Abstract
Artificial neural networks (ANN) are computing architectures with massively parallel interconnections of simple neurons and has been applied to biomedical fields such as imaging analysis and diagnosis. We have developed a new ANN framework called Cox-nnet to predict patient prognosis from high throughput transcriptomics data. In over 10 TCGA RNA-Seq data sets, Cox-nnet achieves a statistically significant increase in predictive accuracy, compared to the other three methods including Cox-proportional hazards (Cox-PH), Random Forests Survival and CoxBoost. Cox-nnet also offers richer biological information, from both pathway and gene levels. The outputs from the hidden layer node can be utilized as a new approach for survival-sensitive dimension reduction. In summary, we have developed a new method for more accurate and efficient prognosis prediction, with functional biological insights. The source code is freely available at https://github.com/lanagarmire/cox-nnet.
