-line modality for DD assessment. This review article details the what (i.e., what is diastolic function and dysfunction), when (i.e., when should diastolic function be measured, and when is caution advised) and how (i.e., how should diastolic function be measured) of DD assessment via sonography. For the sake of pragmatism and familiarity, the American Society of Echocardiography/ European Association of Cardiovascular Imaging 2016 algorithms will be discussed in this article. However, clinicians should familiarize themselves with the limitations of those algorithms. Through advances in the field of diastology, including the use of strain imaging, assessment of diastolic function will continue to become more inclusive and comprehensive.

Artificial intelligence (AI) has revolutionized multiple domains of cardiovascular patient care and is being increasingly applied at different stages of the echocardiography workflow. Contemporary applications include automated view classification, real-time image quality guidance, chamber and function assessments (ejection fraction, chamber volumes, strain), and assisted diagnosis of cardiac conditions, such as heart failure, valvular disease, and cardiomyopathies. In some domains of echocardiography, AI algorithms can match or surpass the performance of human experts. Recent advances in large language models and multi-modal vision-language models have paved the way for complete end-to-end echocardiographic report generation. In this narrative review, we provide an introductory survey of the landscape of currently available AI tools for enhancing each step of the echocardiography workflow. We aim to equip practising community physicians with frameworks to understand and apply AI-based ultrasound technologies in an informed manner. By understanding current applications and limitations, and by selecting tools judiciously, clinicians may safely integrate AI into echocardiography practice to improve patient care.

Danon disease is a rare genetic cardio-skeletal myopathy. We present a case of an 18-year-old patient experiencing intermittent chest pain, dyspnea, and palpitations. Initial investigations unveiled elevated NT-pro brain natriuretic peptide, creatinine kinase, and cardiac enzyme levels.Electrocardiogram findings displayed left ventricular hypertrophy with a strain pattern and left bundle branch block. Transthoracic echocardiography and cardiac magnetic resonance imaging confirmed severe concentric left ventricular hypertrophy, accompanied by late gadolinium enhancement in specific myocardial regions. Genetic testing identified prevalent frameshift mutations in the lysosomal-associated membrane protein-2 (LAMP2) gene, indicative of Danon disease. This condition manifests as a severe, early-onset cardiomyopathy with associated complications such as heart failure, arrhythmias, and conduction disturbances, particularly in males. Diagnosis relies on genetic evidence, emphasizing the significance of testing in conjunction with clinical and imaging tools.