Background and aim of the study: In clinical research, survival, reliability and failure analyses, the use of censored lifetime data often becomes a necessity. In this paper we present a novel methodology developed to allow for the use of censored data to train neural networks to predict the time of specific adverse events.

Methods and results: Specifically, for patients with implanted bioprostheses, we were able to design and train a neural system to successfully predict the time from valve implant to valve dysfunction. Further, we were able to demonstrate the clear improvement in performance and predictive accuracy of the system when trained using this method. The assertion that censored data carry additional and extremely valuable information, especially in cases of rare events, is substantiated by this correlation analysis.

Conclusions: This new methodology, in combination with results obtained from previous models which were able to identify the patients most likely to experience such events, now completes the picture by pin-pointing the 'who', as well as the 'when'.

How to cite: Katz, A. S., Katz, S., & van der Wal, E. A. (1996). Censored lifetime data in adaptive neural networks. The Journal of heart valve disease, 5(1), 84–89.