Deep Reinforcement Learning Control of Type-1 Diabetes with Cross-Patient Generalization

Управление сахарным диабетом 1-го типа с помощью глубокого обучения с подкреплением и обобщением на разных пациентах
Mohab M. H. Atanasious, Valentina Becchetti, Federico Baldisseri, Danilo Menegatti, Andrea Wrona
2024-06-11

Deep Deterministic Policy GradientSimglucose simulatorcross-patient generalizationdeep reinforcement learningtype 1 diabetes
Type 1 diabetes is one of the major concerns in current medical studies, as the World Health Organisation plans to reduce mortality due to such disease by one third by 2030. Standard clinical practice involves self-administered injections of insulin, while current research in the field of automatic control of blood glucose concentration mostly focuses on model-based control techniques. This work presents an application of a Deep Reinforcement Learning-based controller for autonomous treatment of type 1 diabetes, building on the Deep Determin-istic Policy Gradient algorithm. Such control framework is applied for the first time on the Python implementation of the UVA/Padova simulator, named Simglucose. The proposed methodology is validated through in-vitro simulations on an inter-cluster cross-generalization group of virtual adult patients, showing that normoglycemia is successfully preserved while assuring cross-patient generalization and outperforming clinical practice, without the direct knowledge of the amount of ingested carbohydrates.
1
A Deep Deterministic Policy Gradient controller is applied to autonomous type 1 diabetes treatment using the Python-based Simglucose implementation of the UVA/Padova simulator.
2
The controller demonstrates cross-patient generalization, maintaining effective glucose control across patients beyond those represented during training.
3
The method outperforms standard clinical practice in simulation without directly knowing the amount of ingested carbohydrates.
4
The proposed deep reinforcement learning framework successfully preserves normoglycemia in in-vitro simulations involving an inter-cluster group of virtual adult patients.

type 1 diabetes treatment represented by virtual adult patients in the Simglucose UVA/Padova simulator

autonomous blood-glucose control for insulin treatment, including normoglycemia preservation and cross-patient generalization without direct carbohydrate-intake information

Publication Details
Publication Date
2024-06-11
Journal
Mediterranean Conference on Control and Automation (MED)
Publisher
Institute of Electrical and Electronics Engineers
ISSN
2325-369X
Cited by
8
Access Type
Author Information
Authors
Mohab M. H. Atanasious
Valentina Becchetti
Federico Baldisseri
Danilo Menegatti
Andrea Wrona
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%