A Generalized Evolutionary Classifier (EC) for Evolutionarily Guided Precision Medicine (EGPM)

Precision medicine (PM) matches patients to therapies, utilizing traditional biomarker classifiers. Dynamic precision medicine (DPM) is an evolutionarily directed approach which adapts every six weeks, plans ahead for future resistance development, incorporates multiple therapeutic agents, and may improve survival (simulated hazard ratio DPM:PM, HR-DPM/PM, 0.52). We developed an evolutionary classifier (EC) to select patients who benefit from DPM. Subclonal prevalence and growth, mutation, and drug sensitivity parameters determine each DPM recommended adaptation (move). In simulations, if the first two moves are identical for DPM and PM, patients will not benefit (90% negative predictive value). The first two moves provide nearly the benefit of 40 moves. Patients benefiting equally between 2 and 40 moves have extraordinary predicted benefit (HR-DPM/PM 0.04). This EC development paradigm may apply to other dynamic cancer models despite different underlying assumptions. It may reduce the duration and frequency of required monitoring, and also enable “window” clinical trials. STATEMENT OF SIGNIFICANCE Biomarker classifiers match patients to therapies. Dynamic precision medicine (DPM) directs therapeutic sequence and timing using evolutionary dynamics. We present an evolutionary classifier (EC) for predicting patient benefit from DPM, discovering that many require only briefly, thereby improving cost-effectiveness. This approach may generalize to other evolutionarily directed strategies. ### Competing Interest Statement RAB consults for or has recently consulted for AstraZeneca, CStone, EMD Serono, Vertex, and Zymeworks. He is the Chief Scientific Officer of Onco-Mind. The other authors declare no competing interests. ### Funding Statement Supported in part by The Royal Society International Exchanges Award to DP and RAB. ### 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: Theoretical/Computational Study, no real patients were used, and no IRB was necessary. All necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived. 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 and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable. Yes The data from the study is derived from computational simulations, the methods for their generation and recreation are provided in Beckman et. al., PNAS (2012) https://doi.org/10.1073/pnas.1203559109