Abstract 44P
Background
Immunotherapy has significantly improved survival outcomes for patients with metastatic renal cell carcinoma (mRCC). However, considerable variability exists in patient survival. Machine learning (ML) models offer an opportunity to harness diverse patient data to predict survival outcomes and tailor treatment strategies. This study aimed to develop ML models to predict the overall survival (OS) in mRCC patients receiving first-line immunotherapy.
Methods
We analysed 4895 mRCC patients from the National Cancer Database who received first-line immunotherapy since 2015. Fifteen features were selected based on the univariate Cox regression for OS, including demographics, Charlson-Deyo Score, tumour side, grade, lymph vascular invasion, and prior surgery or radiotherapy. Missing values were imputed using K-Nearest Neighbors. The data was split into training (70%) and testing (30%) sets. Classification and regression models were compared using hyperparameter tuning and 5-fold cross-validation. The SMOT technique addressed class imbalance.
Results
The 1-year and 3-year OS were 32.7% and 9.9%, respectively. Among the classification models, CatBoost demonstrated the best performance, with an area under curve (AUC) of 0.87, followed by LightGBM (0.86), XGBoost (0.86), and Decision Tree (0.86). The Decision Tree model achieved the highest F1 score (0.57), indicating a good balance between precision and recall. However, simpler models like Naive Bayes showed lower performance across all metrics. In the regression task, CatBoost also achieved the best performance, with a Mean Squared Error (MSE) of 115.5 and an R2 score of 0.52, indicating robust predictive accuracy. Feature importance analysis showed that tumour grade was the most significant predictor, followed by prior surgery and patient age. Socioeconomic factors, such as insurance status and facility type, also contributed significantly to the outcomes, while race had minimal predictive importance in this cohort.
Conclusions
Ensemble methods, particularly CatBoost, show superior performance in predicting mRCC outcomes. Tumour grade, surgery, and patient age emerged as key predictors.
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
99P - Real-world management of ir-colitis, a Danish 10-year cohort study
Presenter: Soeren Petersen
Session: Poster Display session
Resources:
Abstract
101P - Comparison on the effectiveness of multiple single and double immunotherapy treatments on advanced angiosarcoma patients: Meta analysis & systematic review
Presenter: Enzo Marson
Session: Poster Display session
Resources:
Abstract
102P - A real-world study of the efficacy of second-line treatment of unresectable hepatocellular carcinoma after progression on first-line lenvatinib combined with PD-1 inhibitor
Presenter: Saifeng Li
Session: Poster Display session
Resources:
Abstract
103P - Tislelizumab combined with chemoradiotherapy for locally advanced esophageal squamous cell carcinoma: A multicenter, prospective, single-arm, real-world study
Presenter: zhihua wen
Session: Poster Display session
Resources:
Abstract
104P - The efficacy and safety of a novel PD-1/CTLA-4 bispecific antibody cadonilimab (AK104) as second- or later-line therapy for metastatic non-small cell lung cancer
Presenter: Hualin Chen
Session: Poster Display session
Resources:
Abstract
105P - A retrospective study using machine learning to analyze the effects of VEGFR-TKIs and PD-1 inhibitors as third-line or later treatment in patients with MSS mCRC
Presenter: Shumei Han
Session: Poster Display session
Resources:
Abstract
106P - Immunotherapy after progression to double immunotherapy: Pembrolizumab and Lenvatinib versus conventional chemotherapy for patients with metastatic melanoma after failure of PD-1/CTLA-4 inhibition
Presenter: Dimitrios Ziogas
Session: Poster Display session
Resources:
Abstract
107P - Efficacy and safety of first-line TKI plus ICI therapy in metastatic non-clear cell renal cell carcinoma: A real-world multiple-centre study
Presenter: Yulu Peng
Session: Poster Display session
Resources:
Abstract
108P - Transarterial chemoembolization (TACE) combined with atezolizumab and bevacizumab versus TACE alone in patients with Barcelona Clinic liver cancer stage B unresectable hepatocellular carcinoma: A retrospective, propensity score-matched analysis
Presenter: Hongjie Cai
Session: Poster Display session
Resources:
Abstract
109P - Efficacy of first-line immune-based combined systemic therapy and brain radiotherapy in patients with brain metastases (BM) from driver gene-negative NSCLC
Presenter: Mengxing You
Session: Poster Display session
Resources:
Abstract