BACKGROUND Hypertrophic cardiomyopathy (HCM) is a heart disease characterized by hypertrophy of the left ventricular myocardium. HCM is the most common cause of sudden cardiac death (SCD) in young people and competitive athletes due to fatal ventricular arrhythmias. However, in most patients, HCM has a benign course. That is why it is of utmost importance to properly evaluate patients and identify those who would benefit from a cardioverter-defibrillator (ICD) implantation. The HCM SCD-Risk Calculator is a useful tool for estimating the risk of SCD. The parameters included in the model at evaluation are: age, maximum left ventricular (LV) wall thickness, left atrial (LA) dimension, maximum gradient in left ventricular outflow tract, family history of SCD, non-sustained ventricular tachycardia (nsVT) and unexplained syncope. Nevertheless, there is potential to improve and optimize the effectiveness of this tool in clinical practice. Therefore, the following new risk factors are proposed: LV global longitudinal strain (GLS), LV average strain (ASI) and LA volume index (LAVI). GLS and ASI are sensitive and noninvasive methods of assessing LV function. LAVI more accurately characterizes the size of the left atrium in comparison to the LA dimension. METHODS 252 HCM patients (aged 20-88 years, of which 49,6% were men) treated in our Department from 2005 to 2018, were examined. The follow-up period was 0-13 years (average: 3.8 years). SCD was defined as sudden cardiac arrest (SCA) or an appropriate ICD intervention. All patients underwent an echocardiographic examination. The medical and family histories were collected and ICD examinations were performed. RESULTS 76 patients underwent an ICD implantation during the follow-up period. 20 patients have reached an SCD end-point. 1 patient died due to SCA and 19 had an appropriate ICD intervention. There were statistically significant differences of GLS and ASI values between SCD and non-SCD groups; p = 0.026389 and p = 0.006208, respectively. The average GLS in the SCD group was -12.4% ± 3.4%, and -15.1% ± 3.5% in the non-SCD group. The average ASI values were -9.9% ± 3.8% and -12.4% ± 3.5%, respectively. There was a statistically significant difference between LAVI values in SCD and non-SCD groups; p = 0.005343. The median LAVI value in the SCD group was 45.7 ml/m2 and 37.6 ml/m2 in the non-SCD group. The ROC curves showed the following cut-off points for GLS, ASI and LAVI: -13.8%, -13.7% and 41 ml/m2, respectively. Cox’s proportional hazards model for the parameters used in the Calculator was at the borderline of significance; p = 0.04385. The model with new variables (GLS and LAVI instead of LA dimension) was significant; p = 0.00094. The important factors were LAVI; p = 0.000075 and nsVT; p = 0.012267. CONCLUSIONS The proposed new SCD risk factors were statistically significant in the study population and should be taken into account when considering ICD implantation.

