Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer

5001 Background: Androgen deprivation therapy (ADT) improves survival and reduces risk of metastasis in men with high-risk localized prostate cancer (PC) receiving radiotherapy (RT). Predictive biomarkers are needed to guide ADT duration to maximize benefits and minimize risks. We sought to train and validate the first predictive biomarker for long-term (LT) vs short-term (ST) ADT using multiple phase III NRG Oncology randomized trials. Methods: Pre-treatment prostate biopsy slides were digitized from six phase III NRG/RTOG randomized trials of men receiving RT +/- ADT. The artificial intelligence (AI)-derived clinical and histopathological predictive biomarker was trained on RTOG 9408, 9413, 9902, 9910, and 0521 to predict differential benefit of LTADT on distant metastasis (DM). After the AI biomarker was locked, it was validated on RTOG 9202, which randomized men to RT + STADT (4 mo) vs LTADT (28 mo). The predictive utility of the AI biomarker was evaluated for the primary and secondary endpoints of DM and PC-specific mortality (PCSM), respectively, for ADT duration with Fine-Gray interaction models. Event rates were estimated by the cumulative incidence method. Deaths from other causes were treated as competing risks. Results: The AI-derived biomarker was trained on 2,641 men (median follow-up of 9.8 years, IQR [8.2, 11.5]) and validated on 1,192 men from RTOG 9202 (median follow-up of 17.2 years, IQR [9.1, 19.6]), where 80% had at least one high/very high (H/VH) risk feature (cT3-4, Gleason 8-10, PSA > 20, or primary Gleason pattern 5). Consistent with published results, LTADT significantly improved DM (subdistribution HR [sHR] 0.64, 95% CI 0.50-0.82, p < 0.001) in the validation cohort. The AI biomarker was prognostic for DM (sHR 2.35, 95% CI 1.72-3.19, p < 0.001). A significant biomarker-treatment interaction was observed (p = 0.04), in which AI-biomarker (+) men (n = 785, 66%) had reduced DM with LTADT (sHR 0.55, 95% CI 0.41-0.73, p < 0.001), but no benefit was observed (sHR 1.06, 95% CI 0.61-1.84, p = 0.84) for AI-biomarker (-) men (n = 407, 34%). The 10-year DM rate difference between RT + LTADT vs RT + STADT was 13% in AI-biomarker (+) men vs 2% in AI-biomarker (-) men. Similar trends were observed for PCSM outcomes. Risk classification (NCCN intermediate [n = 221, 43% (+)] vs other H/VH risk [n = 954, 71% (+)]) was prognostic but not predictive of LTADT benefit. Conclusions: We have successfully validated the first predictive biomarker of LTADT benefit with RT in localized high-risk PC using an AI-derived digital pathology-based platform in the phase III NRG/RTOG 9202 trial. The predictive AI biomarker identified 34% of men that could derive similar benefit with STADT, avoiding the side effects of prolonged ADT, and 43% of intermediate risk men who would benefit from LTADT.

NOVEL STAGING TOOL FOR LOCALIZED PROSTATE CANCER: A PILOT STUDY USING GENETIC ADAPTIVE NEURAL NETWORKS

223 Background: The current standard of care for men with intermediate- and high-risk localized prostate cancer treated with radiotherapy (RT) is the addition of androgen deprivation therapy (ADT). Presently, there are no validated predictive biomarkers to guide ADT use or duration in such men. Herein, we train and validate the first predictive biomarker for ADT use in prostate cancer using multiple phase III NRG Oncology randomized trials. Methods: Pre-treatment biopsy slides were digitized from five phase III NRG Oncology randomized trials of men receiving RT with or without ADT. The training set to develop the artificial intelligence (AI)-derived predictive biomarker included NRG/RTOG 9202, 9413, 9910, and 0126, and was trained to predict distant metastasis (DM). A multimodal deep learning architecture was developed to learn from both clinicopathologic and digital imaging histopathology data and identify differential outcomes by treatment type. After the model was locked, an independent biostatistician performed validation on NRG/RTOG 9408, a phase III randomized trial of RT +/- 4 months of ADT. The DM rates were calculated using cumulative incidence functions in biomarker positive and negative groups, and biomarker-treatment interaction was assessed using Fine-Gray regression such that death without DM was treated as a competing event. Results: Clinical and histopathological data was available for 5,654 of 7,957 eligible patients (71.1%). The training cohort included 3,935 patients and had a median follow-up of 13.6 years (IQR [10.2, 17.7]). After the AI-derived predictive ADT classifier was trained, it was validated in NRG/RTOG 9408 (n = 1719, median follow-up 17.6 years, IQR [15.0, 19.7]). In the NRG/RTOG 9408 validation cohort that had digital histopathology data, ADT significantly improved DM (HR 0.62, 95% CI [0.44, 0.87], p = 0.006), consistent with the published trial results. The biomarker-treatment interaction was significant (p-value = 0.0021). In patients with AI-biomarker positive disease (n = 673, 39%), ADT had a greater benefit compared to RT alone (HR 0.33, 95% CI [0.19, 0.57], p < 0.001). In the biomarker negative subgroup (n = 1046, 61%), the addition of ADT did not improve outcomes over RT alone (HR 1.00, 95% CI [0.64, 1.57], p = 0.99). The 15-year DM rate difference between RT versus RT+ADT in the biomarker negative group was 0.3%, vs biomarker positive group 9.4%. Conclusions: We have successfully validated in a phase III randomized trial the first predictive biomarker of ADT benefit with RT in localized intermediate risk prostate cancer using a novel AI-derived digital pathology-based platform. This AI-derived predictive biomarker demonstrates that a majority of patients treated with RT on NRG/RTOG 9408 did not require ADT and could have avoided the associated costs and side effects of this treatment.

