The analysis of the combined effects of anti-cancer drugs remains limited, especially with DNA quantity data analysis using flow cytometry (FCM). In this study, we aimed to develop a more applicable analytical method combining FCM and machine learning to evaluate the combined effects of anti-cancer drugs more objectively. Human gastric cancer cell lines MKN45, MKN28, and KATO III were treated with platinum-based drugs cisplatin (CDDP) and oxaliplatin (LOHP), both alone and in combination, for 24 hrs. Cells were then fixed and stained with propidium iodide (PI) for DNA content analysis by FCM. A random forest model using Python's scikit-learn was applied to the obtained dataset (comprising four groups: non-drug-treated control, CDDP alone, LOHP alone, and combination). The model successfully distinguished between groups with over 95% accuracy by utilizing not only PI fluorescence intensity but also cell size (with forward scatter, FSC) and internal structural complexity (with side scatter, SSC) as features. An analysis of the combination effects revealed different trends depending on the cell line, with MKN45 showing effects similar to LOHP alone and KATO III showing effects similar to CDDP alone. This novel analytical method enables a more objective evaluation of drug combination effects that are difficult to capture with conventional statistical analysis, potentially contributing to the optimization of future cancer treatment strategies.