A Simple Discrete-Time Survival Model for Neural Networks

There is currently great interest in applying neural networks to prediction tasks in medicine. It is important for predictive models to be able to use survival data, where each patient has a known follow-up time and event/censoring indicator. This avoids information loss when training the model and enables generation of predicted survival curves. In this paper, we describe a discrete-time survival model that is designed to be used with neural networks. The model is trained with the maximum likelihood method using minibatch stochastic gradient descent (SGD). The use of SGD enables rapid training speed. The model is flexible, so that the baseline hazard rate and the effect of the input data can vary with follow-up time. It has been implemented in the Keras deep learning framework, and source code for the model and several examples is available online. We demonstrated the high performance of the model by using it as part of a convolutional neural network to predict survival for over 10,000 patients with metastatic cancer, using the full text of 1,137,317 provider notes. The model's C-index on the validation set was 0.71, which was superior to a linear baseline model (C-index 0.69).

[1]  Frank E. Harrell,et al.  Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis , 2001 .

[2]  John B. Willett,et al.  It’s About Time: Using Discrete-Time Survival Analysis to Study Duration and the Timing of Events , 1993 .

[3]  Li Li,et al.  Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records , 2016, Scientific Reports.

[4]  William Moran,et al.  On the use of artificial neural networks for the analysis of survival data , 1997, IEEE Trans. Neural Networks.

[5]  I. Graham,et al.  Value and limitations of existing scores for the assessment of cardiovascular risk: a review for clinicians. , 2009, Journal of the American College of Cardiology.

[6]  N. Breslow,et al.  A Large Sample Study of the Life Table and Product Limit Estimates Under Random Censorship , 1974 .

[7]  Albee Y. Ling,et al.  A Clinical Score for Predicting Atrial Fibrillation in Patients with Cryptogenic Stroke or Transient Ischemic Attack , 2017, Cardiology.

[8]  T. Panzarella,et al.  Accuracy of survival prediction by palliative radiation oncologists. , 2005, International journal of radiation oncology, biology, physics.

[9]  D Faraggi,et al.  A neural network model for survival data. , 1995, Statistics in medicine.

[10]  Uri Shaham,et al.  DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network , 2016, BMC Medical Research Methodology.

[11]  Travers Ching,et al.  Cox-nnet: an artificial neural network Cox regression for prognosis prediction , 2016 .

[12]  D.,et al.  Regression Models and Life-Tables , 2022 .

[13]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[14]  H. Prigerson,et al.  Clinical trial participation as part of end-of-life cancer care: associations with medical care and quality of life near death. , 2014, Journal of pain and symptom management.

[15]  R. Kay.  The Analysis of Survival Data , 2012 .

[16]  James E. Helmreich.  Regression Modeling Strategies with Applications to Linear Models, Logistic and Ordinal Regression and Survival Analysis (2nd Edition) , 2016 .

[17]  P. Royston,et al.  Flexible parametric proportional‐hazards and proportional‐odds models for censored survival data, with application to prognostic modelling and estimation of treatment effects , 2002, Statistics in medicine.

[18]  Egil Martinsson,et al.  WTTE-RNN : Weibull Time To Event Recurrent Neural Network A model for sequential prediction of time-to-event in the case of discrete or continuous censored data, recurrent events or time-varying covariates , 2017 .

[19]  Jeffrey Dean,et al.  Scalable and accurate deep learning with electronic health records , 2018, npj Digital Medicine.

[20]  U. G. Dailey.  Cancer,Facts and Figures about. , 2022, Journal of the National Medical Association.

[21]  Andrew Y. Ng,et al.  Improving palliative care with deep learning , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[22]  Xun Zhu,et al.  Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data , 2018, PLoS Comput. Biol..

[23]  P. Royston,et al.  External validation of a Cox prognostic model: principles and methods , 2013, BMC Medical Research Methodology.

[24]  Daniel L. Rubin,et al.  Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) Utilizing Free-Text Clinical Narratives , 2018, Scientific Reports.

[25]  Christopher H Jackson,et al.  flexsurv: A Platform for Parametric Survival Modeling in R. , 2016, Journal of statistical software.

[26]  E. Emanuel,et al.  Comparison of Site of Death, Health Care Utilization, and Hospital Expenditures for Patients Dying With Cancer in 7 Developed Countries. , 2016, JAMA.