BackgroundRestricted mean survival time (RMST) is a measure of average survival time up to a specified time point. There has been an increased interest in using RMST to compare treatment arms in randomized clinical trials (RCTs) because such comparisons do not rely on proportional hazards or other assumptions about the nature of the relationship between survival curves.MethodsThis paper addresses the question of whether covariate adjustment in randomized clinical trials that compare RMSTs improves precision of the estimated treatment effect (difference in RMSTs between treatment arms). Although precision generally increases in linear models when prognostic covariates are added, this is not necessarily the case in non-linear models. For example, in logistic and Cox regression, the standard error of the estimated treatment effect does not decrease when prognostic covariates are added, although the situation is complicated in those settings because the estimand changes as well. Because estimation of RMST in the manner described in this paper is also based on a model that is nonlinear in the covariates, we investigate whether the comparison of RMSTs with adjustment for covariates leads to a reduction in the standard error of the estimated treatment effect relative to the unadjusted estimator or whether covariate adjustment provides no improvement in precision. Chen and Tsiatis (2001) suggest that precision will increase if covariates are chosen judiciously. We present results of simulation studies that compare unadjusted vs. adjusted comparisons of RMST between treatment arms in randomized clinical trials.ResultsWe find that for comparison of restricted means in an RCT, adjusting for covariates that are associated with survival increases precision and therefore statistical power, relative to the unadjusted estimator. Omitting important covariates results in less precision but estimates remain unbiased.ConclusionsWhen comparing restricted means in an RCT, adjusting for prognostic covariates can improve precision and increase power.

Population Based Study of Hormonal Therapy and Survival in Men With Metastatic Prostate Cancer

Reply from Authors re: Ronald C. Chen. Decisions Regarding Whether to Use Androgen Deprivation Therapy with Radiotherapy in Prostate Cancer: Is Cardiovascular Mortality the Most Relevant Outcome? Eur Urol 2016;69:211–2: Outcomes for Favorable and Unfavorable Intermediate Risk Prostate Cancer Patients Receiving Radiation Therapy With or Without Short-term Androgen Deprivation Therapy

Comorbidity and Primary Treatment for Localized Prostate Cancer: Data From C <scp>a</scp> PSURE™

ObjectiveThe present study aimed to compare time to effective pain relief between diclofenac 75 mg intramuscular (IM) and tramadol 50 mg intravenous (IV) for ED patients with acute renal colic.MethodsA randomised, double‐blinded, sham‐controlled, superiority trial was conducted. Patients diagnosed with acute renal colic (hydronephrosis and/or stone visualisation on point‐of‐care ultrasound) in the ED were randomly assigned to receive an IM injection of 75 mg of diclofenac or IV tramadol 50 mg. Pain relief was defined as a numerical rating scale reduction of two or more points (standard 0–10 scale) and a reduction of at least one level of pain transition question (‘much better’, ‘little better’, ‘unchanged’, ‘little worse’, ‘much worse’). The primary outcome was the multivariable‐adjusted subdistribution‐hazard ratio (SHRs) within 120 min in the ED, estimated using the cumulative incidence function (CIF). The secondary outcome compared the average time to pain relief using the restricted mean survival time (RMST).ResultsA total of 68 patients were randomised, with 34 patients allocated to each group. At the 120 min, pain relief was reported in diclofenac and tramadol, 32 (94%) and 22 (65%) patients respectively. SHR was 2.86 (95% CI: 1.80–4.55; P value <0.001). For diclofenac and tramadol, the RMSTs were 37.09 min (95% CI: 30.00, 44.15) and 78.74 min (95% CI: 66.49, 90.99) respectively, with the difference of 41.67 min (95% CI: 55.71, 27.62).ConclusionDiclofenac 75 mg IM provides faster effective pain relief compared with tramadol 50 mg IV.

