Search

Aims Our aim was to develop a machine learning (ML)-based risk stratification system to predict 1-, 2-, 3-, 4-, and 5-year all-cause mortality from pre-implant parameters of patients undergoing cardiac resynchronization therapy (CRT). Methods and results Multiple ML models were trained on a retrospective database of 1510 patients undergoing CRT implantation to predict 1- to 5-year all-cause mortality. Thirty-three pre-implant clinical features were selected to train the models. The best performing model [SEMMELWEIS-CRT score (perSonalizEd assessMent of estiMatEd risk of mortaLity With machinE learnIng in patientS undergoing CRT implantation)], along with pre-existing scores (Seattle Heart Failure Model, VALID-CRT, EAARN, ScREEN, and CRT-score), was tested on an independent cohort of 158 patients. There were 805 (53%) deaths in the training cohort and 80 (51%) deaths in the test cohort during the 5-year follow-up period. Among the trained classifiers, random forest demonstrated the best performance. For the prediction of 1-, 2-, 3-, 4-, and 5-year mortality, the areas under the receiver operating characteristic curves of the SEMMELWEIS-CRT score were 0.768 (95% CI: 0.674–0.861; P Conclusion The SEMMELWEIS-CRT score (available at semmelweiscrtscore.com) exhibited good discriminative capabilities for the prediction of all-cause death in CRT patients and outperformed the already existing risk scores. By capturing the non-linear association of predictors, the utilization of ML approaches may facilitate optimal candidate selection and prognostication of patients undergoing CRT implantation.

Introduction In patients with chronic heart failure (CHF) left ventricular dysfunction results in elevated left atrial (LA) pressure, triggering pathological atrial remodelling and atrial fibrillation (AF). Nevertheless, it has been reported that some patients with CHF remain in sinus rhythm (SR) despite of the pathological structural alterations (e.g. dilation and fibrosis) of the LA. Of particular interest, data is scarce regarding the molecular explanation for the observed variability in AF development among CHF patients. Recent studies have indicated that alterations in microRNA (miRNA) expression might contribute to the pathogenesis of AF. However, the majority of previous studies focusing on miRNA expression compared healthy LA with SR to pathologically remodelled, dilated LA with AF. Consequently, whether dysregulation of miRNA expression directly contribute to AF and not only to pathological LA remodelling has not been tested before. Purpose The present study aimed to investigate miRNA expression in comparably remodelled LA from end-stage CHF patients with permanent AF (CHF-AF) or SR (CHF-SR). Methods LA samples were collected from male, non-diabetic, ischemic end-stage CHF patients undergoing heart transplantation (n=24). Patients were carefully selected to avoid any differences in age (55±2 vs. 54±2 years, CHF-AF vs. CHF-SR, n.s.), ejection fraction ([EF]: 22.5±1.8 vs. 23.3±2.5%, CHF-AF vs. CHF-SR, n.s.) LA diameters (longitudinal LA diameter: 56±4 vs. 48±5mm.; CHF-AF vs. CHF-SR, n.s.; horizontal LA diameter: 61±2 vs. 54±3, CHF-AF vs. CHF-SR, n.s.) and NYHA stage. As a molecular marker of atrial load, the mRNA expression of atrial natriuretic peptide (ANP) was measured with qRT-PCR. The extent of left atrial fibrosis was assessed on picrosirius red stained histological sections. Global LA miRNA expression profiling (including the measurement of 800 human miRNA) was carried out using a commercially available kit. Results LA mRNA expression of ANP was comparable between the AF-CHF and the SR-CHF groups, suggesting that atrial load occurred to the same level in the two experimental groups. Furthermore, no differences could be observed in the extent of atrial collagen content between the AF-CHF and the SR-CHF groups (collagen area: 20.3±1.3% vs. 23.9±3.1%, n.s.), providing evidence that fibrotic remodelling had occurred to a similar magnitude. The high-throughput miRNA measurement revealed no differences in atrial miRNA expression between the two study groups. Conclusion The present study provides evidence for the first time that AF is not associated with different LA miRNA expression in end-stage CHF patients with comparable level of LA dilatation, ANP expression (atrial load) and interstitial fibrosis. Based on these findings, the potential of miRNA-based therapeutic interventions might be limited in AF patients with ischemic end-stage CHF. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): NVKP_16-1-2016-0017

Background Cardiac Resynchronization Therapy (CRT) has well-known beneficial effects in patients with advanced heart failure, reduced ejection fraction and wide QRS complex. However, mortality rates still remain high in this patient population. Therefore, precise risk stratification would be essential, nonetheless, the currently available risk scores have several shortcomings which hamper their utilization in the everyday clinical practice. Purpose Accordingly, our objective was to design and validate a machine learning based risk stratification system to predict 2-year and 5-year mortality from pre-implant parameters of patients undergoing CRT implantation. Methods We trained two models separately to predict 2-year (model 1) and 5-year mortality (model 2). As training cohort of model 1 we used 1678 patients (67±10 years, 1251 [75%] males) undergoing CRT implantation. From this population, 1320 patients (66±10 years, 1005 [76%] males) also completed 5-year follow-up and they served as the training cohort for model 2. Forty-seven pre-implant parameters (demographics, cardiovascular risk factors and clinical characteristics) were used to train the models. Our models were designed in a way to tolerate missing values. Among non-linear classifiers, random forest demonstrated the best performance. We validated our models, along with the Seattle Heart Failure Model (SHFM), VALID-CRT risk score and EAARN score on an independent cohort of 136 patients (66±10 years, 110 [81%] males). Based on the predicted probability of survival, patients were split into quartiles and survival was plotted via Kaplan-Meier (KM) curves. Results There were 358 (21%) deaths in the 2-year, 697 (53%) deaths in the 5-year training cohort. In the validation cohort, there were 30 (22%) deaths at 2 years and 58 (43%) deaths at 5 years after CRT implantation. For the prediction of 2-year mortality, the Area Under the Receiver-Operating Characteristic Curve (AUC) for model 1 was 0.77 (95% CI: 0.67–0.87; p=0.002), for SHFM was 0.54 (95% CI: 0.39–0.69; p=0.006), for EAARN was 0.57 (95% CI: 0.46–0.68, p=0.002), and for VALID-CRT was 0.62 (95% CI: 0.52–0.71; p=0.002). To predict 5-year mortality, the AUC for model 2 was 0.85 (95% CI: 0.78–0.91; p=0.001), for SHFM was 0.62 (95% CI: 0.51–0.74; p=0.003), for EAARN was 0.61 (95% CI: 0.51–0.70, p=0.002), for VALID-CRT was 0.65 (95% CI: 0.56–0.74; p=0.002). The AUCs of the machine learning based models were significantly higher than the AUCs of the pre-existing scores (DeLong test, all p Conclusion Our results indicate that machine learning algorithms can outperform the already existing linear model based scores. By capturing the non-linear association of predictors, the utilization of these state-of-the-art approaches may facilitate optimal candidate selection and prognostication of patients undergoing CRT implantation.