Random Survival Forests Analysis of Intraoperative Complicat
Now open: Certificate Course in Management of Covid-19 by Govt. Of Gujarat and PlexusMDKnow more...Now open: Certificate Course in Management of Covid-19 by Govt. Of Gujarat and PlexusMDKnow more...
A new analytic method can evaluate factors of interest associated with graft failure after Descemet stripping automated endothelial keratoplasty (DSAEK) or more generally in any ophthalmic surgical setting with a time-to-event outcome. The objective was to reanalyze types of intraoperative complications associated with Descemet stripping automated endothelial keratoplasty graft failure in the Cornea Preservation Time Study using random survival forests.

Descemet stripping automated endothelial keratoplasty with random assignment of a donor cornea with preservation time of 7 days or less or 8 to 14 days. This study included 1090 participants, representing 1330 eyes. Random survival forests ranked a Descemet stripping automated endothelial keratoplasty intraoperative complication as the third most predictive factor of graft failure, after surgeon and eye bank, in the final model with 5 predictors. In the first 47 months after Descemet stripping automated endothelial keratoplasty, the estimated mean difference in restricted mean survival time for grafts that experienced a Descemet stripping automated endothelial keratoplasty intraoperative complication vs those that did not was ?227 days based on the final RSF model.

Ranked variable importance for intraoperative complications among 50 donor, recipient, and eye bank variables and restricted mean survival time through 47 months (1434 days) after Descemet stripping automated endothelial keratoplasty were examined. Random survival forests, a nonparametric method (with less restrictive model assumptions) that is far more flexible in its ability to model nonlinear effects and interactions, were used to analyze the data.

These findings, while post hoc, support the hypothesis that random survival forests allow for an improved analytic approach for identifying factors predictive of graft failure and for obtaining adjusted graft survival estimates. Random survival forests offer the opportunity to guide the development of future population-based cohort ophthalmic surgical studies, establishing definitive factors for procedural success.

Source:https://jamanetwork.com/journals/jamaophthalmology/article-abstract/2774378
Like
Comment
Share