FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212775672> ?p ?o ?g. }

• W4212775672 abstract "Despite a great deal of interest in the application of artificial intelligence (AI) to sepsis/critical illness, most current approaches are limited in their potential impact: prediction models do not (and cannot) address the lack of effective therapeutics and current approaches to enhancing the treatment of sepsis focus on optimizing the application of existing interventions, and thus cannot address the development of new treatment options/modalities. The inability to test new therapeutic applications was highlighted by the generally unsatisfactory results from drug repurposing efforts in COVID-19.Addressing this challenge requires the application of simulation-based, model-free deep reinforcement learning (DRL) in a fashion akin to training the game-playing AIs. We have previously demonstrated the potential of this method in the context of bacterial sepsis in which the microbial infection is responsive to antibiotic therapy. The current work addresses the control problem of multi-modal, adaptive immunomodulation in the circumstance where there is no effective anti-pathogen therapy (e.g., in a novel viral pandemic or in the face of resistant microbes).This is a proof-of-concept study that determines the controllability of sepsis without the ability to pharmacologically suppress the pathogen. We use as a surrogate system a previously validated agent-based model, the Innate Immune Response Agent-based Model (IIRABM), for control discovery using DRL. The DRL algorithm 'trains' an AI on simulations of infection where both the control and observation spaces are limited to operating upon the defined immune mediators included in the IIRABM (a total of 11). Policies were learned using the Deep Deterministic Policy Gradient approach, with the objective function being a return to baseline system health.DRL trained an AI policy that improved system mortality from 85% to 10.4%. Control actions affected every one of the 11 targetable cytokines and could be divided into those with static/unchanging controls and those with variable/adaptive controls. Adaptive controls primarily targeted 3 different aspects of the immune response: 2 nd order pro-inflammation governing TH1/TH2 balance, primary anti-inflammation, and inflammatory cell proliferation.The current treatment of sepsis is hampered by limitations in therapeutic options able to affect the biology of sepsis. This is heightened in circumstances where no effective antimicrobials exist, as was the case for COVID-19. Current AI methods are intrinsically unable to address this problem; doing so requires training AIs in contexts that fully represent the counterfactual space of potential treatments. The synthetic data needed for this task is only possible through the use of high-resolution, mechanism-based simulations. Finally, being able to treat sepsis will require a reorientation as to the sensing and actuating requirements needed to develop these simulations and bring them to the bedside." @default.
• W4212775672 created "2022-02-24" @default.
• W4212775672 creator A5005224275 @default.
• W4212775672 creator A5013370370 @default.
• W4212775672 creator A5033965192 @default.
• W4212775672 date "2022-02-18" @default.
• W4212775672 modified "2023-09-29" @default.
• W4212775672 title "Preparing for the next COVID: Deep Reinforcement Learning trained Artificial Intelligence discovery of multi-modal immunomodulatory control of systemic inflammation in the absence of effective anti-microbials" @default.
• W4212775672 cites W1526693451 @default.
• W4212775672 cites W1586165122 @default.
• W4212775672 cites W1977523316 @default.
• W4212775672 cites W2065699321 @default.
• W4212775672 cites W2119124369 @default.
• W4212775672 cites W2557183043 @default.
• W4212775672 cites W2607074353 @default.
• W4212775672 cites W2617620062 @default.
• W4212775672 cites W2618126485 @default.
• W4212775672 cites W2766447205 @default.
• W4212775672 cites W2786438063 @default.
• W4212775672 cites W2902907165 @default.
• W4212775672 cites W2912926578 @default.
• W4212775672 cites W2951611630 @default.
• W4212775672 cites W2982316857 @default.
• W4212775672 cites W3023650684 @default.
• W4212775672 cites W3037185429 @default.
• W4212775672 cites W3038796705 @default.
• W4212775672 cites W3043083362 @default.
• W4212775672 cites W3049368833 @default.
• W4212775672 cites W3087156149 @default.
• W4212775672 cites W3092608315 @default.
• W4212775672 cites W3096464600 @default.
• W4212775672 cites W3106337323 @default.
• W4212775672 cites W3112044717 @default.
• W4212775672 cites W3120408379 @default.
• W4212775672 cites W3141007276 @default.
• W4212775672 cites W3163822529 @default.
• W4212775672 cites W3177828909 @default.
• W4212775672 cites W4200371263 @default.
• W4212775672 cites W4210642183 @default.
• W4212775672 doi "https://doi.org/10.1101/2022.02.17.480940" @default.
• W4212775672 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35194613" @default.
• W4212775672 hasPublicationYear "2022" @default.
• W4212775672 type Work @default.
• W4212775672 citedByCount "4" @default.
• W4212775672 countsByYear W42127756722022 @default.
• W4212775672 crossrefType "posted-content" @default.
• W4212775672 hasAuthorship W4212775672A5005224275 @default.
• W4212775672 hasAuthorship W4212775672A5013370370 @default.
• W4212775672 hasAuthorship W4212775672A5033965192 @default.
• W4212775672 hasBestOaLocation W42127756721 @default.
• W4212775672 hasConcept C119857082 @default.
• W4212775672 hasConcept C127413603 @default.
• W4212775672 hasConcept C151730666 @default.
• W4212775672 hasConcept C154945302 @default.
• W4212775672 hasConcept C2779343474 @default.
• W4212775672 hasConcept C41008148 @default.
• W4212775672 hasConcept C519536355 @default.
• W4212775672 hasConcept C548081761 @default.
• W4212775672 hasConcept C71924100 @default.
• W4212775672 hasConcept C86803240 @default.
• W4212775672 hasConcept C97541855 @default.
• W4212775672 hasConceptScore W4212775672C119857082 @default.
• W4212775672 hasConceptScore W4212775672C127413603 @default.
• W4212775672 hasConceptScore W4212775672C151730666 @default.
• W4212775672 hasConceptScore W4212775672C154945302 @default.
• W4212775672 hasConceptScore W4212775672C2779343474 @default.
• W4212775672 hasConceptScore W4212775672C41008148 @default.
• W4212775672 hasConceptScore W4212775672C519536355 @default.
• W4212775672 hasConceptScore W4212775672C548081761 @default.
• W4212775672 hasConceptScore W4212775672C71924100 @default.
• W4212775672 hasConceptScore W4212775672C86803240 @default.
• W4212775672 hasConceptScore W4212775672C97541855 @default.
• W4212775672 hasLocation W42127756721 @default.
• W4212775672 hasLocation W42127756722 @default.
• W4212775672 hasLocation W42127756723 @default.
• W4212775672 hasOpenAccess W4212775672 @default.
• W4212775672 hasPrimaryLocation W42127756721 @default.
• W4212775672 hasRelatedWork W1562959674 @default.
• W4212775672 hasRelatedWork W2748952813 @default.
• W4212775672 hasRelatedWork W2899084033 @default.
• W4212775672 hasRelatedWork W2923653485 @default.
• W4212775672 hasRelatedWork W2952472710 @default.
• W4212775672 hasRelatedWork W2957776456 @default.
• W4212775672 hasRelatedWork W3022038857 @default.
• W4212775672 hasRelatedWork W4255994452 @default.
• W4212775672 hasRelatedWork W4319083788 @default.
• W4212775672 hasRelatedWork W4361026739 @default.
• W4212775672 isParatext "false" @default.
• W4212775672 isRetracted "false" @default.
• W4212775672 workType "article" @default.