FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307173343> ?p ?o ?g. }

• W4307173343 abstract "<sec> <title>BACKGROUND</title> Trauma-related mortality is a heavy burden. Estimating the mortality risk in trauma patients is crucial to enhance treatment efficiency and reduce the burden. The most popular and accurate model is the injury severity score based on the abbreviated injury scale (AIS), which is an anatomical injury severity scoring system. However, the AIS requires specialists to code the injury scale by reviewing a patient's medical record; therefore, applying the model to every hospital is impossible. </sec> <sec> <title>OBJECTIVE</title> We aimed to develop an artificial intelligence (AI) model to predict in-hospital mortality in trauma patients using the international classification of disease (ICD)-10, triage scale, procedure codes, and other clinical features. </sec> <sec> <title>METHODS</title> We used the Korean National Emergency Department Information System (NEDIS) dataset (n=778,111) from over 400 hospitals from 2016 to 2019. To predict in-hospital mortality, we used ICD-10; patient’s age; gender; intentionality; injury mechanism; emergent symptom; AVPU scale; Korean triage and acuity scale (KTAS); and procedure codes as input features. We proposed the ensemble of deep neural networks (EDNN) via five-fold cross-validation, and compared with other state-of-the-art machine learning models, including traditional prediction models. We further investigated the effect of features. </sec> <sec> <title>RESULTS</title> Our proposed EDNN with all features provided the highest AUROC of 0.9507, which outperformed other state-of-the-art models, including traditional prediction models: AdaBoost (AUROC of 0.9433), XGBoost (AUROC of 0.9331), ICD-based injury severity score (AUROC of 0.8699 an inclusive model and AUROC of 0.8224 an exclusive model), and KTAS (AUROC of 0.1841). In addition, using all features provided higher AUROC than any other partial features: EDNN with the features of ICD-10 only (AUROC of 0.8964) and EDNN with the features excluding ICD-10 (AUROC of 0.9383). </sec> <sec> <title>CONCLUSIONS</title> Our proposed EDNN with all features outperforms other state-of-the-art models, including the traditional diagnostic code-based prediction model and triage scale. </sec>" @default.
• W4307173343 created "2022-10-29" @default.
• W4307173343 creator A5000533334 @default.
• W4307173343 creator A5021585332 @default.
• W4307173343 creator A5032054737 @default.
• W4307173343 creator A5040725804 @default.
• W4307173343 creator A5040897748 @default.
• W4307173343 creator A5042028949 @default.
• W4307173343 creator A5063322911 @default.
• W4307173343 creator A5071806453 @default.
• W4307173343 date "2022-10-23" @default.
• W4307173343 modified "2023-09-28" @default.
• W4307173343 title "Development of artificial intelligence model for predicting in-hospital mortality derived from international classification of diseases, triage scales, procedure codes, and other clinical features in trauma patients: A nationwide population-based study (Preprint)" @default.
• W4307173343 cites W1971733235 @default.
• W4307173343 cites W1980011459 @default.
• W4307173343 cites W1985428966 @default.
• W4307173343 cites W1991195527 @default.
• W4307173343 cites W1994682257 @default.
• W4307173343 cites W2014640268 @default.
• W4307173343 cites W2044000962 @default.
• W4307173343 cites W2069000578 @default.
• W4307173343 cites W2076078073 @default.
• W4307173343 cites W2079623713 @default.
• W4307173343 cites W2093831045 @default.
• W4307173343 cites W2114470813 @default.
• W4307173343 cites W2148143831 @default.
• W4307173343 cites W2767830799 @default.
• W4307173343 cites W2790209545 @default.
• W4307173343 cites W2896538719 @default.
• W4307173343 cites W2909473246 @default.
• W4307173343 cites W2933592092 @default.
• W4307173343 cites W2944772663 @default.
• W4307173343 cites W3049118317 @default.
• W4307173343 cites W3101230421 @default.
• W4307173343 cites W3102476541 @default.
• W4307173343 cites W3136470988 @default.
