AI-based Model CRM to Evaluate the Responses of Breast Cancer Patients to CDK4/6 Inhibitors-Based Therapies and Simulate Real-World Clinical Trials

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][1], [NCT02079636][2], [NCT03155997][3], [NCT02513394][4], [NCT02675231][5]), 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. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This work was supported by National Natural Science Foundation of China (grant no. 82072939 to M. Yang), Natural Science Foundation of Guangdong Province (grant no. 2022A1515010425 to M. Yang), Guangzhou Science and Technology Program (grant no. 202206010110 to M. Yang), Hefei National Laboratory for Physical Sciences at the Microscale (grant no. KF2020009 to G. Niu). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Ethics committee of Guangdong Provincial People's Hospital gave ethical approval for this work I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors [1]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT02246621&atom=%2Fmedrxiv%2Fearly%2F2023%2F05%2F16%2F2023.05.15.23289976.atom [2]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT02079636&atom=%2Fmedrxiv%2Fearly%2F2023%2F05%2F16%2F2023.05.15.23289976.atom [3]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT03155997&atom=%2Fmedrxiv%2Fearly%2F2023%2F05%2F16%2F2023.05.15.23289976.atom [4]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT02513394&atom=%2Fmedrxiv%2Fearly%2F2023%2F05%2F16%2F2023.05.15.23289976.atom [5]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT02675231&atom=%2Fmedrxiv%2Fearly%2F2023%2F05%2F16%2F2023.05.15.23289976.atom