 This paper proposes a novel meta-learning framework for personalized blood glucose level prediction. The authors use nested meta-learning to combine multiple lags into a single model, which can then be applied to different individuals. The proposed framework was evaluated using two publicly available datasets from the Ohio Diabetes Research Center. The results show that the proposed framework outperforms existing methods in terms of both accuracy and precision. This article was authored by Haydar Kadem, Hoda Nemat, Jackie Elliott, and others.