Abstract
At a glance
Precision oncology has transformed how cancer is characterized, yet clinical decisions often remain reactive. This perspective considers how longitudinal molecular surveillance, evolutionary biology, and computational intelligence could help clinicians anticipate tumour trajectories before resistance or progression becomes clinically established.
Author information
Authors: Louise Chevalier, Camille Laurent, Élodie Bernard, Amélie Girard
Affiliation: PMNCO Laboratory, INSERM U981, Gustave Roussy, Université Paris-Saclay, Villejuif, France
Why forecasting matters
Cancer is not a fixed molecular state. It is an adaptive system shaped by therapy, immune pressure, and the tumour microenvironment. A precise description of disease today does not automatically reveal where it will move tomorrow.
Longitudinal profiling changes the question. Repeated observations through liquid biopsy, residual-disease monitoring, and spatial or single-cell methods can turn isolated snapshots into an evolving clinical trajectory.
Predictive evolutionary oncology
Predictive Evolutionary Oncology brings evolutionary theory, longitudinal biology, and computational modelling into one clinical frame. Its purpose is not perfect prediction; it is to estimate probable futures early enough to influence a decision.
Artificial intelligence is one part of that system, not the system itself. Useful forecasts depend on representative biological data, explicit uncertainty, clinical validation, and models that fit real care pathways.
From prediction to anticipation
The practical opportunity is timing. If clinicians can identify a likely resistant clone or metastatic programme before it dominates, treatment sequencing and surveillance may become proactive rather than reactive.
Prospective trials, standardized evolutionary endpoints, and collaboration across oncology, biology, data science, and ethics will determine whether this framework improves outcomes.
References
- Garraway LA, Verweij J, Ballman KV. Precision oncology: An overview. Journal of Clinical Oncology. 2013;31(15):1803–1805.
- Greaves M, Maley CC. Clonal evolution in cancer. Nature. 2012;481(7381):306–313.
- Wan JCM, Massie C, Garcia-Corbacho J, et al. Liquid biopsies come of age. Nature Reviews Cancer. 2017;17(4):223–238.
How to cite
Chevalier, L., Laurent, C., Bernard, E., & Girard, A. (2026). From monitoring cancer to forecasting its future. Science Academique, 7(2), 67–76.