Survival Among Men With Clinically Localized Prostate Cancer Treated With Radical Prostatectomy or Radiation Therapy in the Prostate Specific Antigen Era

Expanded Prostate Cancer Index Composite for Clinical Practice: Development and Validation of a Practical Health Related Quality of Life Instrument for Use in the Routine Clinical Care of Patients With Prostate Cancer

Genitourinary Imaging in 2040.

Advanced but Not Localized Prostate Cancer is Associated With Increased Oxidative Stress

HOXB13 is a key lineage homeobox transcription factor that plays a critical role in the differentiation of the prostate gland. Several studies have suggested that HOXB13 alterations may be involved in prostate cancer development and progression. Despite its potential biological relevance, little is known about the expression of HOXB13 across the disease spectrum of prostate cancer. To this end, we validated a HOXB13 antibody using genetic controls and investigated HOXB13 protein expression in murine and human developing prostates, localized prostate cancers, and metastatic castration-resistant prostate cancers. We observed that HOXB13 expression increases during later stages of murine prostate development. All localized prostate cancers showed HOXB13 protein expression. Interestingly, lower HOXB13 expression levels were observed in higher-grade tumors, although no significant association between HOXB13 expression and recurrence or disease-specific survival was found. In advanced metastatic prostate cancers, HOXB13 expression was retained in the majority of tumors. While we observed lower levels of HOXB13 protein and mRNA levels in tumors with evidence of lineage plasticity, 84% of androgen receptor-negative castration-resistant prostate cancers and neuroendocrine prostate cancers (NEPCs) retained detectable levels of HOXB13. Notably, the reduced expression observed in NEPCs was associated with a gain of HOXB13 gene body CpG methylation. In comparison to the commonly used prostate lineage marker NKX3.1, HOXB13 showed greater sensitivity in detecting advanced metastatic prostate cancers. Additionally, in a cohort of 837 patients, 383 with prostatic and 454 with non-prostatic tumors, we found that HOXB13 immunohistochemistry had a 97% sensitivity and 99% specificity for prostatic origin. Taken together, our studies provide valuable insight into the expression pattern of HOXB13 during prostate development and cancer progression. Furthermore, our findings support the utility of HOXB13 as a diagnostic biomarker for prostate cancer, particularly to confirm the prostatic origin of advanced metastatic castration-resistant tumors. © 2023 The Pathological Society of Great Britain and Ireland.

PAGE4 Positivity Is Associated with Attenuated AR Signaling and Predicts Patient Survival in Hormone-Naive Prostate Cancer

e16550 Background: Prostate cancer (PC) is generally resistant to current immune checkpoint blockade. Reduced expression of human leukocyte antigen-A (HLA-A) and b2-microglobulin (B2M) of cancer cells can cause deficit immune recognition and attack by cytotoxic T cells, and may be the major mechanism of intrinsic resistance to immune checkpoint blockade in PC patients. Methods: Formalin-fixed paraffin-embedded tissue of human localized or metastatic PC was used for evaluation of expression of HLA-A and B2M by Immunohistochemical staining. The expression was scored as: 0, no tumor cells stained; 1+, &lt; 10% of tumor cells stained; 2+, 10-50% of tumor cells stained; and 3+, &gt; 50% of tumor cells stained. Differences in HLA-A or B2M expression among groups were assessed by Chi-Square or Fisher’s exact test. Results: A total of 134 PC specimens [69 localized PC (LPC), 32 metastatic castration-naïve PC (mCNPC), and 33 metastatic castration-resistant PC (mCRPC)] from 115 patients were assessed. Significant loss (0 or 1+) of HLA-A was found in 56 (81.2%) LPCs, 30 (93.8 %) mCNPCs and 29 (87.9%) mCRPCs; while significant loss of B2M was found in 22 (32.6%) LPC, 11 (34.4%) mCNPCs, and 17 (51.2%) mCRPCs. In localized PCs, the expression of HLA-A or B2M was similar between high-grade prostate intraepithelial neoplasia foci and corresponding malignant counterpart, and did not significantly correlate to biochemical failure. In 14 patients with paired CN and CR PC specimens, significant loss of HLA-A was found in all tumors. B2M expression varied between CN and CR PCs, and progressive loss of B2M was found in 7 (50%) patients. Among 3 patients receiving immune checkpoint blockade, 1 patient with intact expression of HLA-A and B2M in pre-treatment tumor specimen achieved partial response; whereas the others with reduced expression of HLA-A (0) and B2M (1+) did not. Conclusions: Reduced expression of HLA-A or B2M is an early event in prostate carcinogenesis.