The prognosis for pancreatic cancer (PC) is poor, with a 5-year survival rate of approximately 10%. Methods such as machine learning (ML) can facilitate prognostic assessments by examining complex patterns in patient data that may not be discernible with traditional methods. The aim of this study was to analyze prognostic factors that may influence overall survival in advanced-stage PC using ML methods, and to evaluate the performance of various ML algorithms in predicting patient survival outcomes. A total of 315 patients with inoperable locally advanced or metastatic PC between 2005 and 2023 were included in the study. MATLAB software was used for feature selection. Overall survival was defined as the time from diagnosis to death or last follow-up, and was used as the primary parameter for analysis. The power of 19 clinical and laboratory features of the patients to predict whether patients were deceased, as reflected by importance scores (F-scores), was evaluated using the minimum redundancy–maximum relevance, chi-square, analysis of variance, and Kruskal–Wallis tests as feature selection methods. 24 ML methods were evaluated with these feature selection methods and the results regarding the most effective features were used to predict whether patients were deceased or not. The median age of the patients was 62 years, and 30.5% were women while 69.5% were men. As a result of the analysis of the feature selection methods, the first-line chemotherapy a patient received had the highest F-score in predicting that patient’s survival. Among ML methods, the support vector machine (SVM) kernel method had the highest accuracy rate (87%) in predicting whether patients were deceased. When the feature selection methods were combined with the SVM kernel ML method, patients’ survival statuses could be predicted with an accuracy rate of 87.9%. The SVM kernel method has been demonstrated to show potential as a means of predicting survival for patients with advanced PC. The integration of feature selection with this method yielded high accuracy, thereby underscoring its significance. The findings emphasize the pivotal function of first-line chemotherapy and indicate that ML models have the potential to enhance clinical decision-making and patient care.

The prognostic role of fibroblast growth factor 11 (FGF11) has only been reported in cancers such as nasopharyngeal carcinoma and prostate cancer. The role of FGF11 in breast cancer is not fully known. It was aimed to compare FGF11 expression levels in de novo metastatic hormone receptor-positive, human epidermal reseptor-2-negative breast tumor tissue and healthy breast tissue and investigate the effect of the FGF11 expression on survival in breast cancer patients. To determine the FGF11 expression rate, breast tumor tissue of breast cancer patients diagnosed by breast biopsy and healthy breast tissue of healthy individuals who underwent breast biopsy due to benign lesions were used. The study population included 38 breast cancer patients and 24 healthy controls. The number of patients with a FGF11 expression level score of 1 (15.8% vs 12.5%), score of 2 (18.4% vs 12.5%), and score of 3 (31.6% vs 0%) was significantly higher in the patient group compared to the healthy control group. The median overall survival and progression-free survival were numerically better in the group with a FGF11 expression score of 0 to 1 than the group with a FGF11 expression score of 2 and 3, but this difference was not statistically significant. FGF11 may be a predictive marker for breast cancer formation. Additionally, with new FGF11-targeted treatment agents to be developed, endocrine resistance may be reduced, and better survival results may be achieved in hormone receptor-positive, human epidermal reseptor-2-negative breast cancer.