Prediction models for progression to castration-resistant prostate cancer after androgen deprivation therapy: a narrative review (2021–2026)
Abstract
BackgroundProstate cancer is one of the most common male malignancies. Androgen deprivation therapy (ADT) is the backbone of treatment for locally advanced and metastatic disease, yet many patients progress to castration-resistant prostate cancer (CRPC), historically within about 2 years of ADT monotherapy, and validated, widely generalisable tools to identify high-risk patients early remain limited.MethodsPubMed and OpenAlex were searched from January 2021 to August 2026 and supplemented by citation tracking; peer-reviewed studies reporting prediction models for progression to CRPC after ADT were included and synthesised narratively, with a PROBAST+AI-style appraisal of representative models.ResultsOf 65 unique records screened, 53 met the eligibility criteria (12 excluded as outside the scope or superseded); 17 references were added during revision, so 70 references are cited. CRPC arises through androgen receptor pathway activation, AR-V7, and neuroendocrine differentiation. Gleason score, PSA nadir, bone metastasis, inflammatory blood indices (neutrophil-to-lymphocyte ratio, systemic immune-inflammation index), circulating tumor cells, circulating tumor DNA, and genetic signatures are established risk factors. Individual studies report higher discrimination for machine-learning models than for traditional nomograms, but the comparisons are within-study and at high risk of bias and optimism, and external validation was reported for only two of eight core models. Super Learner, an ensemble framework, has proved stable across clinical outcome predictions; its use for CRPC prediction is only beginning.ConclusionA multi-parameter Super Learner model could improve CRPC risk stratification after ADT, provided it is validated prospectively in multicenter cohorts and reported transparently.
Related
- The VCPIP1‐UBE3A Deubiquitination‐Ubiquitination Cascade Contributes to Castration‐Resistant Prostate Cancer Progression
- m6A-Driven Intratumoral Cholesterol Biosynthesis Fuels Castration-Resistant Prostate Cancer Progression
- Peripheral blood mRNA-based prognostic model for progression to metastatic castration-resistant prostate cancer and identification of SLC6A8 as a glycolysis-promoting biomarker
- An Immunocompetent Mouse Model of Degarelix Induced Chemical Castration to Investigate Acquired Resistance to Androgen Deprivation.
- A low-androgen environment sustains redox-active sGC states required to restrain castration-resistant prostate cancer growth via elevated cGMP levels
BibTeX
@article{yuan2026prediction,
title = {{Prediction models for progression to castration-resistant prostate cancer after androgen deprivation therapy: a narrative review (2021–2026)}},
author = {Jun Yuan and Ziwei Jiang and Wenxian Chen and Shaocheng Wang},
journal = {Frontiers in Oncology},
year = {2026},
month = nov,
doi = {10.3389/fonc.2026.1964985},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1964985},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Prediction models for progression to castration-resistant prostate cancer after androgen deprivation therapy: a narrative review (2021–2026)
AU - Jun Yuan
AU - Ziwei Jiang
AU - Wenxian Chen
AU - Shaocheng Wang
PY - 2026
DA - 2026/11/05
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1964985
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1964985
AB - BackgroundProstate cancer is one of the most common male malignancies. Androgen deprivation therapy (ADT) is the backbone of treatment for locally advanced and metastatic disease, yet many patients progress to castration-resistant prostate cancer (CRPC), historically within about 2 years of ADT monotherapy, and validated, widely generalisable tools to identify high-risk patients early remain limited.MethodsPubMed and OpenAlex were searched from January 2021 to August 2026 and supplemented by citation tracking; peer-reviewed studies reporting prediction models for progression to CRPC after ADT were included and synthesised narratively, with a PROBAST+AI-style appraisal of representative models.ResultsOf 65 unique records screened, 53 met the eligibility criteria (12 excluded as outside the scope or superseded); 17 references were added during revision, so 70 references are cited. CRPC arises through androgen receptor pathway activation, AR-V7, and neuroendocrine differentiation. Gleason score, PSA nadir, bone metastasis, inflammatory blood indices (neutrophil-to-lymphocyte ratio, systemic immune-inflammation index), circulating tumor cells, circulating tumor DNA, and genetic signatures are established risk factors. Individual studies report higher discrimination for machine-learning models than for traditional nomograms, but the comparisons are within-study and at high risk of bias and optimism, and external validation was reported for only two of eight core models. Super Learner, an ensemble framework, has proved stable across clinical outcome predictions; its use for CRPC prediction is only beginning.ConclusionA multi-parameter Super Learner model could improve CRPC risk stratification after ADT, provided it is validated prospectively in multicenter cohorts and reported transparently.
SN - 2234-943X
ER -