Harnessing Unsupervised Machine Learning with [ 18 F]FDG PET/CT to Develop a Composite Model for Predicting Overall Survival in Cervical Cancer Patients Undergoing Concurrent Chemoradiotherapy

Jinyu Shi¹Lian Wang²Min Zhou³Shushan Ge¹Bin ZHANG¹Jiangqin Han^1*Jihui Li^1*Deng Shengming^1*

• ¹The First Affiliated Hospital of Soochow University, Suzhou, China
• ²Department of Oncology, Xuyi People's Hospital, Huaian 211799, China, Xuyi, China
• ³Department of Nuclear Medicine, Yancheng No.1 People's Hospital, Affliated Hospital of Medical School, Nanjing University, Yancheng, China., Yancheng, China

Background and purpose This study sought to develop an advanced composite model to enhance the prognostic accuracy for cervical cancer patients undergoing concurrent chemoradiotherapy (CCRT). The model integrated imaging features from [18F]FDG PET/CT scans with inflammatory markers using a novel unsupervised two-way clustering approach.MethodsIn this retrospective study, 154 patients diagnosed with primary cervical cancer and treated with CCRT were evaluated using [18F]FDG PET/CT scans. A total of 1,702 radiomic features were extracted from the imaging data. These features underwent rigorous selection based on reproducibility and non-redundancy. The unsupervised two-way clustering method was then employed to simultaneously stratify patients and reduce the dimensionality of features, resulting in the generation of meta-features that were subsequently used to predict overall survival.ResultsKaplan-Meier survival analysis demonstrated that the two-way clustering method successfully stratified patients into distinct risk groups with significant survival differences (P<0.001), outperforming traditional K-means clustering. Predictive models constructed using meta-features derived from two-way clustering showed superior performance compared to those using principal component analysis (PCA), particularly when more than four features were included. The highest C-index values for the COX, COX_Lasso, and RSF models were observed with nine meta-features, yielding results of 0.691±0.026, 0.634±0.018, and 0.684±0.020, respectively. In contrast, models based solely on clinical variables exhibited lower predictive performance, with C-index values of 0.645±0.041, 0.567±0.016, and 0.561±0.033. The combination of clinical data, inflammatory markers, and radiomic features achieved the highest predictive accuracy, with a mean AUC of 0.88 ± 0.07.ConclusionIntegrating radiomic data with inflammatory markers using unsupervised two-way clustering offered a robust approach for predicting survival outcomes in cervical cancer patients. This methodology presented a promising avenue for personalized patient management, potentially leading to more informed treatment decisions and improved outcomes.