Interpretable deep neural network for cancer survival analysis by integrating genomic and clinical data

Abstract

Background: Understanding the complex biological mechanisms of cancer patient survival using genomic and clinical data is vital, not only to develop new treatments for patients, but also to improve survival prediction. However, highly nonlinear and high-dimension, low-sample size (HDLSS) data cause computational challenges to applying conventional survival analysis. Results: We propose a novel biologically interpretable pathway-based sparse deep neural network, named Cox-PASNet, which integrates high-dimensional gene expression data and clinical data on a simple neural network architecture for survival analysis. Cox-PASNet is biologically interpretable where nodes in the neural network correspond to biological genes and pathways, while capturing the nonlinear and hierarchical effects of biological pathways associated with cancer patient survival. We also propose a heuristic optimization solution to train Cox-PASNet with HDLSS data. Cox-PASNet was intensively evaluated by comparing the predictive performance of current state-of-the-art methods on glioblastoma multiforme (GBM) and ovarian serous cystadenocarcinoma (OV) cancer. In the experiments, Cox-PASNet showed out-performance, compared to the benchmarking methods. Moreover, the neural network architecture of Cox-PASNet was biologically interpreted, and several significant prognostic factors of genes and biological pathways were identified. Conclusions: Cox-PASNet models biological mechanisms in the neural network by incorporating biological pathway databases and sparse coding. The neural network of Cox-PASNet can identify nonlinear and hierarchical associations of genomic and clinical data to cancer patient survival. The open-source code of Cox-PASNet in PyTorch implemented for training, evaluation, and model interpretation is available at: https://github.com/DataX-JieHao/Cox-PASNet.

Identification and validation of stemness-related lncRNA prognostic signature for breast cancer

“…In addition, Cox-nnet has a better performance than SurvivalNet models, and SurvivalNet models provide comparable performance to the Cox elastic net [39,40]. Moreover, Cox-PASNet, which is a novel pathway-based sparse deep neural network for survival analysis that integrates high-dimensional genomic data and clinical data, has been applied to identify significant prognostic factors [40]. However, our study has some limitations.…”

“…Bayesian-optimized deep survival models (SurvivalNet models) have successfully improved the accuracy of prognostic prediction for high-dimensional cancer genomic profiles [39]. In addition, Cox-nnet has a better performance than SurvivalNet models, and SurvivalNet models provide comparable performance to the Cox elastic net [39,40]. Moreover, Cox-PASNet, which is a novel pathway-based sparse deep neural network for survival analysis that integrates high-dimensional genomic data and clinical data, has been applied to identify significant prognostic factors [40].…”

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19

“…Although there are still limited studies, we believe that the methods from other related studies could be borrowed. 1) In the prognosis of other pneumonia diseases, machine learning-based methodology could inspire the follow-up study of COVID-19 [81][82][83][84].…”

Novel coronavirus (COVID-19) diagnosis using computer vision and artificial intelligence techniques: a review

“…Despite limited solutions, a methodology based on machine learning [ 36 , 57 , 59 , 114 ], medical imaging [ 102 ], fusion and oncology, Natural language processing [ 118 ], and different learning algorithms [ 14 , 32 , 48 – 56 , 75 , 76 , 81 , 87 , 119 – 121 , 125 ] could be used for measuring the coronavirus COVID-19 disease.…”