A Deep Active Survival Analysis approach for precision treatment recommendations: Application of prostate cancer

Abstract

Survival analysis has been developed and applied in the number of areas including manufacturing, finance, economics and healthcare. In healthcare domain, usually clinical data are high-dimensional, sparse and complex and sometimes there exists few amount of timeto-event (labeled) instances. Therefore building an accurate survival model from electronic health records is challenging. With this motivation, we address this issue and provide a new survival analysis framework using deep learning and active learning with a novel sampling strategy. First, our approach provides better representation with lower dimensions from clinical features using labeled (time-to-event) and unlabeled (censored) instances and then actively trains the survival model by labeling the censored data using an oracle. As a clinical assistive tool, we introduce a simple effective treatment recommendation approach based on our survival model. In the experimental study, we apply our approach on SEER-Medicare data related to prostate cancer among African-Americans and white patients. The results indicate that our approach outperforms significantly than baseline models.

Prostate cancer classification with multiparametric MRI transfer learning model

“…This research work focused on prostate cancer classification. Since the prediction of disease‐free survival is the ultima goal in clinical trial, we will further collect data and develop suitable models for survival prediction to promote the deep learning‐based radiomics.…”

Deep Neural Networks Outperform the CAPRA Score in Predicting Biochemical Recurrence After Prostatectomy

“…Unfortunately, they considered a limited dataset without imputing the censored cases. Other sophisticated models based on active learning have been used to improve Cox regression and to predict prostate cancer survival among patients in the Surveillance, Epidemiology, and End Results (SEER) database, with c-indexes over 0.8 ( 22 , 23 ).…”

A weighted random survival forest

“…One of the most important areas is the medical research where survival models are widely used to evaluate the significance of prognostic variables in outcomes such as death or cancer recurrence and subsequently inform patients of their treatment options [34]. The datasets used in the survival analysis or just the survival data differ from many datasets by the fact that time to event of interest for a part of observations or instances is unknown because the event might not have happened during the period of study [49]. If the observed survival time is less than or equal to the true survival time, then we have a special case of censoring data called right-censoring data.…”

“…Faraggi and Simon in their pioneering work [17] presented an approach to modelling survival data using the input-output relationship associated with a simple feed-forward neural network as the basis for a non-linear proportional hazards model. The proposed model was a basis for developing more complex generalization using the deep neural networks [34,44,49,53,71,75]. The convolutional neural networks (CNN) also have been applied to the survival analysis.…”

“…Several models based on neural networks are considered in the review by Wang et al [65]. A review of deep learning methods for dealing with survival data is presented by Nezhad et al [49]. The proposed generalizations have many advantages, but there is an important disadvantage.…”