Rubén Andrés Nisperuza Franco

Cardiomyopathies constitute a heterogeneous group of myocardial disorders that frequently remain clinically silent until advanced stages, limiting opportunities for early intervention and prevention of adverse outcomes. Although the 12-lead electrocardiogram (ECG) is one of the most accessible diagnostic tools in cardiovascular care, its conventional interpretation has limited sensitivity for detecting early or subclinical myocardial disease. In recent years, deep-learning approaches have enabled a paradigm shift in ECG analysis by allowing the extraction of complex and subtle signal patterns associated with underlying structural and functional cardiac abnormalities. This review synthesizes current evidence on deep-learning–based ECG algorithms for the silent detection of cardiomyopathies, with particular emphasis on hypertrophic cardiomyopathy and subclinical ventricular dysfunction. The analysis highlights methodological strategies, reference standards, and validation approaches used across key studies, as well as their potential clinical and educational implications. The findings suggest that deep-learning ECG analysis can function as an effective screening and risk-stratification tool, facilitating earlier identification of individuals who may benefit from confirmatory imaging and specialist evaluation. This approach is especially relevant for healthcare systems in Mexico, Colombia, and Ecuador, where access to advanced diagnostic resources may be limited. Continued research focusing on external validation, population-specific calibration, and real-world implementation is essential to ensure safe and effective integration into clinical practice.

Metabolic frailty has traditionally been associated with older populations; however, accumulating evidence suggests that frailty-related metabolic alterations may emerge much earlier in the life course. This narrative review examines metabolic frailty in young adults as an early vulnerability state characterized by metabolic dysregulation, adverse body composition, chronic low-grade inflammation, and reduced physiological reserve, even in the absence of overt chronic disease. Drawing on international literature and integrating evidence relevant to Latin American contexts, particularly Mexico, Colombia, and Ecuador, this study synthesizes current knowledge on the biological and clinical pathways linking central adiposity, insulin resistance, sarcopenia-related changes, and cardiometabolic risk clustering to early frailty-related processes. The findings support the interpretation of metabolic frailty as a continuous, multidimensional construct that extends classical frailty frameworks beyond geriatric populations. Early identification of metabolic frailty using combined anthropometric, metabolic, and muscle-related indicators may provide a valuable opportunity to prevent or delay the onset of chronic noncommunicable diseases and preserve long-term functional capacity.

Clinically significant drug–drug interactions (DDIs) remain a major source of preventable harm in modern pharmacotherapy, particularly in patients exposed to polypharmacy and complex medication regimens. Traditional rule-based clinical decision support systems have contributed to improved medication safety but are frequently limited by alert fatigue, inadequate prioritization, and limited support for actionable clinical decisions. In recent years, deprescribing has emerged as a structured, patient-centered strategy to reduce medication burden and optimize therapeutic outcomes. This review examines the convergence of deprescribing principles with algorithm-driven decision support, a concept referred to as smart deprescribing, aimed at proactively reducing clinically significant DDIs. Through an integrative analysis of international evidence, this study synthesizes findings on rule-based systems, machine learning, and deep learning approaches, highlighting their respective strengths, limitations, and roles within deprescribing-oriented frameworks. The results indicate that algorithm-assisted deprescribing can improve prioritization of high-risk interactions, reduce low-value alerts, and support medication optimization when grounded in robust clinical frameworks. The review further explores implementation pathways across diverse healthcare contexts, including middle-income settings, emphasizing the importance of scalability, interpretability, and workflow integration. Overall, smart deprescribing represents a promising evolution in medication safety that complements clinical judgment while supporting rational prescribing and medical education.