Researchers used causal machine learning to model time-dependent treatment effects of radiotherapy and chemotherapy in patients with lower-grade gliomas. The approach aims to infer treatment timelines and effects more precisely than conventional observational comparisons, addressing the complexity of glioma progression and variable response trajectories. Causal machine learning—an approach that estimates what would happen under different treatment conditions—was used to reconstruct time-linked outcomes tied to therapy exposure. The report frames the method as a way to better characterize when treatments matter most along a patient’s disease course. The update is methodological, but it points toward more individualized treatment planning and better interpretation of real-world treatment patterns in glioma.