• W4307173343 cites W3188363006 @default.
• W4307173343 cites W4200369777 @default.
• W4307173343 cites W4205780241 @default.
• W4307173343 cites W4214655560 @default.
• W4307173343 doi "https://doi.org/10.2196/preprints.43757" @default.
• W4307173343 hasPublicationYear "2022" @default.
• W4307173343 type Work @default.
• W4307173343 citedByCount "0" @default.
• W4307173343 crossrefType "posted-content" @default.
• W4307173343 hasAuthorship W4307173343A5000533334 @default.
• W4307173343 hasAuthorship W4307173343A5021585332 @default.
• W4307173343 hasAuthorship W4307173343A5032054737 @default.
• W4307173343 hasAuthorship W4307173343A5040725804 @default.
• W4307173343 hasAuthorship W4307173343A5040897748 @default.
• W4307173343 hasAuthorship W4307173343A5042028949 @default.
• W4307173343 hasAuthorship W4307173343A5063322911 @default.
• W4307173343 hasAuthorship W4307173343A5071806453 @default.
• W4307173343 hasConcept C119857082 @default.
• W4307173343 hasConcept C126322002 @default.
• W4307173343 hasConcept C154945302 @default.
• W4307173343 hasConcept C190385971 @default.
• W4307173343 hasConcept C194828623 @default.
• W4307173343 hasConcept C205649164 @default.
• W4307173343 hasConcept C2776567890 @default.
• W4307173343 hasConcept C2777120189 @default.
• W4307173343 hasConcept C2778755073 @default.
• W4307173343 hasConcept C2908647359 @default.
• W4307173343 hasConcept C3017944768 @default.
• W4307173343 hasConcept C41008148 @default.
• W4307173343 hasConcept C545542383 @default.
• W4307173343 hasConcept C58471807 @default.
• W4307173343 hasConcept C58640448 @default.
• W4307173343 hasConcept C71924100 @default.
• W4307173343 hasConcept C85004164 @default.
• W4307173343 hasConcept C99454951 @default.
• W4307173343 hasConceptScore W4307173343C119857082 @default.
• W4307173343 hasConceptScore W4307173343C126322002 @default.
• W4307173343 hasConceptScore W4307173343C154945302 @default.
• W4307173343 hasConceptScore W4307173343C190385971 @default.
• W4307173343 hasConceptScore W4307173343C194828623 @default.
• W4307173343 hasConceptScore W4307173343C205649164 @default.
• W4307173343 hasConceptScore W4307173343C2776567890 @default.
• W4307173343 hasConceptScore W4307173343C2777120189 @default.
• W4307173343 hasConceptScore W4307173343C2778755073 @default.
• W4307173343 hasConceptScore W4307173343C2908647359 @default.
• W4307173343 hasConceptScore W4307173343C3017944768 @default.
• W4307173343 hasConceptScore W4307173343C41008148 @default.
• W4307173343 hasConceptScore W4307173343C545542383 @default.
• W4307173343 hasConceptScore W4307173343C58471807 @default.
• W4307173343 hasConceptScore W4307173343C58640448 @default.
• W4307173343 hasConceptScore W4307173343C71924100 @default.
• W4307173343 hasConceptScore W4307173343C85004164 @default.
• W4307173343 hasConceptScore W4307173343C99454951 @default.
• W4307173343 hasLocation W43071733431 @default.
• W4307173343 hasOpenAccess W4307173343 @default.
• W4307173343 hasPrimaryLocation W43071733431 @default.
• W4307173343 hasRelatedWork W1981432161 @default.
• W4307173343 hasRelatedWork W2033609379 @default.
• W4307173343 hasRelatedWork W2042782666 @default.
• W4307173343 hasRelatedWork W2061049130 @default.
• W4307173343 hasRelatedWork W2105210204 @default.
• W4307173343 hasRelatedWork W2329834253 @default.
• W4307173343 hasRelatedWork W2528087880 @default.
• W4307173343 hasRelatedWork W2989721927 @default.

• next