Electrocardiographic parameter profiles for differentiating hypertrophic cardiomyopathy stages

We read the article “Electrocardiographic parameter profiles for differentiating hypertrophic cardiomyopathy stages” by Hirota et al., published in the Journal of Arrhythmia, with great interest. We appreciate the authors' remarkable efforts in investigating the role of electrocardiographic (ECG) parameters in differentiating between the stages of hypertrophic cardiomyopathy (HCM) and its progression to dilated hypertrophic cardiomyopathy (DCM), optimized with AI-enhanced diagnostic models.1 While providing valuable insights, it is important to acknowledge specific concerns that merit our attention. The study excludes conditions such as active cancers; it does not explicitly account for potential confounders such as undiagnosed metabolic conditions, medication use, or lifestyle factors that could influence ECG findings. A case reported by Garcia-Granja et al. highlights the use of propafenone, a class IC antiarrhythmic drug, which can adversely affect ECG interpretability in patients with hypertrophic cardiomyopathy.2 Propafenone significantly altered ECG parameters such as PR interval and QRS duration by worsening conduction delays. These changes obscure cardiac conditions and potentially lead to misdiagnosis. Furthermore, limited follow-up data make it challenging to track gradual changes in ECG parameters that may show the transition from HCM to dHCM. Kagumi et al. provide strong evidence on how serial ECG changes can be early markers of progression from HCM to dHCM.3 Moreover, they showed that progression to dHCM was associated with a higher incidence of ventricular tachycardia and cardiac death, underscoring the need for longitudinal ECG monitoring as a predictive and preventive strategy in patients with HCM. Because of ethnic and demographic variations, different genetic predispositions to HCM, and significant disparities in healthcare access, these findings may not be widely applicable,4 as the study is based on a Japanese cohort. An attempt to use AI-based models to analyze ECG parameters lacks explainability on how AI interprets the ECG features. This makes it difficult for clinicians to rely on and apply the findings in real-world settings.5 Hirota et al. present a meticulous analysis and valuable insights into the role of ECG parameters in diagnosing and differentiating HCM and its dilated phase (dHCM), making a significant contribution to cardiovascular medicine. Nevertheless, a more detailed investigation integrating lifestyle influences, genetic testing, and specific comorbidities is needed to better analyze the subgroups with or without comorbidities. Our assessment underscores the importance of broadening the focus of future studies beyond the use of ECG to provide critical validation of findings. Also, improving the study's real-world clinical applicability should be a priority beyond technical refinements. These steps would contribute to a more comprehensive, clinically beneficial, and widely applicable approach to diagnosing and monitoring HCM. Author Muhammad Shaheer Bin Faheem contributed to Conceptualization, Writing—Original Draft, Writing—Review & Editing, Data curation, Supervision, and Project administration. Author Nisha Khatri contributed to Conceptualization, Writing—Original Draft, and Data curation. Author Shamikha Cheema and Muhammad Rehan Zahid contributed to Investigation and Data Curation. Author Sumaya Samadi contributed to Project administration. Authors declare no conflict of interests for this article. No new data generated.