Log in to MyACC
Predicting Long-Term Clinical Outcomes in Recurrent Pericarditis
Quick Takes
- A risk stratification scheme based on patient age, sex, heart rate, etiology, LVEF, LGE on cardiac MRI, prior recurrence, and steroid or colchicine use identifies patients at risk of recurrent pericarditis.
- This model will allow clinicians to better identify patients at higher risk for recalcitrant pericarditis, implement appropriate preventive measures, and ultimately reduce morbidity and improve the quality of life for those affected by recurrent pericarditis.
Study Questions:
What are the factors associated with long-term outcomes in patients with recurrent pericarditis?
Methods:
The investigators retrospectively studied a total of 365 consecutive patients with recurrent pericarditis from 2012 to 2019. The primary outcome was clinical remission, defined as cessation of all anti-inflammatory therapy with complete resolution of symptoms. Five machine learning survival models were used to calculate the likelihood of clinical remission within 5 years and stratify patients into high-risk, intermediate-risk, and low-risk groups. The Kaplan-Meier method was employed to construct survival curves, which were then compared using the multivariate log-rank test. The Cox proportional hazards model was used to calculate the hazard ratios for the events.
Results:
Among the cohort, the mean age was 46 ± 15 years, and 205 (56%) were women. Clinical remission was achieved in 118 (32%) patients. The final model included steroid dependency, total number of recurrences, pericardial late gadolinium enhancement (LGE), age, etiology, sex, left ventricular ejection fraction (LVEF), and heart rate as the most important parameters. The model predicted the outcome with a c-index of 0.800 on the test set and exhibited a significant ability in stratification of patients into low-risk, intermediate-risk, and high-risk groups (log-rank test; p < 0.0001).
Conclusions:
The authors report a novel risk-stratification model for predicting clinical remission in recurrent pericarditis.
Perspective:
This study reports a survival model to predict the long-term outcomes in patients with recurrent pericarditis and identify those at risk for recalcitrant pericarditis. Furthermore, this risk stratification scheme based on patient age, sex, heart rate, etiology, LVEF, LGE on cardiac magnetic resonance imaging (MRI), prior recurrence, and steroid or colchicine use identifies patients at risk of recurrent pericarditis. This model will allow clinicians to better identify patients at higher risk for recalcitrant pericarditis, implement appropriate preventive measures, and ultimately reduce morbidity and improve the quality of life for those affected by recurrent pericarditis. Overall, this study highlights the favorable role of the novel risk stratification model in advancing personalized medicine and enhancing clinical decision-making in recurrent pericarditis.
Clinical Topics: Cardiovascular Care Team, Pericardial Disease, Prevention
Keywords: Machine Learning, Pericardium, Risk Assessment
< Back to Listings
