Validation of an Artificial Intelligence-Based Prognostic Biomarker in Patients with Oligometastatic Castration-Sensitive Prostate Cancer

Authors

Jarey H. Wang
Matthew P. Deek
Adrianna A. Mendes
Yang Song
Amol Shetty
Soha Bazyar
Kim Van der Eecken
Emmalyn Chen
Timothy N. Showalter
Trevor J. Royce
Tamara Todorovic
Huei-Chung Huang
Scott A. Houck
Rikiya Yamashita
Ana P. Kiess
Daniel Y. Song
Tamara Lotan
Theodore DeWeese
Luigi Marchionni
Lei Ren
Amit Sawant
Nicole L. Simone, Thomas Jefferson UniversityFollow
Alejandro Berlin
Cem Onal
Andre Esteva
Felix Y. Feng
Phuoc T. Tran
Philip Sutera
Piet Ost

Document Type

Article

Publication Date

11-6-2024

Comments

This article is the author's final published version in Radiotherapy and Oncology, Volume 202, 2025, Article number 110618.

The published version is available at https://doi.org/10.1016/j.radonc.2024.110618.

Copyright © 2024 The Author(s)

Abstract

BACKGROUND: There is a need for clinically actionable prognostic and predictive tools to guide the management of oligometastatic castration-sensitive prostate cancer (omCSPC).

METHODS: This is a multicenter retrospective study to assess the prognostic and predictive performance of a multimodal artificial intelligence biomarker (MMAI; the ArteraAI Prostate Test) in men with omCSPC (n = 222). The cohort also included 51 patients from the STOMP and ORIOLE phase 2 clinical trials which randomized patients to observation versus metastasis-directed therapy (MDT). MMAI scores were computed from digitized histopathology slides and clinical variables. Overall survival (OS) and time to castration-resistant prostate cancer (TTCRPC) were assessed for the entire cohort from time of diagnosis. Metastasis free survival (MFS) was assessed for the trial cohort from time of randomization.

RESULTS: In the overall cohort, patients with a high MMAI score had significantly worse OS (HR = 6.46, 95 % CI = 1.44-28.9; p = 0.01) and shorter TTCRPC (HR = 2.07, 95 % CI = 1.15-3.72; p = 0.015). In a multivariable Cox model, MMAI score remained the only variable significantly associated with OS (HR = 6.51, 95 % CI = 1.32-32.2; p = 0.02). In the subset of patients randomized in the STOMP and ORIOLE trials, high MMAI score corresponded to improved MFS with MDT (p = 0.039) compared to patients with a low score, with p_interaction = 0.04.

CONCLUSION: The ArteraAI MMAI biomarker is prognostic for OS and TTCRPC among patients with omCSPC and may predict for response to MDT. Further work is needed to validate the MMAI biomarker in a broader mCSPC cohort.

Recommended Citation

Wang, Jarey H.; Deek, Matthew P.; Mendes, Adrianna A.; Song, Yang; Shetty, Amol; Bazyar, Soha; Van der Eecken, Kim; Chen, Emmalyn; Showalter, Timothy N.; Royce, Trevor J.; Todorovic, Tamara; Huang, Huei-Chung; Houck, Scott A.; Yamashita, Rikiya; Kiess, Ana P.; Song, Daniel Y.; Lotan, Tamara; DeWeese, Theodore; Marchionni, Luigi; Ren, Lei; Sawant, Amit; Simone, Nicole L.; Berlin, Alejandro; Onal, Cem; Esteva, Andre; Feng, Felix Y.; Tran, Phuoc T.; Sutera, Philip; and Ost, Piet, "Validation of an Artificial Intelligence-Based Prognostic Biomarker in Patients with Oligometastatic Castration-Sensitive Prostate Cancer" (2024). Department of Radiation Oncology Faculty Papers. Paper 199.
https://jdc.jefferson.edu/radoncfp/199

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

PubMed ID

39510141

Language

English