FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313236824> ?p ?o ?g. }

• W4313236824 endingPage "667" @default.
• W4313236824 startingPage "656" @default.
• W4313236824 abstract "Abstract Objective Extracorporeal membrane oxygenation (ECMO) resource allocation tools are currently lacking. We developed machine learning (ML) models for predicting COVID-19 patients at risk of receiving ECMO to guide patient triage and resource allocation. Material and Methods We included COVID-19 patients admitted to intensive care units for &gt;24 h from March 2020 to October 2021, divided into training and testing development and testing-only holdout cohorts. We developed ECMO deployment timely prediction model ForecastECMO using Gradient Boosting Tree (GBT), with pre-ECMO prediction horizons from 0 to 48 h, compared to PaO2/FiO2 ratio, Sequential Organ Failure Assessment score, PREdiction of Survival on ECMO Therapy score, logistic regression, and 30 pre-selected clinical variables GBT Clinical GBT models, with area under the receiver operator curve (AUROC) and precision recall curve (AUPRC) metrics. Results ECMO prevalence was 2.89% and 1.73% in development and holdout cohorts. ForecastECMO had the best performance in both cohorts. At the 18-h prediction horizon, a potentially clinically actionable pre-ECMO window, ForecastECMO, had the highest AUROC (0.94 and 0.95) and AUPRC (0.54 and 0.37) in development and holdout cohorts in identifying ECMO patients without data 18 h prior to ECMO. Discussion and Conclusions We developed a multi-horizon model, ForecastECMO, with high performance in identifying patients receiving ECMO at various prediction horizons. This model has potential to be used as early alert tool to guide ECMO resource allocation for COVID-19 patients. Future prospective multicenter validation would provide evidence for generalizability and real-world application of such models to improve patient outcomes." @default.
• W4313236824 created "2023-01-06" @default.
• W4313236824 creator A5035244816 @default.
• W4313236824 creator A5037248049 @default.
• W4313236824 creator A5061152007 @default.
• W4313236824 creator A5070305373 @default.
• W4313236824 creator A5071367198 @default.
• W4313236824 creator A5071663340 @default.
• W4313236824 creator A5077569089 @default.
• W4313236824 date "2022-12-28" @default.
• W4313236824 modified "2023-10-02" @default.
• W4313236824 title "Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients" @default.
• W4313236824 cites W1966716734 @default.
• W4313236824 cites W1974873560 @default.
• W4313236824 cites W1996204666 @default.
• W4313236824 cites W2019694480 @default.
• W4313236824 cites W2021046603 @default.
• W4313236824 cites W2048608755 @default.
• W4313236824 cites W2108690333 @default.
• W4313236824 cites W2143749588 @default.
• W4313236824 cites W2771310921 @default.
• W4313236824 cites W2806033195 @default.
• W4313236824 cites W2972443274 @default.
• W4313236824 cites W2998247378 @default.
• W4313236824 cites W3008421357 @default.
• W4313236824 cites W3010095828 @default.
• W4313236824 cites W3012186724 @default.
• W4313236824 cites W3016922353 @default.
• W4313236824 cites W3018341597 @default.
• W4313236824 cites W3022950647 @default.
• W4313236824 cites W3024915375 @default.
• W4313236824 cites W3027014777 @default.
• W4313236824 cites W3035437790 @default.
• W4313236824 cites W3038024550 @default.
• W4313236824 cites W3043285783 @default.
• W4313236824 cites W3045542537 @default.
• W4313236824 cites W3045712297 @default.
• W4313236824 cites W3048608983 @default.
• W4313236824 cites W3049675062 @default.
• W4313236824 cites W3092617928 @default.
• W4313236824 cites W3101272847 @default.
• W4313236824 cites W3108217640 @default.
• W4313236824 cites W3108389911 @default.
• W4313236824 cites W3110548544 @default.
• W4313236824 cites W3113749891 @default.
• W4313236824 cites W3117412766 @default.
• W4313236824 cites W3118362663 @default.
• W4313236824 cites W3118445967 @default.
• W4313236824 cites W3119034938 @default.
• W4313236824 cites W3124163620 @default.
• W4313236824 cites W3124281496 @default.
• W4313236824 cites W3128686564 @default.
• W4313236824 cites W3131850829 @default.
• W4313236824 cites W3133903458 @default.
• W4313236824 cites W3134118717 @default.
• W4313236824 cites W3134499779 @default.
• W4313236824 cites W3134724323 @default.
• W4313236824 cites W3144142918 @default.
• W4313236824 cites W3145060000 @default.
• W4313236824 cites W3150419368 @default.
• W4313236824 cites W3152942920 @default.
• W4313236824 cites W3155073785 @default.
• W4313236824 cites W3156398560 @default.
• W4313236824 cites W3158873712 @default.
• W4313236824 cites W3162993540 @default.
• W4313236824 cites W3165728576 @default.
• W4313236824 cites W3166549569 @default.
• W4313236824 cites W3177092316 @default.
• W4313236824 cites W3178951640 @default.
• W4313236824 cites W3180282780 @default.
• W4313236824 cites W3183309779 @default.
• W4313236824 cites W3183983384 @default.
• W4313236824 cites W3187524430 @default.
• W4313236824 cites W3189499440 @default.
• W4313236824 cites W3195273986 @default.
• W4313236824 cites W3197059639 @default.
• W4313236824 cites W3199601182 @default.
• W4313236824 cites W3201825099 @default.
• W4313236824 cites W3202915227 @default.
• W4313236824 cites W3216352771 @default.
• W4313236824 cites W4210968232 @default.
• W4313236824 cites W4214539199 @default.
• W4313236824 cites W4214814910 @default.
• W4313236824 cites W4214865357 @default.
• W4313236824 cites W4224252268 @default.
• W4313236824 cites W4224434477 @default.
• W4313236824 cites W4225923552 @default.
• W4313236824 cites W4226160291 @default.
• W4313236824 cites W4226553029 @default.
• W4313236824 cites W4280526031 @default.
• W4313236824 cites W4280531141 @default.
• W4313236824 cites W4281401987 @default.
• W4313236824 cites W4283641073 @default.
• W4313236824 cites W4285719527 @default.
• W4313236824 doi "https://doi.org/10.1093/jamia/ocac256" @default.
• W4313236824 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36575995" @default.
• W4313236824 hasPublicationYear "2022" @default.
• W4313236824 type Work @default.

• next