PhD Scientific Days 2019

Budapest, April 25–26, 2019

Survival Prediction in Patients Undergoing Cardiac Resynchronization Therapy: A Machine Learning Based Risk Stratification System

Tokodi, Márton

Márton Tokodi MD
Heart and Vascular Center, Semmelweis University, Budapest, Hungary

Language of the presentation


Text of the abstract

Introduction: 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.
Aims: 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 2098 patients undergoing CRT implantation. From this population, 1650 patients also completed 5-year follow-up and they served as the training cohort for model 2. Forty-seven pre-implant parameters were used to train the non-linear classifiers (random forest). We validated our models, along with the Seattle Heart Failure Model (SHFM), VALID-CRT and EAARN scores on an independent cohort of 136 patients.
Results: For the prediction of 2-year mortality, the 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=0.314), for EAARN was 0.57 (95%CI: 0.46-0.68, p=0.115), and for VALID-CRT was 0.62 (95%CI: 0.52-0.71; p=0.019). 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=0.021), for EAARN was 0.61 (95%CI: 0.51-0.70, p=0.014), for VALID-CRT was 0.65 (95%CI: 0.56-0.74; p<0.001). The Kaplan-Meier curves of the quartiles were significantly separating in both models (all p<0.001).
Conclusion: Our results indicate that machine learning algorithms can outperform the already existing risk 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.

Data of the presenter

Doctoral School: Basic and Translational Medicine, Károly Rácz School of PhD Studies, Semmelweis University
Program: Cardiovascular Disorders: Physiology and Medicine of Ischaemic Circulatory Diseases
Supervisor: Attila Kovács MD PhD