Citations

144 Background: Androgen receptor pathway inhibitors (abiraterone acetate [AAP], apalutamide [APA], enzalutamide [E], darolutamide [DARO] have become the cornerstone for pts with PCa due to survival benefits. Comparative data on fracture risk among ARPi are limited. This study quantified the risk of bone fractures with ARPi plus androgen deprivation therapy (ADT) and compared fracture risk across different ARPi agents. Methods: MEDLINE and EMBASE were searched from inception through September 1 st 2025 to identify positive phase III trials assessing ARPi in addition to ADT in pts with PCa (m0CRPC, mCSPC, mCRPC). Trials were included if they reported bone fractures in either arm. Pairwise, random-effects meta-analysis was conducted using Paul-Mendel approach. Sensitivity analyses using Hartung-Knapp (HK) adjustment was performed to assess robustness of results. To assess the comparative risk of bone fractures among different ARPi agents, mixed treatment comparisons were made using frequentist network meta-analysis. P-scores were computed to assess relative treatment rankings. Treatment effect was expressed as odds ratio (OR) with 95% confidence intervals (CI). Results: This systematic review included 13 phase III trials with 15468 pts (8890 received ARPi+ADT, 6578 received ADT alone). A total of 596 (6.7%) bone fractures were observed with ARPi+ADT compared to 180 (2.74%) with ADT alone. Patients receiving ARPi+ADT were associated with an increased risk of bone fractures compared to those receiving ADT (OR: 2.40; 95% CI: 1.93-2.98). Sensitivity analyses with HK adjustment showed consistent results (2.40; 1.88-3.06). There was no statistically significant effect modification by PCa clinical setting (p: 0.27). Mixed treatment comparisons showed a statistically significant increased risk of bone fractures with AAP+ADT (2.35; 1.29-4.27), APA+ADT (2.04; 1.47-2.86), and E+ADT (3.13; 2.44-4.00) but not with DARO+ADT (1.30; 0.80-2.08) when compared to ADT alone. Among different ARPi agents, E+ADT was associated with an increased risk compared to APA+ADT (1.54; 1.01-2.33) and DARO+ADT (2.44; 1.41-4.17). Ranking analysis showed that E+ADT was ranked as potentially the least safe treatment (P score: 0.05) in terms of relative fracture risk followed by AAP+ADT (P score: 0.30), APA+ADT (P score: 0.43), DARO+ADT (P score: 0.76). Sensitivity analyses limiting to mCSPC trials only showed consistent results. Conclusions: The risk of bone fractures varies among different ARPi agents, with enzalutamide posing the highest relative risk and darolutamide the lowest. These differences may guide treatment selection, particularly in pts with mCSPC and bone metastases. Prospective studies adjusting for covariates are needed to evaluate bone-protective strategies to mitigate fracture risk particularly in mCSPC patients who are considering treatment with ARPi.

405 Background: Clinical trials are critical to advancing prostate cancer treatment, yet patient enrollment remains a major bottleneck. Despite strong interest in AI for trial matching, real-world use remains limited due to reasons such as complex infrastructure requirements. To address this, we developed a lightweight, scalable AI framework leveraging the Google Healthcare Search API—requiring minimal technical expertise—to automate trial eligibility screening. Methods: We used a pre-trained GPT-5 large language model (LLM) to decompose the eligibility criteria of 13 prostate cancer clinical trials into 269 YES/NO questions, such that for an eligible patient of a given trial, the chart review would yield YES for inclusion and NO for exclusion questions. From 348 patients enrolled in one of the trials, we built a dataset linking each eligibility question to each patient, resulting in 4,947 patient–question pairs (2,034 inclusion pairs with YES labels and 2,913 exclusion pairs with NO labels). The task was framed as binary classification. During evaluation, for each patient–question pair, the LLM extracted search phrases from the question to retrieve relevant EHR information via the Google Healthcare Search API, then used the question and retrieved information to predict YES or NO responses. Performance was measured using accuracy, precision, recall, specificity, and F1 score. Results: Across 4,947 question–patient pairs, our framework achieved 0.81 accuracy, 0.85 precision, 0.65 recall, 0.92 specificity and a F1 score of 0.74. Results for different phases of trials is reported in Table 1, which demonstrates the approach’s robustness across trial phases. Predictions for exclusion criteria were highly precise, while inclusion criteria were more challenging. Most errors were observed in criteria involving complex nested logical conditions, interpretable clinical definitions and data not explicitly measurable or recorded in the EHR (e.g., planned treatments or clinician-assessed scores). Conclusions: This work demonstrates a practical AI framework to support clinical trial matching. The system can identify complex disease states (biochemical recurrence vs radiographic metastasis), castration status (sensitive, resistant) and genomics. Future work should focus on developing human-in-the-loop supervision and improving question decomposition to reduce errors in complex eligibility criteria. Screening performance of the proposed framework across different phases of trials. Trial Phase #Patient-Question Pairs #YES/NO labels Accuracy Precision Recall Specificity F1 score I, II, I/II 4,227 Yes: 1,735 No: 2,492 0.80 0.84 0.66 0.92 0.74 III 720 Yes: 299 No: 421 0.82 0.90 0.63 0.95 0.74 All 4,947 Yes: 2,034 No: 2,913 0.81 0.85 0.65 0.92 0.74 #YES/NO labels: The number of patient-question pairs that are labeled YES/NO among total patient-question pairs of the same row.

