C25 PREDICTION OF ALL–CAUSE MORTALITY FOLLOWING PERCUTANEOUS CORONARY INTERVENTION IN BIFURCATION LESIONS USING MACHINE LEARNING ALGORITHMS – THE RAIN–ML PREDICTION MODEL

Aims

Stratifying prognosis following coronary bifurcation percutaneous coronary intervention (PCI) is an unmet need. Machine learning (ML) may identify patterns from multidimensional, non–linear relationships to make outcome predictions. We sought to develop a ML–based risk stratification model built on clinical, anatomical and procedural features to predict all–cause mortality following contemporary bifurcation PCI.

Methods and Results

Multiple ML models to predict all–cause mortality were tested on a cohort of 2,393 patients (training, n = 1,795; internal validation, n = 598) undergoing bifurcation PCI with contemporary stents from the real–world RAIN (veRy thin stents for patients with left mAIn or bifurcatioN in real life) registry. Among 38 commonly available features, 25 (13 patient–related, 12 lesion–related) were selected to train ML models. The best performing model (the RAIN–ML prediction model) was validated in an external validation cohort of 1,701 patients undergoing bifurcation PCI from the DUTCH PEERS (DUrable polymer–based sTent CHallenge of Promus ElemEnt versus ReSolute integrity: TWENTE II) trial and the BIO–RESORT trial cohorts. The area under the receiver operating characteristic curves for the prediction of 2–year mortality was 0.786 (0.74–0.83) in the overall population, 0.736 (0.72–0.847) at internal validation and 0.706 (0.6919–0.794) at external validation. Performance at risk ranking analysis, k–center cross validation, and with continual learning confirmed the generalizability of the models, available also as an online interface.

Conclusions

The RAIN–ML prediction model represents the first tool combining clinical, anatomical and procedural features to predict all–cause mortality among patients undergoing contemporary bifurcation PCI with a good discriminative performance.

Machine learning applied to ambulatory blood pressure monitoring: a new tool to diagnose autonomic failure?

BACKGROUND

Autonomic failure (AF) complicates Parkinson's disease (PD) in one-third of cases, resulting in complex blood pressure (BP) abnormalities. While autonomic testing represents the diagnostic gold standard for AF, accessibility to this examination remains limited to a few tertiary referral centers.

OBJECTIVE

The present study sought to investigate the accuracy of a machine learning algorithm applied to 24-h ambulatory BP monitoring (ABPM) as a tool to facilitate the diagnosis of AF in patients with PD.

METHODS

Consecutive PD patients naïve to vasoactive medications underwent 24 h-ABPM and autonomic testing. The diagnostic accuracy of a Linear Discriminant Analysis (LDA) model exploiting ABPM parameters was compared to autonomic testing (as per a modified version of the Composite Autonomic Symptom Score not including the sudomotor score) in the diagnosis of AF.

RESULTS

The study population consisted of n = 80 PD patients (33% female) with a mean age of 64 ± 10 years old and disease duration of 6.2 ± 4 years. The prevalence of AF at the autonomic testing was 36%. The LDA model showed 91.3% accuracy (98.0% specificity, 79.3% sensitivity) in predicting AF, significantly higher than any of the ABPM variables considered individually (hypotensive episodes = 82%; reverse dipping = 79%; awakening hypotension = 74%).

CONCLUSION

LDA model based on 24-h ABPM parameters can effectively predict AF, allowing greater accessibility to an accurate and easy to administer test for AF. Potential applications range from systematic AF screening to monitoring and treating blood pressure dysregulation caused by PD and other neurodegenerative disorders.