BACKGROUND Hypertrophic cardiomyopathy (HCM) is a heart disease characterized by hypertrophy of the left ventricular myocardium. The disease is the most common cause of sudden cardiac death (SCD) in young people and competitive athletes due to fatal ventricular arrhythmias, but in most patients, however, HCM has a benign course. Therefore, it is of the utmost importance to properly evaluate patients and identify those who would benefit from a cardioverter-defibrillator (ICD) implantation. The HCM SCD-Risk Calculator is a useful tool for estimating the 5-year risk of SCD. Parameters included in the model at evaluation are: age, maximum left ventricular wall thickness, left atrial dimension, maximum gradient in left ventricular outflow tract, family history of SCD, non-sustained ventricular tachycardia and unexplained syncope. Patients’ risk of SCD is classified as low (<4%), intermediate (4-<6%) or high (≥6%). Those in the high-risk group should have an ICD implantation. It can also be considered in the intermediate-risk group. However, the calculator still needs improvement and machine learning (ML) has the potential to fulfill this task. ML algorithm creates a model for solving a specific problem without explicit programming - instead it relies only on available data - by discovering patterns and relations. METHODS 252 HCM patients (aged 20-88 years, 49,6% were men) treated in our Department from 2005 to 2018, have been enrolled. The follow-up lasted 0-13 years (average: 3.8 years). SCD was defined as sudden cardiac arrest (SCA) or an appropriate ICD intervention. All parameters from HCM SCD-Risk Calculator have been obtained and the risk of SCD has been calculated for all patients during the first echocardiographic evaluation. ML model with variables from HCM SCD-Risk Calculator has been created. Both methods have been compared. RESULTS 20 patients reached an SCD end-point. 1 patient died due to SCA and 19 had an appropriate ICD intervention. Among them, there were respectively 6, 7 and 7 patients in the low, intermediate and high-risk group of SCD. 1 patient, who died, had a low risk. The ML model correctly assessed the SCD event only in 1 patient. According to ML, the risk of SCD ≤2.07% was a negative predictor. CONCLUSIONS The study did not show an advantage of ML over HCM SCD-Risk Calculator. Because of the characteristic of the dataset (approximately the same number of features and observations), the selection of machine learning algorithms was limited. Best results (evaluated using LOOCV) were achieved with a decision tree. We expect that bigger dataset would allow improving model performance because of strong regularization need in the current setup.

BACKGROUND Hypertrophic cardiomyopathy (HCM) is a heart disease characterized by hypertrophy of the left ventricular myocardium. The structural and functional abnormalities cannot be explained by flow-limiting coronary artery disease or loading conditions. HCM has a benign course, however approximately 5% of these patients suffer from the end-stage of the disease. The so-called burned-out phase, characterized by systolic dysfunction with a left ventricular ejection fraction ≤50%, is often associated with wall thinning and chamber dilation. These patients should have more frequent clinic visits and have a more intensive treatment plan. They are also candidates for heart transplantation. Currently there are no risk factors of progression to burned-out phase before the onset of heart failure symptoms. Therefore, the potential risk factors: left ventricular global longitudinal strain (GLS), left ventricular average strain (ASI), right ventricular average strain (RV-ASI) and left atrial volume index (LAVI), have been examined. GLS, derived from speckle tracking echocardiography, and ASI, derived from tissue doppler imaging, are the sensitive and noninvasive methods of assessing the ventricular function. LAVI more accurately characterizes the size of the left atrium, which usually increases in the course of the disease. METHODS A total of 252 patients with HCM (aged 20-88 years, 49,6% were men), treated in our Department have been enrolled in the study. GLS, ASI, RV-ASI and LAVI assessment has been made in addition to standard echocardiographic examination. Burned-out was characterized as systolic dysfunction with a left ventricular ejection fraction ≤50%. RESULTS 5.6% patients in the study population were diagnosed with burned-out phase in hypertrophic cardiomyopathy. The t-Student test and t-Student test with Cochran-Cox adjustment showed statistically significant differences of GLS and ASI values between burned-out and non-burned-out groups; p = 0.000001 and p < 0.000001, respectively. Average and median values of GLS in burned-out group were -7.4% ± 2.9%, -7.1% and -15.3% ± 4.3%, -15.4% in non-burned-out group. For ASI those values were respectively -7.6% ± 2.2%, -7.1% and -12.9% ± 4.5%, -13.0%. The Mann-Whitney test showed statistically significant differences of RV-ASI and LAVI values between burned-out and non-burned-out groups; p = 0.000208 and p = 0.005302, respectively. Median value of RV-ASI in burned-out group was -15.8% and -27.1% in non- burned-out group. Median value of LAVI in burned-out group was 52.6 ml/m2 and 37.8 ml/m2 in non-burned-out group. CONCLUSIONS Each of the proposed new risk factors of burned-out development was statistically significant in the study population. Therefore, all HCM patients should have regular echocardiographic examinations and those with deteriorating values of new parameters should become the subjects of intensified medical care.