Modelling multiple time-scales with flexible parametric survival models.

BACKGROUND: There are situations when we need to model multiple time-scales in survival analysis. A usual approach in this setting would involve fitting Cox or Poisson models to a time-split dataset. However, this leads to large datasets and can be computationally intensive when model fitting, especially if interest lies in displaying how the estimated hazard rate or survival change along multiple time-scales continuously. METHODS: We propose to use flexible parametric survival models on the log hazard scale as an alternative method when modelling data with multiple time-scales. By choosing one of the time-scales as reference, and rewriting other time-scales as a function of this reference time-scale, users can avoid time-splitting of the data. RESULT: Through case-studies we demonstrate the usefulness of this method and provide examples of graphical representations of estimated hazard rates and survival proportions. The model gives nearly identical results to using a Poisson model, without requiring time-splitting. CONCLUSION: Flexible parametric survival models are a powerful tool for modelling multiple time-scales. This method does not require splitting the data into small time-intervals, and therefore saves time, helps avoid technological limitations and reduces room for error.

Survival and risk of vascular complications in myelofibrosis-A population-based study from the Swedish MPN group.

OBJECTIVE: To gain knowledge of underlying risk factors for vascular complications and their impact on life expectancy in myelofibrosis. METHODS: From a cohort of 392 myelofibrosis patients registered in the Swedish MPN registry 58 patients with vascular complications during follow-up were identified. Patients with vascular complications were compared with both 1:1 matched controls and the entire myelofibrosis cohort to explore potential risk factors for vascular complications and their impact on survival. RESULTS: Incidence of vascular complications was 2.8 events per 100 patient-years and the majority of complications were thrombotic. Patients with complications were significantly older and had lower hemoglobin when compared to the entire cohort. In the case-control analysis, no significant risk factor differences were observed. The major cause of death was vascular complications and median survival was significantly impaired in patients with vascular complications (48 months) compared to controls (92 months). Inferior survival in patients with vascular complications was found to be dependent on IPSS risk category in a Cox regression model. CONCLUSION: Vascular complications have a considerable impact on survival in MF. At diagnosis, risk assessment by IPSS does not only predict survival but is also associated with the risk of vascular complications.

Highly reduced survival in essential thrombocythemia and polycythemia vera patients with vascular complications during follow-up.

OBJECTIVE: To explore the relative importance of risk factors, treatments, and blood counts for the occurrence of vascular complications and their impact on life expectancy in essential thrombocythemia (ET) and polycythemia vera (PV). METHODS: Nested case-control study within the Swedish MPN registry. From a cohort of 922 ET patients and 763 PV patients, 71 ET and 81 PV cases with vascular complications were compared with matched controls. RESULTS: Incidence of vascular complications was 2.0 and 3.4 events per 100 patient-years in ET and PV, respectively. At diagnosis, no significant risk factor differences were observed between cases and controls in neither of the diseases. At the time of vascular event, ET complication cases did not differ significantly from controls but in PV, cases had significantly higher WBCs and were to a lesser extent treated with anti-thrombotic and cytoreductive therapy. Life expectancy was significantly decreased in both ET and PV cases compared with controls. CONCLUSIONS: The risk of vascular complications is high in both ET and PV, and these complications have a considerable impact on life expectancy. The protective effect of anti-thrombotic and cytoreductive therapy for vascular complications in PV underscores the importance of avoiding undertreatment.