Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383224587> ?p ?o ?g. }
- W4383224587 abstract "Predicting clinical deterioration in COVID-19 patients remains a challenging task in the Emergency Department (ED). To address this aim, we developed an artificial neural network using textual (e.g. patient history) and tabular (e.g. laboratory values) data from ED electronic medical reports. The predicted outcomes were 30-day mortality and ICU admission. We included consecutive patients from Humanitas Research Hospital and San Raffaele Hospital in the Milan area between February 20 and May 5, 2020. We included 1296 COVID-19 patients. Textual predictors consisted of patient history, physical exam, and radiological reports. Tabular predictors included age, creatinine, C-reactive protein, hemoglobin, and platelet count. TensorFlow tabular-textual model performance indices were compared to those of models implementing only tabular data. For 30-day mortality, the combined model yielded slightly better performances than the tabular fastai and XGBoost models, with AUC 0.87 ± 0.02, F1 score 0.62 ± 0.10 and an MCC 0.52 ± 0.04 (p < 0.32). As for ICU admission, the combined model MCC was superior (p < 0.024) to the tabular models. Our results suggest that a combined textual and tabular model can effectively predict COVID-19 prognosis which may assist ED physicians in their decision-making process." @default.
- W4383224587 created "2023-07-06" @default.
- W4383224587 creator A5001334583 @default.
- W4383224587 creator A5006984986 @default.
- W4383224587 creator A5018998411 @default.
- W4383224587 creator A5020920439 @default.
- W4383224587 creator A5021783902 @default.
- W4383224587 creator A5023180439 @default.
- W4383224587 creator A5028820202 @default.
- W4383224587 creator A5046032818 @default.
- W4383224587 creator A5047773736 @default.
- W4383224587 creator A5051944867 @default.
- W4383224587 creator A5064186692 @default.
- W4383224587 creator A5071432733 @default.
- W4383224587 creator A5073291164 @default.
- W4383224587 creator A5078072572 @default.
- W4383224587 creator A5079055724 @default.
- W4383224587 date "2023-07-05" @default.
- W4383224587 modified "2023-10-17" @default.
- W4383224587 title "Multimodal deep learning for COVID-19 prognosis prediction in the emergency department: a bi-centric study" @default.
- W4383224587 cites W2169818249 @default.
- W4383224587 cites W2568515780 @default.
- W4383224587 cites W2605650096 @default.
- W4383224587 cites W2957684845 @default.
- W4383224587 cites W2963026768 @default.
- W4383224587 cites W2979825899 @default.
- W4383224587 cites W2999309192 @default.
- W4383224587 cites W3006436762 @default.
- W4383224587 cites W3011508296 @default.
- W4383224587 cites W3011610993 @default.
- W4383224587 cites W3014524604 @default.
- W4383224587 cites W3041319886 @default.
- W4383224587 cites W3044165763 @default.
- W4383224587 cites W3046656138 @default.
- W4383224587 cites W3046681822 @default.
- W4383224587 cites W3084565377 @default.
- W4383224587 cites W3088020307 @default.
- W4383224587 cites W3089983516 @default.
- W4383224587 cites W3092208592 @default.
- W4383224587 cites W3092284106 @default.
- W4383224587 cites W3092436046 @default.
- W4383224587 cites W3093928028 @default.
- W4383224587 cites W3094321215 @default.
- W4383224587 cites W3097189258 @default.
- W4383224587 cites W3097794852 @default.
- W4383224587 cites W3100798628 @default.
- W4383224587 cites W3119630042 @default.
- W4383224587 cites W3119947644 @default.
- W4383224587 cites W3120017613 @default.
- W4383224587 cites W3144611861 @default.
- W4383224587 cites W3160767347 @default.
- W4383224587 cites W3161713811 @default.
- W4383224587 cites W3161987470 @default.
- W4383224587 cites W3162199380 @default.
- W4383224587 cites W3162810948 @default.
- W4383224587 cites W3165656738 @default.
- W4383224587 cites W3175922516 @default.
- W4383224587 cites W3185455591 @default.
- W4383224587 cites W3203592520 @default.
- W4383224587 cites W3207128852 @default.
- W4383224587 cites W3214403769 @default.
- W4383224587 cites W4200144489 @default.
- W4383224587 cites W4205805845 @default.
- W4383224587 cites W4213279110 @default.
- W4383224587 cites W4220703970 @default.
- W4383224587 cites W4224233036 @default.
- W4383224587 cites W4224438814 @default.
- W4383224587 cites W4225493996 @default.
- W4383224587 cites W4281713208 @default.
- W4383224587 doi "https://doi.org/10.1038/s41598-023-37512-3" @default.
- W4383224587 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37407595" @default.
- W4383224587 hasPublicationYear "2023" @default.
- W4383224587 type Work @default.
- W4383224587 citedByCount "1" @default.
- W4383224587 crossrefType "journal-article" @default.
- W4383224587 hasAuthorship W4383224587A5001334583 @default.
- W4383224587 hasAuthorship W4383224587A5006984986 @default.
- W4383224587 hasAuthorship W4383224587A5018998411 @default.
- W4383224587 hasAuthorship W4383224587A5020920439 @default.
- W4383224587 hasAuthorship W4383224587A5021783902 @default.
- W4383224587 hasAuthorship W4383224587A5023180439 @default.
- W4383224587 hasAuthorship W4383224587A5028820202 @default.
- W4383224587 hasAuthorship W4383224587A5046032818 @default.
- W4383224587 hasAuthorship W4383224587A5047773736 @default.
- W4383224587 hasAuthorship W4383224587A5051944867 @default.
- W4383224587 hasAuthorship W4383224587A5064186692 @default.
- W4383224587 hasAuthorship W4383224587A5071432733 @default.
- W4383224587 hasAuthorship W4383224587A5073291164 @default.
- W4383224587 hasAuthorship W4383224587A5078072572 @default.
- W4383224587 hasAuthorship W4383224587A5079055724 @default.
- W4383224587 hasBestOaLocation W43832245871 @default.
- W4383224587 hasConcept C118552586 @default.
- W4383224587 hasConcept C119857082 @default.
- W4383224587 hasConcept C126322002 @default.
- W4383224587 hasConcept C154945302 @default.
- W4383224587 hasConcept C194828623 @default.
- W4383224587 hasConcept C195910791 @default.
- W4383224587 hasConcept C206179267 @default.
- W4383224587 hasConcept C2777120189 @default.
- W4383224587 hasConcept C2779134260 @default.