Breast cancer patients exhibit diverse responses to CDK4/6 inhibitor (CDK4/6i)-based therapies, and identifying eligible patients remains a challenge. Artificial intelligence (AI) has demonstrated the potential to address complex clinical problems. Here, we applied a novel AI-based approach, named as CDK4/6i Response Model (CRM), which combined a previously published method and a scoring model based on random forest algorithm for evaluating breast cancer patients' sensitivity to CDK4/6i-based therapies. To train the CRM, we transformed the genomic data of 980 breast cancer patients from the TCGA database into signaling pathway activity profiles (APSP) by utilizing the modified Damage Assessment of Genomic Mutations (DAGM) algorithm. To mimic the mechanism of action of CDK4/6 inhibitors, a scoring model was then trained to classify the HR+/HER2- and HR-/HER2- breast cancer molecular subtypes by the differential APSP features between the two, which reasonably reflected the potential role played by CDK4/6 molecules in HR+/HER2- breast cancer cells. The effectiveness of the CRM's ability was verified by accurately classifying HR+/HER2- and HR-/HER2- breast cancer patients in a separate local patient cohort (n = 343) in Guangdong, China. Significantly, the scores were observed to be distinct (p = 0.025) between CDK4/6i-treated patients with different responses. Furthermore, breast cancer patients belonging to different subtypes were grouped into five distinct populations based on the scores assigned by the CRM. The results showed not only the heterogenetic responses across subtypes but also more than half of HR+/HER2+ patients might be benefited from CDK4/6i-based treatment. The CRM empowered us to conduct in-silico clinical trials (ICT) on different types of cancer patients responding to CDK4/6i-based therapies. In this study, we performed twin ICT of previously disclosed clinical trials (NCT02246621,NCT02079636,NCT03155997,NCT02513394,NCT02675231), and observed concerted results as the real-world clinical outcomes. These findings show the potential of CRM as a companion diagnostic for CDK4/6i-based therapies and demonstrate promising applications by ICT to guide pan-cancer treatment using CDK4/6 inhibitors in the clinical ends.