Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140623462> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3140623462 abstract "Introduction: Developing reliable medication dosing guidelines is challenging because individual dose-response relationships are mitigated by both static (e. g., demographic) and dynamic factors (e.g., kidney function). In recent years, several data-driven medication dosing models have been proposed for sedatives, but these approaches have been limited in their ability to assess interindividual differences and compute individualized doses. Objective: The primary objective of this study is to develop an individualized framework for sedative-hypnotics dosing. Method: Using publicly available data (1,757 patients) from the MIMIC IV intensive care unit database, we developed a sedation management agent using deep reinforcement learning. More specifically, we modeled the sedative dosing problem as a Markov Decision Process and developed an RL agent based on a deep deterministic policy gradient approach with a prioritized experience replay buffer to find the optimal policy. We assessed our method's ability to jointly learn an optimal personalized policy for propofol and fentanyl, which are among commonly prescribed sedative-hypnotics for intensive care unit sedation. We compared our model's medication performance against the recorded behavior of clinicians on unseen data. Results: Experimental results demonstrate that our proposed model would assist clinicians in making the right decision based on patients' evolving clinical phenotype. The RL agent was 8% better at managing sedation and 26% better at managing mean arterial compared to the clinicians' policy; a two-sample t-test validated that these performance improvements were statistically significant (p < 0.05). Conclusion: The results validate that our model had better performance in maintaining control variables within their target range, thereby jointly maintaining patients' health conditions and managing their sedation." @default.
- W3140623462 created "2021-04-13" @default.
- W3140623462 creator A5054997546 @default.
- W3140623462 creator A5071524422 @default.
- W3140623462 creator A5076266282 @default.
- W3140623462 date "2021-03-31" @default.
- W3140623462 modified "2023-09-27" @default.
- W3140623462 title "Patient-Specific Sedation Management via Deep Reinforcement Learning" @default.
- W3140623462 cites W1509868643 @default.
- W3140623462 cites W1978815455 @default.
- W3140623462 cites W1980840327 @default.
- W3140623462 cites W1998875285 @default.
- W3140623462 cites W2018910203 @default.
- W3140623462 cites W2091631034 @default.
- W3140623462 cites W2138928595 @default.
- W3140623462 cites W2159167585 @default.
- W3140623462 cites W2162800060 @default.
- W3140623462 cites W2193923384 @default.
- W3140623462 cites W2317878958 @default.
- W3140623462 cites W2328867239 @default.
- W3140623462 cites W2345460154 @default.
- W3140623462 cites W2535327675 @default.
- W3140623462 cites W2592964660 @default.
- W3140623462 cites W2886941630 @default.
- W3140623462 cites W2896893468 @default.
- W3140623462 cites W2898645858 @default.
- W3140623462 cites W2899397942 @default.
- W3140623462 cites W2908893749 @default.
- W3140623462 cites W2911236815 @default.
- W3140623462 cites W2937671098 @default.
- W3140623462 cites W3025019304 @default.
- W3140623462 cites W3040948586 @default.
- W3140623462 cites W4253096148 @default.
- W3140623462 cites W615876487 @default.
- W3140623462 cites W875859 @default.
- W3140623462 doi "https://doi.org/10.3389/fdgth.2021.608893" @default.
- W3140623462 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8521809" @default.
- W3140623462 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34713090" @default.
- W3140623462 hasPublicationYear "2021" @default.
- W3140623462 type Work @default.
- W3140623462 sameAs 3140623462 @default.
- W3140623462 citedByCount "2" @default.
- W3140623462 countsByYear W31406234622021 @default.
- W3140623462 countsByYear W31406234622022 @default.
- W3140623462 crossrefType "journal-article" @default.
- W3140623462 hasAuthorship W3140623462A5054997546 @default.
- W3140623462 hasAuthorship W3140623462A5071524422 @default.
- W3140623462 hasAuthorship W3140623462A5076266282 @default.
- W3140623462 hasBestOaLocation W31406234621 @default.
- W3140623462 hasConcept C119857082 @default.
- W3140623462 hasConcept C154945302 @default.
- W3140623462 hasConcept C177713679 @default.
- W3140623462 hasConcept C2776277131 @default.
- W3140623462 hasConcept C2776376669 @default.
- W3140623462 hasConcept C2776814716 @default.
- W3140623462 hasConcept C2777288759 @default.
- W3140623462 hasConcept C2777602617 @default.
- W3140623462 hasConcept C2781072394 @default.
- W3140623462 hasConcept C41008148 @default.
- W3140623462 hasConcept C42219234 @default.
- W3140623462 hasConcept C71924100 @default.
- W3140623462 hasConcept C97541855 @default.
- W3140623462 hasConcept C98274493 @default.
- W3140623462 hasConceptScore W3140623462C119857082 @default.
- W3140623462 hasConceptScore W3140623462C154945302 @default.
- W3140623462 hasConceptScore W3140623462C177713679 @default.
- W3140623462 hasConceptScore W3140623462C2776277131 @default.
- W3140623462 hasConceptScore W3140623462C2776376669 @default.
- W3140623462 hasConceptScore W3140623462C2776814716 @default.
- W3140623462 hasConceptScore W3140623462C2777288759 @default.
- W3140623462 hasConceptScore W3140623462C2777602617 @default.
- W3140623462 hasConceptScore W3140623462C2781072394 @default.
- W3140623462 hasConceptScore W3140623462C41008148 @default.
- W3140623462 hasConceptScore W3140623462C42219234 @default.
- W3140623462 hasConceptScore W3140623462C71924100 @default.
- W3140623462 hasConceptScore W3140623462C97541855 @default.
- W3140623462 hasConceptScore W3140623462C98274493 @default.
- W3140623462 hasLocation W31406234621 @default.
- W3140623462 hasLocation W31406234622 @default.
- W3140623462 hasLocation W31406234623 @default.
- W3140623462 hasLocation W31406234624 @default.
- W3140623462 hasLocation W31406234625 @default.
- W3140623462 hasOpenAccess W3140623462 @default.
- W3140623462 hasPrimaryLocation W31406234621 @default.
- W3140623462 hasRelatedWork W2001683931 @default.
- W3140623462 hasRelatedWork W2053864670 @default.
- W3140623462 hasRelatedWork W2360430513 @default.
- W3140623462 hasRelatedWork W2364740953 @default.
- W3140623462 hasRelatedWork W2373094126 @default.
- W3140623462 hasRelatedWork W2373281146 @default.
- W3140623462 hasRelatedWork W2406168803 @default.
- W3140623462 hasRelatedWork W2779957514 @default.
- W3140623462 hasRelatedWork W2980005765 @default.
- W3140623462 hasRelatedWork W3038092059 @default.
- W3140623462 hasVolume "3" @default.
- W3140623462 isParatext "false" @default.
- W3140623462 isRetracted "false" @default.
- W3140623462 magId "3140623462" @default.
- W3140623462 workType "article" @default.