Prostate Cancer Risk Stratification in NRG Oncology Phase III Randomized Trials Using Multimodal Deep Learning With Digital Histopathology

Abstract

Purpose: Current clinical risk stratification methods for localized prostate cancer are suboptimal, leading to over- and undertreatment. Recently, machine learning approaches using digital histopathology have shown superior prognostic ability in phase III trials. This study aims to develop a clinically usable risk grouping system using multimodal artificial intelligence (MMAI) models that outperform current National Comprehensive Cancer Network (NCCN) risk groups.

Materials and methods: The cohort comprised 9,787 patients with localized prostate cancer from eight NRG Oncology randomized phase III trials, treated with radiation therapy, androgen deprivation therapy, and/or chemotherapy. Locked MMAI models, which used digital histopathology images and clinical data, were applied to each patient. Expert consensus on cut points defined low-, intermediate-, and high-risk groups on the basis of 10-year distant metastasis rates of 3% and 10%, respectively. The MMAI's reclassification and prognostic performance were compared with the three-tier NCCN risk groups.

Results: The median follow-up for censored patients was 7.9 years. According to NCCN risk categories, 30.4% of patients were low-risk, 25.5% intermediate-risk, and 44.1% high-risk. The MMAI risk classification identified 43.5% of patients as low-risk, 34.6% as intermediate-risk, and 21.8% as high-risk. MMAI reclassified 1,039 (42.0%) patients initially categorized by NCCN. Despite the MMAI low-risk group being larger than the NCCN low-risk group, the 10-year metastasis risks were comparable: 1.7% (95% CI, 0.2 to 3.2) for NCCN and 3.2% (95% CI, 1.7 to 4.7) for MMAI. The overall 10-year metastasis risk for NCCN high-risk patients was 16.6%, with MMAI further stratifying this group into low-, intermediate-, and high-risk, showing metastasis rates of 3.4%, 8.2%, and 26.3%, respectively.

Conclusion: The MMAI risk grouping system expands the population of men identified as having low metastatic risk and accurately pinpoints a high-risk subset with elevated metastasis rates. This approach aims to prevent both overtreatment and undertreatment in localized prostate cancer, facilitating shared decision making.

FIG 1.

CONSORT diagram. n, number of patients; RTOG, Radiation Therapy Oncology Group.

FIG 2.

Cumulative incidence estimates of DM by (A) NCCN risk group, (B) MMAI risk group, and (C) NCCN and MMAI subgroups. Fourteen patients with missing NCCN were excluded from their corresponding analyses. DM, distant metastasis; MMAI, multimodal artificial intelligence; NCCN, National Comprehensive Cancer Network.

FIG 3.

Prognostic evaluation of MMAI within clinical and treatment subgroups for distant metastasis. One patient with Tx and 26 patients with missing Gleason score were excluded from their corresponding analyses. ADT, androgen deprivation therapy; IT, intermediate-term; LT, long-term; N, number of patients; ng/mL, nanogram per milliliter; RT, radiation therapy; sHR, subdistribution hazard ratio; ST, short-term.

FIG 4.

Reclassification between standard risk prognostic factors and MMAI risk group: (A) PSA grouping, (B) Grade Group, (C) T-stage, and (D) NCCN risk group. Twenty-seven patients missing Grade Group and 14 patients missing NCCN risk group were excluded from their corresponding analyses. MMAI, multimodal artificial intelligence; n, number of patients; NA, not applicable; NCCN, National Comprehensive Cancer Network; PSA, prostate-specific antigen.