Recurrent event survival analysis predicts future risk of hospitalization in patients with paroxysmal and persistent atrial fibrillation

Abstract

Background In patients with paroxysmal atrial fibrillation (PAF) or persistent atrial fibrillation (PeAF) symptom burden and fear of hospital readmission are major causes of reduced quality of life. We attempted to develop a prediction model for future atrial fibrillation hospitalization (AFH) risk in PAF and PeAF patients including all previously experienced AFHs in the analysis, as opposed to time to first event. Methods Recurrent event survival analysis was used to model the impact of past AFHs on the risk of future AFHs. A recurrent event was defined as a hospitalization due to a new episode of AF. Death or progression to permanent AF were included as competing risks. Results We enrolled 174 patients with PAF or PeAF, mean follow up duration was 1279 days, and 325 AFHs were observed. Median patient age was 63.0 (IQR 52.2–68.0), 29% had PAF, and 71% were male. Highly significant predictors of future AFH risk were PeAF (HR 3.20, CI 2.01–5.11) and number of past AFHs observed (HR for 1 event: 2.97, CI 2.04–4.32, HR for ≥2 events: 7.54, CI 5.47–10.40). Conclusion In PAF and PeAF patients, AF type and observed AFH frequency are highly significant predictors of future AFH risk. The developed model enables risk prediction in individual patients based on AFH history and baseline characteristics, utilizing all events experienced by the patient. This is the first time recurrent event survival analysis has been used in AF patients.

Associations of Atrial Fibrillation Patterns With Mortality and Cardiovascular Events: Implications of the MISOAC-AF Trial

“…Regarding hospitalizations, a recent small study suggested that persistent AF be associated with higher future AF-hospitalizations. 22 We consider our findings important from an epidemiological perspective, given the association of multiple hospitalizations with an impaired quality of life and an increased financial burden worldwide. 7,[23][24][25] No significant differences in stroke incidence were detected among all AF patterns.…”

Pitfalls in Time-to-Event Analysis of Registry Data: A Tutorial based on Simulated and Real Cases

“…In practice, this means that having already experienced one or more recurrent events may or may not influence the risk of further occurrences. This is a remarkable feature of the confidence interval formula because in practice, patients that have already experienced an event are often more likely to experience future occurrences (22).…”

Exploring causal mechanisms and quantifying direct and indirect effects using a joint modeling approach for recurrent and terminal events

“…Such recurrent events are often highly associated with patients' disease progression and survival. [1][2][3][4] There is significant interest in comprehending the relationship between recurrent events and terminal events. [5][6][7][8][9] Specifically, there is an urgent need for appropriate methods to thoroughly examine the role of these recurrent events in the causal pathway between exposure to time-to-event outcomes, such as death, failure, relapse, or the emergence of a new illness.…”

“…Examples include repeated asthma attacks, recurrent hospitalizations, recurrence of leukemia and other cancers, as well as multiple opportunistic infections (OIs) in Human Immunodeficiency Virus (HIV)‐infected patients. Such recurrent events are often highly associated with patients' disease progression and survival 1‐4 . There is significant interest in comprehending the relationship between recurrent events and terminal events 5‐9 .…”