MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Deep-Learning Based Survival Analysis of the NCDB Brain Metastasis Dataset

N Bice*, N Kirby , M Fakhreddine , University of Texas HSC SA, San Antonio, TX

Presentations

(Wednesday, 7/17/2019) 7:30 AM - 9:30 AM

Room: 225BCD

Purpose: Prognostic indices such as the brain met Graded Prognostic Index have been used in clinical settings to aid physicians and patients in determining an appropriate treatment regimen. These indices are derivative of classical statistical survival analysis techniques such as Multivariate Cox Regression and Recursive Partitioning Analysis (RPA). Previous studies have shown that by evaluating Cox Proportional Hazards (CPH) risk with a nonlinear deep neural network, DeepSurv, patient survival can be modeled more accurately. In this work, we apply DeepSurv to a test case: breast cancer patients with brain metastases who have received stereotactic radiosurgery.

Methods: Survival times, censorship status, and 27 covariates including age, staging information, and hormone receptor status were provided for 1673 patients by the NCDB. Monte Carlo cross-validation with 50 samples of 1400 patients was used to train and validate the DeepSurv, CPH, and RPA models independently. DeepSurv was implemented with L2 regularization, batch normalization, dropout, Nesterov momentum, and learning rate decay. RPA was implemented as a random survival forest (RSF). Concordance indices of test sets of 140 patients were used for each sample to assess the generalizable predictive capacity of each model.

Results: DeepSurv was trained for 7000 epochs per sample at 32 minutes per sample on a 1.33 GHz quad-core CPU. Test set concordance indices of 0.7473 ± 0.0056, 0.6323 ± 0.0068, and 0.7368 ± 0.0047, were found for DeepSurv, CPH, and RSF, respectively. A Tukey HSD test demonstrates a statistically significant difference between the mean concordance indices of the three models.

Conclusion: The data suggests that deep-learning based survival analysis can outperform classical models, specifically in a case where an accurate prognosis is highly clinically relevant. We recommend that where appropriate data is available, deep-learning based prognostic indicators should be used to supplement classical statistics.

Keywords

Not Applicable / None Entered.

Taxonomy

Not Applicable / None Entered.

Contact Email