Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205274018> ?p ?o ?g. }
- W4205274018 abstract "<sec> <title>BACKGROUND</title> Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease. </sec> <sec> <title>OBJECTIVE</title> Our objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department. </sec> <sec> <title>METHODS</title> Data were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics. </sec> <sec> <title>RESULTS</title> The XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics. </sec> <sec> <title>CONCLUSIONS</title> The XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19. </sec>" @default.
- W4205274018 created "2022-01-25" @default.
- W4205274018 creator A5008416216 @default.
- W4205274018 creator A5035326955 @default.
- W4205274018 creator A5041158101 @default.
- W4205274018 creator A5068193554 @default.
- W4205274018 creator A5068492860 @default.
- W4205274018 creator A5084966628 @default.
- W4205274018 creator A5090798506 @default.
- W4205274018 creator A9999999999 @default.
- W4205274018 date "2020-09-10" @default.
- W4205274018 modified "2023-09-23" @default.
- W4205274018 title "A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation (Preprint)" @default.
- W4205274018 cites W1987300508 @default.
- W4205274018 cites W2006861926 @default.
- W4205274018 cites W2060449205 @default.
- W4205274018 cites W2064711903 @default.
- W4205274018 cites W2082257894 @default.
- W4205274018 cites W2096863518 @default.
- W4205274018 cites W2108712612 @default.
- W4205274018 cites W2111547563 @default.
- W4205274018 cites W2167139263 @default.
- W4205274018 cites W2169167455 @default.
- W4205274018 cites W2244501064 @default.
- W4205274018 cites W2323525554 @default.
- W4205274018 cites W2415049751 @default.
- W4205274018 cites W2553927900 @default.
- W4205274018 cites W2607075056 @default.
- W4205274018 cites W2612337648 @default.
- W4205274018 cites W2775049615 @default.
- W4205274018 cites W2776492990 @default.
- W4205274018 cites W2782697061 @default.
- W4205274018 cites W2899364832 @default.
- W4205274018 cites W2965372631 @default.
- W4205274018 cites W2979156210 @default.
- W4205274018 cites W2979728569 @default.
- W4205274018 cites W3009314935 @default.
- W4205274018 cites W3009859788 @default.
- W4205274018 cites W3014442018 @default.
- W4205274018 cites W3016019925 @default.
- W4205274018 cites W3016535995 @default.
- W4205274018 cites W3016785135 @default.
- W4205274018 cites W3017241122 @default.
- W4205274018 cites W3018811022 @default.
- W4205274018 cites W3021203631 @default.
- W4205274018 cites W3023380234 @default.
- W4205274018 cites W3023618360 @default.
- W4205274018 cites W3024853795 @default.
- W4205274018 cites W3034575642 @default.
- W4205274018 cites W3042081405 @default.
- W4205274018 cites W3102476541 @default.
- W4205274018 cites W4250808193 @default.
- W4205274018 cites W4254526633 @default.
- W4205274018 cites W4255143444 @default.
- W4205274018 cites W4255371699 @default.
- W4205274018 doi "https://doi.org/10.2196/preprints.24246" @default.
- W4205274018 hasPublicationYear "2020" @default.
- W4205274018 type Work @default.
- W4205274018 citedByCount "0" @default.
- W4205274018 crossrefType "posted-content" @default.
- W4205274018 hasAuthorship W4205274018A5008416216 @default.
- W4205274018 hasAuthorship W4205274018A5035326955 @default.
- W4205274018 hasAuthorship W4205274018A5041158101 @default.
- W4205274018 hasAuthorship W4205274018A5068193554 @default.
- W4205274018 hasAuthorship W4205274018A5068492860 @default.
- W4205274018 hasAuthorship W4205274018A5084966628 @default.
- W4205274018 hasAuthorship W4205274018A5090798506 @default.
- W4205274018 hasAuthorship W4205274018A9999999999 @default.
- W4205274018 hasBestOaLocation W42052740182 @default.
- W4205274018 hasConcept C118552586 @default.
- W4205274018 hasConcept C119857082 @default.
- W4205274018 hasConcept C126322002 @default.
- W4205274018 hasConcept C151956035 @default.
- W4205274018 hasConcept C154945302 @default.
- W4205274018 hasConcept C194828623 @default.
- W4205274018 hasConcept C2777080012 @default.
- W4205274018 hasConcept C2777120189 @default.
- W4205274018 hasConcept C2777671062 @default.
- W4205274018 hasConcept C2779134260 @default.
- W4205274018 hasConcept C2780724011 @default.
- W4205274018 hasConcept C29825287 @default.
- W4205274018 hasConcept C3008058167 @default.
- W4205274018 hasConcept C41008148 @default.
- W4205274018 hasConcept C45804977 @default.
- W4205274018 hasConcept C524204448 @default.
- W4205274018 hasConcept C58471807 @default.
- W4205274018 hasConcept C71924100 @default.
- W4205274018 hasConcept C76155785 @default.
- W4205274018 hasConceptScore W4205274018C118552586 @default.
- W4205274018 hasConceptScore W4205274018C119857082 @default.
- W4205274018 hasConceptScore W4205274018C126322002 @default.
- W4205274018 hasConceptScore W4205274018C151956035 @default.
- W4205274018 hasConceptScore W4205274018C154945302 @default.
- W4205274018 hasConceptScore W4205274018C194828623 @default.
- W4205274018 hasConceptScore W4205274018C2777080012 @default.
- W4205274018 hasConceptScore W4205274018C2777120189 @default.
- W4205274018 hasConceptScore W4205274018C2777671062 @default.
- W4205274018 hasConceptScore W4205274018C2779134260 @default.
- W4205274018 hasConceptScore W4205274018C2780724011 @default.
- W4205274018 hasConceptScore W4205274018C29825287 @default.