Dataset Information

Treatment Stratification of Patients with Metastatic Castration-Resistant Prostate Cancer by Machine Learning.

ABSTRACT: Prostate cancer is the most common cancer in men in the Western world. One-third of the patients with prostate cancer will develop resistance to hormonal therapy and progress into metastatic castration-resistant prostate cancer (mCRPC). Currently, docetaxel is a preferred treatment for mCRPC. However, about 20% of the patients will undergo early therapeutic failure owing to adverse events induced by docetaxel-based chemotherapy. There is an emergent need for a computational model that can accurately stratify patients into docetaxel-tolerable and docetaxel-intolerable groups. Here we present the best-performing algorithm in the Prostate Cancer DREAM Challenge for predicting adverse events caused by docetaxel treatment. We integrated the survival status and severity of adverse events into our model, which is an innovative way to complement and stratify the treatment discontinuation information. Critical stratification biomarkers were further identified in determining the treatment discontinuation. Our model has the potential to improve future personalized treatment in mCRPC.

SUBMITTER: Deng K

PROVIDER: S-EPMC6976944 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Treatment Stratification of Patients with Metastatic Castration-Resistant Prostate Cancer by Machine Learning.

Deng Kaiwen K Li Hongyang H Guan Yuanfang Y

iScience 20191226 2

Prostate cancer is the most common cancer in men in the Western world. One-third of the patients with prostate cancer will develop resistance to hormonal therapy and progress into metastatic castration-resistant prostate cancer (mCRPC). Currently, docetaxel is a preferred treatment for mCRPC. However, about 20% of the patients will undergo early therapeutic failure owing to adverse events induced by docetaxel-based chemotherapy. There is an emergent need for a computational model that can accura ...[more]

PMID: 31978751

Similar Datasets

Project description:BackgroundRecent approvals of second-generation androgen receptor inhibitors (SGARIs) have changed the treatment landscape for non-metastatic castration-resistant prostate cancer (nmCRPC). These SGARIs have similar efficacy but differ in safety profiles. We used a discrete choice experiment to explore how United States physicians make treatment decisions between adverse events (AEs) and survival gains in nmCRPC, a largely asymptomatic disease.MethodsTreating physicians (n = 149) participated in an online survey that included 14 treatment choice questions, each comparing 2 hypothetical treatment profiles, which varied in terms of 5 safety and 2 efficacy attributes. We described safety attributes (fatigue, skin rash, cognitive problems, falls, and fractures) in terms of severity and frequency, and efficacy attributes (overall survival [OS] and time to pain progression) in terms of duration of effect. We used a random parameters logit model to estimate preference weights and importance scores for each attribute. We also estimated the amount of survival gain physicians were willing to trade for a reduction in specific AEs between treatment options.ResultsPhysicians placed more importance on survival than on time to pain progression, and viewed a reduction in cognitive problems from severe to none, a reduction in risk of a serious fracture from 8% to none, and a reduction in fatigue from severe to none as the most important safety attributes. Physicians were willing to forego 9.1 and 6.6 months of OS, respectively, to reduce cognitive problems and fatigue from severe to mild-to-moderate. To reduce the risk of a serious fracture from 8 to 5% and 5% to none, physicians were willing to trade 3.9 and 5.3 months of OS, respectively.ConclusionsPhysicians were willing to trade substantial amounts of survival to avoid AEs between hypothetical treatments. These results emphasize the importance of carefully balancing therapies' benefits and risks to ultimately optimize the overall quality of nmCRPC patients' survival. Nonetheless, it is noted that the results from the study sample of 149 physicans may not be representative of the viewpoints of all nmCRPC-treating physicians.

Project description:Androgen deprivation therapy remains the single most effective treatment for the initial therapy of advanced prostate cancer, but is uniformly marked by progression to castration-resistant prostate cancer (CRPC). Residual tumor androgens and androgen axis activation are now recognized to play a prominent role in mediating CRPC progression. Despite suppression of circulating testosterone to castrate levels, castration does not eliminate androgens from the prostate tumor microenvironment and residual androgen levels are well within the range capable of activating the androgen receptor (AR) and AR-mediated gene expression. Accordingly, therapeutic strategies that more effectively target production of intratumoral androgens are necessary. The introduction of abiraterone, a potent suppressor of cytochrome P450 17 α-hydroxysteroid dehydrogenase-mediated androgen production, has heralded a new era in the hormonal treatment of men with metastatic CRPC. Herein, the androgen and AR-mediated mechanisms that contribute to CRPC progression and establish cytochrome P450 17 α-hydroxysteroid dehydrogenase as a critical therapeutic target are briefly reviewed. The mechanism of action and pharmacokinetics of abiraterone are reviewed and its recently described activity against AR and 3-β-hydroxysteroid dehydrogenase is discussed. The Phase I and II data initially demonstrating the efficacy of abiraterone and Phase III data supporting its approval for patients with metastatic CRPC are reviewed. The safety and tolerability of abiraterone, including the incidence and management of side effects and potential drug interactions, are discussed. The current place of abiraterone in CRPC therapy is reviewed and early evidence regarding cross-resistance of abiraterone with taxane therapy, mechanisms of resistance to abiraterone, and observations of an abiraterone withdrawal response are presented. Future directions in the use of abiraterone, including optimal dosing strategies, the role of abiraterone in earlier disease settings, including castration sensitive, biochemically recurrent, or localized disease, and the rationale for combinatorial treatment strategies of abiraterone with enzalutamide and other targeted agents are also discussed.

Dataset Information

Treatment Stratification of Patients with Metastatic Castration-Resistant Prostate Cancer by Machine Learning.

Publications

Treatment Stratification of Patients with Metastatic Castration-Resistant Prostate Cancer by Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets