Aguirre, Mateo Alzate

Introduction: Hypertrophic cardiomyopathy (HCM) is a disease characterized by genotypic and phenotypic heterogeneity. Correct classification of genetic variation is critical for clinical interpretation. Herein, variants of uncertain significance (VUS) pose a dilemma in clinical practice, limiting physicians’ decision making and causing anguish to patients and family members. Furthermore, with increasing knowledge and changing guidelines, continuous reassessment is crucial to maintain usefulness in practice. This study sought to assess contemporary variant classification in a large cohort of patients with HCM. Methods: Retrospective analysis of all patients with HCM seen at Mayo Clinic and all patients with a variant in one of 8 genes with strong disease association for HCM were included. Genetic test reports were obtained from electronic health records along with their original variant classification assigned by either a commercial or research laboratory. Reassessment of variant pathogenicity was performed using the 2015 ACMG guideline criteria. Population frequency was obtained using Gnomad. Co-segregation presence or absence was determined by family history and co-segregation studies. Combined Annotation Dependent Depletion (CADD) was used as computational evidence of genetic deleterious effects for single nucleotide variants. Results: Between 2003 to 2019, a total of 1,782 patients underwent laboratory or commercial HCM genetic testing. Of these, 787 (44%) had positive genetic test with a variant at least 1 of the 8 genes. The original pathogenic classification was obtained for 754 patients. Of those, 430 (57%) variants where within the gene MYBPC3, 244 (32%) within MYH7 and 80 (11%) within either ACTC1, MYL2, MYL3, TINNI3, TNNT2 or TPM1. Overall, 222 patients (29%) originally had one or more variants classified as a VUS. Upon reassessment, 120 (54%) were reclassified as either pathogenic (33%), likely pathogenic (58%), benign (5%) or likely benign (3%). Conclusion: Periodic reassessment for HCM genetic variants, especially VUS, is critical for adequate patient care and management. Cascade screening could decrease patients’ uncertainty regarding their prognosis and management.

Abstract Hypertrophic Cardiomyopathy (HCM) is an inheritable heart disease with the highest rate of sudden cardiac death (SCD) in young adults. Implantable Cardioverter Defibrillator (ICD) therapy is recommended for HCM patients at high risk for SCD. Reviewing the recent clinical literature revealed the potential to improve the selection of candidates for ICD implantation. The current study uses information extracted from echocardiography reports to evaluate HCM patients with ICD and aims to provide a comparative insight into patients who benefited the most from the device therapy, including shock and anti-tachycardia pacing (ATP). The proposed interpretable machine learning approach has used the XGboost algorithm. The model’s performance was considered satisfactory, as evidenced by an accuracy score of 81% and an area under the receiver operating characteristic curve (AUC) value of 69% and SHapley Additive exPlanations (SHAP) identified common properties of HCM patients in each category and provided high-level reasoning and foundation for a clinical decision support tool.