Abstract Background The ability of large language models (LLMs) to work collaboratively and screen studies in a systematic review (SR) is under-explored. Hence, we aimed to evaluate the effectiveness of LLMs in automating the process of screening in systematic reviews. Methods This is an observational study which included labeled data (title and abstracts) for five SRs. Originally, two reviewers screened the citations independently for eligibility. A third reviewer cross-checked each citation for quality assurance. GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 were used using zero-shot chain-of-thought prompting. Collaborative approaches included (i): conflict resolution using benefit of the doubt, (ii) majority voting using an independent third LLM and (iii) conflict resolution using an informed third LLM. Performance was assessed using accuracy, precision for exclusion, and recall for inclusion. Work saved over samples (WSS) was computed to estimate the reduction in manual human effort. Results A total of 11300 articles were included in this study. The individual models, GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 exhibited a high precision for exclusion, achieving 99.7%, 99.7%, and 99.2% and high recall for inclusion achieving 95.5%, 96.6% and 85.7%, respectively. However, the collaborative approach utilizing the two best-performing models (GPT-4 and Claude-3S) achieved an average precision of 99.9% and a recall of 98.5% (across all collaborative approaches). Furthermore, the proposed collaborative approach resulted in an average WSS of 63.5%, compared to the average WSS of 45.2% for individual models. Conversational LLM interactions showed a consistent pattern of results. Limitations This study was limited due to reliance on proprietary models, and evaluation on oncology datasets. Conclusion Evidence shows that collaborative LLMs enable efficient, high-performing screening in systematic reviews, supporting continuous evidence updates. Primary funding source NIH (U24CA265879-01-1) and Carolyn-Ann-Kennedy-Bacon Fund.

This guideline has been updated. This ASCO Living Guideline is reviewed on an eight-week cycle. Please see the online dynamic version for the latest updates. Living guidelines are developed for selected topic areas with rapidly evolving evidence that drives frequent change in recommended clinical practice. Living guidelines are updated on a regular schedule by a standing expert panel that systematically reviews the health literature on a continuous basis, as described in the ASCO Guidelines Methodology Manual . ASCO Living Guidelines follow the ASCO Conflict of Interest Policy Implementation for Clinical Practice Guidelines . Living Guidelines and updates are not intended to substitute for independent professional judgment of the treating clinician and do not account for individual variation among patients. See appendix for disclaimers and other important information ( Appendix 1 and Appendix 2 ). Updates are published regularly and can be found at www.asco.org/genitourinary-cancer-guidelines .

