The European Society for Medical Oncology (ESMO) Congress 2024 showcased innovative approaches in personalized medicine, immunotherapy resistance, and artificial intelligence (AI)-driven pathology analysis. Presentations focused on the PIONeeR trial, the Rome trial, and the GigaPath AI model offered insights into the future of cancer treatment and diagnosis.
PIONeeR Trial: Addressing Immunotherapy Resistance in NSCLC
Pascale Tomasini, MD, MSc, presented results from the PIONeeR trial, a phase Ib/IIa study designed to overcome resistance to PD-1 and PD-L1 inhibitors in patients with advanced non-small cell lung cancer (NSCLC). The trial enrolled 114 patients with advanced NSCLC who had experienced disease progression after prior PD-1 or PD-L1 inhibitor treatment.
The adaptive design trial evaluated durvalumab in combination with monalizumab (NKG2A inhibitor), oleclumab (CD73 inhibitor), ceralasertib (ATR inhibitor), or savolitinib (MEK inhibitor), compared to docetaxel chemotherapy. The trial's design allowed for the closure of underperforming arms. Two arms, oleclumab and savolitinib, were closed prematurely due to lack of efficacy or interim analysis results.
The primary endpoint, the 12-week disease control rate, was not met by any experimental arm based on predefined Bayesian model targets. The ceralasertib arm showed the highest disease control rate (50%) among experimental arms, comparable to docetaxel (54.5%). Monalizumab had a disease control rate of 24.1%, and savolitinib 13.6%.
Objective response rates were highest with ceralasertib (17.9%) among experimental arms, but lower than docetaxel (25%). Notably, over 40% of patients in the monalizumab arm achieved stable disease.
While no experimental arm demonstrated superiority in progression-free or overall survival, monalizumab (over 11 months) and ceralasertib (over 17 months) showed promising median overall survival durations, compared to 13.8 months with docetaxel.
Dr. Tomasini noted that biomarker analyses are ongoing to identify predictive biomarkers for patient selection in these novel combination approaches.
Rome Trial: Genomic-Guided Therapy Improves Outcomes
Andrea Botticelli, MD, PhD, presented the final results of the Rome trial, a randomized, multibasket phase II multicenter study exploring personalized treatment approaches based on comprehensive genomic profiling. The trial enrolled patients with metastatic solid tumors who had received one or two prior lines of treatment.
Comprehensive genomic profiling was performed using FoundationOne on tissue and liquid biopsies. A molecular tumor board evaluated each case and decided on patient enrollment and treatment allocation. From November 2020 to December 2023, 1,794 patients were screened, with 897 presenting relevant genetic alterations. 400 patients were randomized to either standard of care or targeted therapy based on their mutation profile.
The trial met its primary endpoint, with a significantly higher objective response rate in the targeted therapy arm compared to standard of care (17% vs 9.5%, P < .05). The targeted therapy arm also demonstrated improved progression-free survival, with a median of 3.7 months vs 2.8 months (HR = 0.64, P < .05). The progression-free survival rate at 1 year was 22.3% with targeted therapy vs 7.7% with standard of care.
Overall survival did not significantly differ between the treatment arms (9.2 months vs 7.6 months, HR = 0.89, P < .05), but 52% of patients in the standard-of-care group crossed over to targeted therapy.
In patients with high tumor mutational burden (≥ 10 mutations/megabase) given immunotherapy, median progression-free survival was not reached with targeted therapy vs 2.8 months with standard of care (HR = 0.15, P < .05) in microsatellite instability–high tumors. In microsatellite-stable tumors, median progression-free survival was 3.6 months vs 2.8 months (HR = 0.65, P < .05).
Dr. Botticelli concluded that targeted therapy driven by comprehensive genomic profiling and mutational tumor board evaluation significantly improved outcomes in pretreated patients with metastatic disease.
Prov-GigaPath: AI for Digital Pathology
Carlo B. Bifulco, MD, presented research on Prov-GigaPath, an open-weight, billion-parameter, whole-slide AI foundation model for cancer mutation prediction and tumor microenvironment analysis. The model was trained on 170,000 pathology slides and 1.3 billion image tiles, incorporating image, genomic, and text data.
Prov-GigaPath uses a generative AI context-based approach and learns to predict image patches based on surrounding context, combining image tile and whole-slide–level pretraining. The model demonstrated superior performance in predicting EGFR mutations compared with convolutional neural network–based models.
The Prov-GigaPath model has been released as an open-weight model and has accrued over 140,000 downloads worldwide since its release in May 2024. Independent benchmarks have shown its high performance in tasks beyond those for which it was specifically trained.
Dr. Bifulco concluded that AI models such as Prov-GigaPath could represent a new tool in interpreting and deriving biological insights from complex multimodal data sets in pathology.
