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.