399 Background: The standard of care for resectable GEA adenocarcinomas is perioperative chemotherapy with the FLOT (fluorouracil, leucovorin, oxaliplatin, docetaxel) regimen. Recent studies investigating the addition of checkpoint inhibitors (CPIs) to perioperative chemotherapy have shown mixed results. An NMA can leverage both direct and indirect comparisons to evaluate the relative efficacies of available regimens in this setting. Methods: MEDLINE, EMBASE, Scopus, Web of Science and CENTRAL were searched until August 27th, 2025. Eligible studies included phase 3 randomized trials evaluating perioperative or neoadjuvant chemotherapy +/- CPIs ± radiation in resectable GEA. The primary outcomes were disease-free survival (DFS) and overall survival (OS). Hazard ratios and 95% confidence intervals (CIs) were estimated using a frequentist NMA framework. Results: Fifteen trials including 8072 patients were analyzed. For DFS, perioperative durvalumab + FLOT (dFLOT) ranked highest (P-score = 0.99), followed by FLOT (P-score = 0.84) (HR for dFLOT vs. FLOT was 0.71, 95% CI 0.58-0.86). dFLOT also ranked higher than perioperative pembrolizumab + cisplatin and fluorouracil/capecitabine (KN-585), though this comparison was not statistically significant (HR 0.65, 95% CI 0.40-1.04). Compared with CROSS, dFLOT showed superior DFS (HR of 0.48, 95% CI 0.36-0.63). For OS, dFLOT ranked the highest (P-score=0.95) and was superior to CROSS (HR 0.57, 95% CI 0.42-0.77). While dFLOT appeared favorable versus FLOT (HR 0.78, 95% CI 0.62-0.98), this finding was primarily driven by MATTERHORN, which did not meet its prespecified OS significance boundary (P = 0.03 vs threshold P < 0.0001), and the proportional hazards assumption was violated. Similarly, no significant OS difference was observed between dFLOT and the KN-585 arms (HR 0.75, 95% CI 0.45-1.23). Conclusions: In this NMA, perioperative FLOT remained the benchmark regimen for resectable GEA. dFLOT has shown promising early results, ranking the highest for DFS and showing favorable, but not statistically definitive OS trends in comparison to FLOT. Importantly, the network enabled indirect comparisons not tested in head-to-head trials, demonstrating that dFLOT ranked above pembrolizumab+CF/CX (KN-585) without reaching statistical significance, and also outperformed CROSS. However, these findings should be interpreted with caution, as they are primarily driven MATTERHORN data in which OS did not cross the prespecified threshold and proportional hazards assumptions were violated. Perioperative immunotherapy combinations appear promising, but final MATTERHORN results and further confirmatory studies are needed before dFLOT can be considered as a new standard of care.

The emergence of state-of-the-art large language models (LLMs), which hold the ability to generalize to diverse natural language processing tasks, has led to new opportunities in health care. Oncology is especially well-suited to leverage these resources as the journeys of patients with cancer inherently yield extensive, longitudinal data sets comprising clinical narratives, pathology and radiology reports, and genomic sequencing reports. This review begins with an overview of the fundamental concepts behind LLMs, including the definitions, architecture, training paradigm, and performance optimization through prompt engineering and retrieval-augmented generation. We also take a moment to explore the newly emerging paradigm of LLMs in a multiagentic framework. We then synthesize current research on how LLMs may benefit stakeholders within the practice of oncology, including patients, oncologists, researchers, and learners. Finally, we address the limitations and risks of LLMs, including hallucinations, inherent biases, patient privacy, and clinician deskilling. While research thus far shows significant potential for LLMs to transform cancer care, necessary future directions include studies emphasizing patient stakeholder perspectives on LLM incorporation in clinical workflows, the development of relevant clinical benchmarks for LLM evaluation, a greater focus on real-world prospective testing, and deeper exploration of LLM reasoning capabilities.

ABSTRACT Background Symptom management in myeloproliferative neoplasms (MPN) remains challenging despite advancements in disease‐directed therapies. This study assessed the impact of demographic, clinical, laboratory and treatment‐related variables on total symptom scores (TSS) and individual symptom scores in patients with polycythemia vera (PV), essential thrombocythemia (ET), and myelofibrosis (MF). Methods A cohort of 553 patients (PV: 200; ET: 190; MF: 163) was identified through a retrospective chart review. Symptom scores, demographic information and clinical variables were captured at the time of the first TSS assessment. Laboratory results within 1 month and treatment information within 90 days prior to the symptom assessment were captured. Univariable linear regression, followed by multivariable regression analyses using a robust variance estimator were performed, with a p value < 0.05 indicating a significant association. Results MF patients experienced the highest symptom burden and fatigue was the most reported symptom across all MPN subtypes. In PV, depression ( β : 10.53; p = 0.001) was associated with a higher TSS whereas older age (−0.17; 0.01) and higher hemoglobin (−1.24; 0.003) were associated with a lower TSS. In ET, depression ( β : 14.19; p < 0.001) was associated with a higher TSS, whereas in MF, depression (12.28; < 0.001) and higher WBC count (0.22; 0.02) were associated with a higher TSS. Depression and non‐White race in PV, depression in ET, and depression, low hemoglobin, and higher WBC count in MF were associated with multiple symptoms. Conclusions Integrating depression screening and management and optimizing hematologic parameters alongside disease‐directed therapy is crucial to improving patient outcomes.

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well- annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.