FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136191756> ?p ?o ?g. }

• W3136191756 abstract "Abstract Background: The rapid spread of coronavirus disease COVID 19 calls for early screening and monitoring of these patients to distinguish those that are likely to worsen from stable patients that may be directed to intermediate care facilities. We designed an algorithm for COVID-19 patients severity assessment, dynamic intubation and prolonged stay prediction using the Breathing Frequency (BF) and oxygen saturation (SPO2) signals. Methods We recorded BF, and SPO2 signals of confirmed COVID-19 patients admitted during the first and second outbreak of the pandemic in France (March to May 2020 and September 2020 to February 2021) in an ICU of a teaching hospital. We extracted four features from the signals that represent the four last hours before intubation for intubated patients and the mean of the four hours before the median intubation time for non-intubated patients. These data were used to train AI algorithms for intubation recognition. Algorithm robustness was checked on a validation set of patients. We selected the best algorithm that was applied every hour to predict intubation, thus a severity evaluation. We performed a 24h moving average of these predictions giving a S 24 severity score that represent the patient's severity during the last 24 h. MS 24 , the maximum of S 24 was confronted with the risk of intubation and prolonged ICU stay (> 5 days). Results We included 177 patients. Among the tested algorithms, the Logistic regression classifier had the best performance. The model had an accuracy of 88.9 % for intubation recognition (AUC = 0.92). The accuracy on the validation set was 92.6 %. The S 24 score of intubated patients was significantly higher than non-intubated patients 48h before intubation and increased 24 hours before intubation. MS 24 score allows distinguishing three severity situations with an increased risk of intubation: green (3%), orange (30%) and red (76%). A MS 24 score superior to 20 was highly predictive of an ICU stay greater than 5 day with an accuracy of 88.8% (AUC = 0.95). Conclusions The score we designed uses simple signals and seems to be efficient to visualize the patient's respiratory situation and may help in decision-making. Real-time computation is easy to implement." @default.
• W3136191756 created "2021-03-29" @default.
• W3136191756 creator A5007346051 @default.
• W3136191756 creator A5007581800 @default.
• W3136191756 creator A5016770480 @default.
• W3136191756 creator A5022871206 @default.
• W3136191756 creator A5023693295 @default.
• W3136191756 creator A5025408711 @default.
• W3136191756 creator A5031859187 @default.
• W3136191756 creator A5047949708 @default.
• W3136191756 creator A5051759836 @default.
• W3136191756 creator A5052175373 @default.
• W3136191756 creator A5054521211 @default.
• W3136191756 creator A5065960824 @default.
• W3136191756 creator A5069282599 @default.
• W3136191756 creator A5072148310 @default.
• W3136191756 creator A5081132575 @default.
• W3136191756 date "2021-03-18" @default.
• W3136191756 modified "2023-10-14" @default.
• W3136191756 title "Artificial Intelligence helps triage and monitoring of COVID-19 Intensive Care patients" @default.
• W3136191756 doi "https://doi.org/10.21203/rs.3.rs-307816/v1" @default.
• W3136191756 hasPublicationYear "2021" @default.
• W3136191756 type Work @default.
• W3136191756 sameAs 3136191756 @default.
• W3136191756 citedByCount "0" @default.
• W3136191756 crossrefType "posted-content" @default.
• W3136191756 hasAuthorship W3136191756A5007346051 @default.
• W3136191756 hasAuthorship W3136191756A5007581800 @default.
• W3136191756 hasAuthorship W3136191756A5016770480 @default.
• W3136191756 hasAuthorship W3136191756A5022871206 @default.
• W3136191756 hasAuthorship W3136191756A5023693295 @default.
• W3136191756 hasAuthorship W3136191756A5025408711 @default.
• W3136191756 hasAuthorship W3136191756A5031859187 @default.
• W3136191756 hasAuthorship W3136191756A5047949708 @default.
• W3136191756 hasAuthorship W3136191756A5051759836 @default.
• W3136191756 hasAuthorship W3136191756A5052175373 @default.
• W3136191756 hasAuthorship W3136191756A5054521211 @default.
• W3136191756 hasAuthorship W3136191756A5065960824 @default.
• W3136191756 hasAuthorship W3136191756A5069282599 @default.
• W3136191756 hasAuthorship W3136191756A5072148310 @default.
• W3136191756 hasAuthorship W3136191756A5081132575 @default.
• W3136191756 hasBestOaLocation W31361917561 @default.
• W3136191756 hasConcept C126322002 @default.
• W3136191756 hasConcept C151956035 @default.
• W3136191756 hasConcept C177713679 @default.
• W3136191756 hasConcept C194828623 @default.
• W3136191756 hasConcept C2777120189 @default.
• W3136191756 hasConcept C2778716859 @default.
• W3136191756 hasConcept C2779134260 @default.
• W3136191756 hasConcept C2987404301 @default.
• W3136191756 hasConcept C30036603 @default.
• W3136191756 hasConcept C3008058167 @default.
• W3136191756 hasConcept C42219234 @default.
• W3136191756 hasConcept C524204448 @default.
• W3136191756 hasConcept C71924100 @default.
• W3136191756 hasConceptScore W3136191756C126322002 @default.
• W3136191756 hasConceptScore W3136191756C151956035 @default.
• W3136191756 hasConceptScore W3136191756C177713679 @default.
• W3136191756 hasConceptScore W3136191756C194828623 @default.
• W3136191756 hasConceptScore W3136191756C2777120189 @default.
• W3136191756 hasConceptScore W3136191756C2778716859 @default.
• W3136191756 hasConceptScore W3136191756C2779134260 @default.
• W3136191756 hasConceptScore W3136191756C2987404301 @default.
• W3136191756 hasConceptScore W3136191756C30036603 @default.
• W3136191756 hasConceptScore W3136191756C3008058167 @default.
• W3136191756 hasConceptScore W3136191756C42219234 @default.
• W3136191756 hasConceptScore W3136191756C524204448 @default.
• W3136191756 hasConceptScore W3136191756C71924100 @default.
• W3136191756 hasLocation W31361917561 @default.
• W3136191756 hasOpenAccess W3136191756 @default.
• W3136191756 hasPrimaryLocation W31361917561 @default.
• W3136191756 hasRelatedWork W1982716358 @default.
• W3136191756 hasRelatedWork W2003280522 @default.
• W3136191756 hasRelatedWork W2035899314 @default.
• W3136191756 hasRelatedWork W2152951948 @default.
• W3136191756 hasRelatedWork W2235464154 @default.
• W3136191756 hasRelatedWork W2398621887 @default.
• W3136191756 hasRelatedWork W2570718878 @default.
• W3136191756 hasRelatedWork W2796424707 @default.
• W3136191756 hasRelatedWork W3119281112 @default.
• W3136191756 hasRelatedWork W4206928004 @default.
• W3136191756 isParatext "false" @default.
• W3136191756 isRetracted "false" @default.
• W3136191756 magId "3136191756" @default.
• W3136191756 workType "article" @default.