Risk of Death from Prostate Cancer with and without Definitive Local Therapy when Gleason Pattern 5 is Present: A Surveillance, Epidemiology, and End Results Analysis

Graph-based multi-modality integration for prediction of cancer subtype and severity

Personalised cancer screening before therapy paves the way toward improving diagnostic accuracy and treatment outcomes. Most approaches are limited to a single data type and do not consider interactions between features, leaving aside the complementary insights that multimodality and systems biology can provide. In this project, we demonstrate the use of graph theory for data integration via individual networks where nodes and edges are individual-specific. We showcase the consequences of early, intermediate, and late graph-based fusion of RNA-Seq data and histopathology whole-slide images for predicting cancer subtypes and severity. The methodology developed is as follows: (1) we create individual networks; (2) we compute the similarity between individuals from these graphs; (3) we train our model on the similarity matrices; (4) we evaluate the performance using the macro F1 score. Pros and cons of elements of the pipeline are evaluated on publicly available real-life datasets. We find that graph-based methods can increase performance over methods that do not study interactions. Additionally, merging multiple data sources often improves classification compared to models based on single data, especially through intermediate fusion. The proposed workflow can easily be adapted to other disease contexts to accelerate and enhance personalized healthcare.

Therapeutic Sequences in the Treatment of High-Risk Prostate Cancer: Paving the Way Towards Multimodal Tailored Approaches

Various definitions are currently in use to describe high-risk prostate cancer. This variety in definitions is important for patient counseling, since predicted outcomes depend on which classification is applied to identify patient’s prostate cancer risk category. Historically, strategies for the treatment of localized high-risk prostate cancer comprise local approaches such as surgery and radiotherapy, as well as systemic approaches such as hormonal therapy. Nevertheless, since high-risk prostate cancer patients remain the group with higher-risk of treatment failure and mortality rates, nowadays, novel treatment strategies, comprising hypofractionated-radiotherapy, second-generation antiandrogens, and hadrontherapy, are being explored in order to improve their long-term oncological outcomes. This narrative review aims to report the current management of high-risk prostate cancer and to explore the future perspectives in this clinical setting.

Number-needed-to-treat analysis of clinical progression in patients with metastatic castration-resistant prostate cancer in the STRIVE and TERRAIN trials

BACKGROUND

This analysis estimated the number needed to treat with enzalutamide versus bicalutamide to achieve one additional patient with chemotherapy-naïve metastatic castration-resistant prostate cancer who would obtain clinical benefit regarding progression-free survival, radiographic progression-free survival, or no prostate-specific antigen progression at 1 and 2 years following treatment initiation.

METHODS

Clinical event rates were obtained from the STRIVE (NCT01664923) and TERRAIN (NCT01288911) trials, and the number needed to treat was the inverse of the absolute rate difference between the event rates of enzalutamide and bicalutamide. The 95% Confidence Interval of the number needed to treat was derived from the 95% Confidence Interval of the event rate difference.

RESULTS

Using STRIVE data (patients with metastatic disease: n = 128 enzalutamide; n = 129 bicalutamide) comparing enzalutamide with bicalutamide at 1 and 2 years, the numbers needed to treat to achieve one additional patient with chemotherapy-naïve metastatic castration-resistant prostate cancer with progression-free survival were 2.0 and 2.8, respectively; with radiographic progression-free survival, 2.6 and 3.0, respectively; and without prostate-specific antigen progression, 1.8 and 2.4, respectively. Using TERRAIN data (n = 184 enzalutamide; n = 191 bicalutamide) comparing enzalutamide with bicalutamide at 1 and 2 years, the numbers needed to treat to achieve one additional patient with progression-free survival were 4.3 and 3.7, respectively; with radiographic progression-free survival, 10.0 and 2.8, respectively; and without prostate-specific antigen progression, 2.1 and 3.2, respectively.

CONCLUSIONS

The combined data from TERRAIN and STRIVE demonstrated that treating chemotherapy-naïve metastatic castration-resistant prostate cancer with enzalutamide leads to more patients without clinical progression at 1 and 2 years than with bicalutamide.

TRIAL REGISTRATION

STRIVE (NCT01664923; registration date: August 10, 2012) and TERRAIN (NCT01288911; registration date: February 1, 2011).