Matches in SemOpenAlex for { <https://semopenalex.org/work/W3087645508> ?p ?o ?g. }
- W3087645508 abstract "People with type 1 diabetes (T1D) lack the ability to produce the insulin their bodies need. As a result, they must continually make decisions about how much insulin to self-administer to adequately control their blood glucose levels. Longitudinal data streams captured from wearables, like continuous glucose monitors, can help these individuals manage their health, but currently the majority of the decision burden remains on the user. To relieve this burden, researchers are working on closed-loop solutions that combine a continuous glucose monitor and an insulin pump with a control algorithm in an `artificial pancreas.' Such systems aim to estimate and deliver the appropriate amount of insulin. Here, we develop reinforcement learning (RL) techniques for automated blood glucose control. Through a series of experiments, we compare the performance of different deep RL approaches to non-RL approaches. We highlight the flexibility of RL approaches, demonstrating how they can adapt to new individuals with little additional data. On over 2.1 million hours of data from 30 simulated patients, our RL approach outperforms baseline control algorithms: leading to a decrease in median glycemic risk of nearly 50% from 8.34 to 4.24 and a decrease in total time hypoglycemic of 99.8%, from 4,610 days to 6. Moreover, these approaches are able to adapt to predictable meal times (decreasing average risk by an additional 24% as meals increase in predictability). This work demonstrates the potential of deep RL to help people with T1D manage their blood glucose levels without requiring expert knowledge. All of our code is publicly available, allowing for replication and extension." @default.
- W3087645508 created "2020-09-25" @default.
- W3087645508 creator A5016466613 @default.
- W3087645508 creator A5018561083 @default.
- W3087645508 creator A5055037967 @default.
- W3087645508 creator A5080941650 @default.
- W3087645508 date "2020-09-18" @default.
- W3087645508 modified "2023-09-24" @default.
- W3087645508 title "Deep Reinforcement Learning for Closed-Loop Blood Glucose Control" @default.
- W3087645508 cites W1836465849 @default.
- W3087645508 cites W1997449038 @default.
- W3087645508 cites W2001273251 @default.
- W3087645508 cites W2025266922 @default.
- W3087645508 cites W2121346710 @default.
- W3087645508 cites W2135124338 @default.
- W3087645508 cites W2145339207 @default.
- W3087645508 cites W2155639879 @default.
- W3087645508 cites W2157331557 @default.
- W3087645508 cites W2163924481 @default.
- W3087645508 cites W2167160009 @default.
- W3087645508 cites W2176981217 @default.
- W3087645508 cites W2288809108 @default.
- W3087645508 cites W2318233141 @default.
- W3087645508 cites W2320454588 @default.
- W3087645508 cites W2322662949 @default.
- W3087645508 cites W2419628072 @default.
- W3087645508 cites W2587843318 @default.
- W3087645508 cites W2747402019 @default.
- W3087645508 cites W2768908787 @default.
- W3087645508 cites W2773348346 @default.
- W3087645508 cites W2790915589 @default.
- W3087645508 cites W2794757725 @default.
- W3087645508 cites W2796695069 @default.
- W3087645508 cites W2806905826 @default.
- W3087645508 cites W2808068544 @default.
- W3087645508 cites W2889249519 @default.
- W3087645508 cites W2890071448 @default.
- W3087645508 cites W2896893468 @default.
- W3087645508 cites W2904246096 @default.
- W3087645508 cites W2950218667 @default.
- W3087645508 cites W2962676505 @default.
- W3087645508 cites W2962803570 @default.
- W3087645508 cites W2962902376 @default.
- W3087645508 cites W2963120839 @default.
- W3087645508 cites W2978644431 @default.
- W3087645508 cites W2980114199 @default.
- W3087645508 cites W2998965188 @default.
- W3087645508 cites W3008110675 @default.
- W3087645508 cites W414253344 @default.
- W3087645508 hasPublicationYear "2020" @default.
- W3087645508 type Work @default.
- W3087645508 sameAs 3087645508 @default.
- W3087645508 citedByCount "2" @default.
- W3087645508 countsByYear W30876455082020 @default.
- W3087645508 crossrefType "posted-content" @default.
- W3087645508 hasAuthorship W3087645508A5016466613 @default.
- W3087645508 hasAuthorship W3087645508A5018561083 @default.
- W3087645508 hasAuthorship W3087645508A5055037967 @default.
- W3087645508 hasAuthorship W3087645508A5080941650 @default.
- W3087645508 hasConcept C105795698 @default.
- W3087645508 hasConcept C119857082 @default.
- W3087645508 hasConcept C126322002 @default.
- W3087645508 hasConcept C134018914 @default.
- W3087645508 hasConcept C154945302 @default.
- W3087645508 hasConcept C2775924081 @default.
- W3087645508 hasConcept C2779306644 @default.
- W3087645508 hasConcept C2780353609 @default.
- W3087645508 hasConcept C2780473172 @default.
- W3087645508 hasConcept C2780598303 @default.
- W3087645508 hasConcept C2781232474 @default.
- W3087645508 hasConcept C2908918659 @default.
- W3087645508 hasConcept C2986379492 @default.
- W3087645508 hasConcept C33923547 @default.
- W3087645508 hasConcept C41008148 @default.
- W3087645508 hasConcept C555293320 @default.
- W3087645508 hasConcept C71924100 @default.
- W3087645508 hasConcept C97541855 @default.
- W3087645508 hasConceptScore W3087645508C105795698 @default.
- W3087645508 hasConceptScore W3087645508C119857082 @default.
- W3087645508 hasConceptScore W3087645508C126322002 @default.
- W3087645508 hasConceptScore W3087645508C134018914 @default.
- W3087645508 hasConceptScore W3087645508C154945302 @default.
- W3087645508 hasConceptScore W3087645508C2775924081 @default.
- W3087645508 hasConceptScore W3087645508C2779306644 @default.
- W3087645508 hasConceptScore W3087645508C2780353609 @default.
- W3087645508 hasConceptScore W3087645508C2780473172 @default.
- W3087645508 hasConceptScore W3087645508C2780598303 @default.
- W3087645508 hasConceptScore W3087645508C2781232474 @default.
- W3087645508 hasConceptScore W3087645508C2908918659 @default.
- W3087645508 hasConceptScore W3087645508C2986379492 @default.
- W3087645508 hasConceptScore W3087645508C33923547 @default.
- W3087645508 hasConceptScore W3087645508C41008148 @default.
- W3087645508 hasConceptScore W3087645508C555293320 @default.
- W3087645508 hasConceptScore W3087645508C71924100 @default.
- W3087645508 hasConceptScore W3087645508C97541855 @default.
- W3087645508 hasLocation W30876455081 @default.
- W3087645508 hasOpenAccess W3087645508 @default.
- W3087645508 hasPrimaryLocation W30876455081 @default.
- W3087645508 hasRelatedWork W1558069834 @default.
- W3087645508 hasRelatedWork W1773654141 @default.