Prediction of individual survival and trial outcomes for anti-PDL1 treatment in non-small cell lung cancer using blood markers-based kinetics-machine learning

Current predictive models for survival following immune-checkpoint inhibition in non-small cell lung cancer typically use baseline or tumor kinetics data. We propose a novel kinetics-machine learning (kML) integrative model of overall survival following anti-PDL1 treatment. It incorporates eleven baseline markers and four on-treatment blood markers: albumin, C-reactive protein, lactate dehydrogenase and neutrophils. The kinetics of the latter were modeled using nonlinear mixed effect modeling. The kML model was developed on three phase 2 trials (862 patients) and validated on a phase 3 trial (553 patients). It outperforms the current state-of-the-art for individual predictions with a test set c-index of 0.79, a 12-months AUC of 0.86 and a hazard ratio of 17.3 (95% CI: 8.11–36.7, p < 0.0001) for identification of long-term survivors. kML was also able to anticipate the success of the phase 3 trial by utilizing only 25 weeks of on-study data. It constitutes a valuable approach to support personalized medicine and drug development. ### Competing Interest Statement This work was sponsored by the Roche Pharma Research and Early Development (pRED) One-D Modeling and Simulation Digital Initiative. It also benefited from funding from ITMO Cancer AVIESAN and French Institut National du Cancer (grant #19CM148-00) ### Funding Statement This work was sponsored by the Roche Pharma Research and Early Development (pRED) One-D Modeling and Simulation Digital Initiative. It also benefited from funding from ITMO Cancer AVIESAN and French Institut National du Cancer (grant #19CM148-00) ### 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: The POPLAR ([NCT01903993][1]) study was done in full accordance with the guidelines for Good Clinical Practice and the Declaration of Helsinki. Protocol (and modification) approval was obtained from an independent ethics committee for each site. FIR ([NCT01846416][2]) was approved by the relevant institutional review or ethics committees and was conducted in accordance with the Declaration of Helsinki and Good Clinical Practice guidelines. All patients provided written informed consent. BIRCH ([NCT02031458][3]) study protocol and amendments were approved by institutional review boards or ethics committees. BIRCH was conducted in accordance with the Declaration of Helsinki and International Conference on Harmonisation Guidelines for Good Clinical Practice. The OAK clinical trial ([NCT02008227][4]) was conducted in accordance with the Declaration of Helsinki and International Conference on Harmonisation Guidelines for Good Clinical Practice. 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 Qualified researchers may request access to individual patient level data through the clinical study data request platform (https://vivli.org/). Further details on Roche's criteria for eligible studies are available here (https://vivli.org/members/ourmembers/). For further details on Roche's Global Policy on the Sharing of Clinical Information and how to request access to related clinical study documents please refer to the Roche website (https://www.roche.com/innovation/process/clinical-trials/data-sharing/). [1]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT01903993&atom=%2Fmedrxiv%2Fearly%2F2023%2F09%2F26%2F2023.09.26.23296135.atom [2]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT01846416&atom=%2Fmedrxiv%2Fearly%2F2023%2F09%2F26%2F2023.09.26.23296135.atom [3]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT02031458&atom=%2Fmedrxiv%2Fearly%2F2023%2F09%2F26%2F2023.09.26.23296135.atom [4]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT02008227&atom=%2Fmedrxiv%2Fearly%2F2023%2F09%2F26%2F2023.09.26.23296135.atom