Editorial comment on: development, validation, and head-to-head comparison of logistic regression-based nomograms and artificial neural network models predicting prostate cancer on initial extended biopsy.

@article{Kattan2008EditorialCO,
  title={Editorial comment on: development, validation, and head-to-head comparison of logistic regression-based nomograms and artificial neural network models predicting prostate cancer on initial extended biopsy.},
  author={Michael W. Kattan},
  journal={European urology},
  year={2008},
  volume={54 3},
  pages={611}
}
Current evidence is quite strong to suggest that modern regression models, as can be represented by nomograms, predict at least as well as artificial neural networks. I was a big fan of neural networks but began to lose interest when real-world data sets produced disappointing results for me [1]. Schwarzer has written some nice reviews of the studies that compared neural networks with regression models and also concluded that neural networks were not living up to their ‘‘hype’’ [2]. In theory… CONTINUE READING

From This Paper

Topics from this paper.

Similar Papers

Loading similar papers…