We present a safety-aware Deep Reinforcement Learning framework for personalized automated insulin delivery. Validated on realistic in silico simulations, it improves glucose control, reduces hypoglycemia risk, lowers insulin dosage, and promotes inclusive access to effective diabetes care.
Safety-Aware Deep-RL for Automated Insulin Delivery: Toward Inclusive Diabetes Care / Lops, Giada; Manfredi, Gioacchino; Racanelli, Vito Andrea; De Cicco, Luca; Mascolo, Saverio. - ELETTRONICO. - (2025). ( Empowering Women in Science: Control Strategies to Close the Diversity and Inclusion Gap Bari June 20, 2025).
Safety-Aware Deep-RL for Automated Insulin Delivery: Toward Inclusive Diabetes Care
Giada Lops
;Gioacchino Manfredi;Vito Andrea Racanelli;Luca De Cicco;Saverio Mascolo
2025
Abstract
We present a safety-aware Deep Reinforcement Learning framework for personalized automated insulin delivery. Validated on realistic in silico simulations, it improves glucose control, reduces hypoglycemia risk, lowers insulin dosage, and promotes inclusive access to effective diabetes care.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
