Utilization of manufacturers' implant card data to estimate heart valve failure

Heart valve manufacturers possess the most complete inventory of world-wide mechanical valve failures, but to convert failures to time-related risks requires estimates of patient follow up. Since manufacturers did not actively track patients, they needed a model that incorporates an assumed death rate to decrease the numbers of patients at risk. We present a method for using a manufacturer's implant card database to estimate time-related complication rates for patient subsets, and illustrate its use by examining the risk of outlet strut fracture (OSF) with the Björk-Shiley 60 degrees Convexo-Concave valve (CC60). We developed a parametric model for valve patient survival based on actively followed valve patients from three centers using only variables typically available from implant cards. Using this survival model, a simulated lifetime was produced for each valve in the CC60 implant database for which the required covariates were known. These lifetimes were then used to analyze OSF as if they were true follow up times. This allowed the use of conventional methods of univariate and multivariate analysis for OSF, including parametric statistical models. According to the approximate linearity of the cumulative hazard functions, OSF risk over time appeared to be fairly constant. Several risk factors were identified, including valve size, patient age at implant and valve position. Using parametric models for both patient survival and OSF permits the estimation of the probability of OSF before death for an individual patient (as opposed to the usual actuarial probability of OSF given that the patient does not die). Because the patient may die before his valve would have failed, this cumulative incidence of OSF is always less than the actuarial risk. For all but the very highest risk patients, the cumulative incidence over their relatively short remaining lifetimes is very small.