Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.

60 Background: When determining the initial chemotherapy regimen for advanced or metastatic pancreatic cancer, various factors must be evaluated. The decision between FOLFIRINOX and Gemcitabine/Nab-paclitaxel (GnP) is challenging, as patient survival hinges on the efficacy and toxicity profiles of these treatments, alongside individual patient characteristics and vulnerabilities.This study aims to guide the selection of an appropriate first-line chemotherapy regimen for advanced or metastatic pancreatic cancer by leveraging machine learning (ML) methods to predict survival outcomes. Methods: We conducted a retrospective analysis involving a cohort of 151 patients who underwent systemic chemotherapy for advanced or metastatic pancreatic cancer at Gangneung Asan Hospital in South Korea between 2019 and 2023. The initial data consisted of 17 types of demographic and clinical characteristics, as well as time-course of response and survival outcomes. The ML models predicting overall survival (OS) were developed using the XGBoost method. The minimal set of covariates resulting in the highest predictive performance during 5-fold cross validation were chosen as inputs to each model. Results: The median age of the patients was 66 years, with 62.3% being male. The ML models achieved the ROC-AUC of 0.81 when predicting OS after 12 months following the initial administration of FOLFIRINOX (n=61) or GnP (n=47). Five (peritoneal metastases, other metastases, bilirubin level, white blood cell counts, and retroperitoneal lymph node metastases) or four (age, tumor location, sex, and metastatic status) covariates were used to achieve the predictive accuracy for the two regimens, respectively. The median OS of the high versus low risk groups of FOLFIRINOX predicted by the ML models were significantly different (7 vs 18 months, P < 0.01), recording the hazard ratio (HR) of 2.79 (95% CI, 1.47-5.26). Similarly, the median OS of the high and low risk groups of GnP were significantly different (8 vs 16 months, P < 0.001, HR 3.50, 95% CI, 1.60-7.66). Conclusions: We developed the ML models that can compute the probability of OS based on the routinely collected data from patients with advanced or metastatic pancreatic cancer. To the best of our knowledge, this is the first ML solution aimed at aiding clinicians in the selection of the first-line chemotherapy regimen for pancreatic cancer.