FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4248448265> ?p ?o ?g. }

• W4248448265 abstract "<sec> <title>BACKGROUND</title> Although most current medication error prevention systems are rule-based, these systems may result in alert fatigue because of poor accuracy. Previously, we had developed a machine learning (ML) model based on Taiwan’s local databases (TLD) to address this issue. However, the international transferability of this model is unclear. </sec> <sec> <title>OBJECTIVE</title> This study examines the international transferability of a machine learning model for detecting medication errors and whether the federated learning approach could further improve the accuracy of the model. </sec> <sec> <title>METHODS</title> The study cohort included 667,572 outpatient prescriptions from 2 large US academic medical centers. Our ML model was applied to build the original model (O model), the local model (L model), and the hybrid model (H model). The O model was built using the data of 1.34 billion outpatient prescriptions from TLD. A validation set with 8.98% (60,000/667,572) of the prescriptions was first randomly sampled, and the remaining 91.02% (607,572/667,572) of the prescriptions served as the local training set for the L model. With a federated learning approach, the H model used the association values with a higher frequency of co-occurrence among the O and L models. A testing set with 600 prescriptions was classified as <i>substantiated</i> and <i>unsubstantiated</i> by 2 independent physician reviewers and was then used to assess model performance. </sec> <sec> <title>RESULTS</title> The interrater agreement was significant in terms of classifying prescriptions as <i>substantiated</i> and <i>unsubstantiated</i> (κ=0.91; 95% CI 0.88 to 0.95). With thresholds ranging from 0.5 to 1.5, the alert accuracy ranged from 75%-78% for the O model, 76%-78% for the L model, and 79%-85% for the H model. </sec> <sec> <title>CONCLUSIONS</title> Our ML model has good international transferability among US hospital data. Using the federated learning approach with local hospital data could further improve the accuracy of the model. </sec>" @default.
• W4248448265 created "2022-05-12" @default.
• W4248448265 creator A5008438843 @default.
• W4248448265 creator A5017869910 @default.
• W4248448265 creator A5021013376 @default.
• W4248448265 creator A5028915930 @default.
• W4248448265 creator A5036110536 @default.
• W4248448265 creator A5042749926 @default.
• W4248448265 creator A5045320870 @default.
• W4248448265 creator A5049955839 @default.
• W4248448265 creator A5051372750 @default.
• W4248448265 creator A5051376406 @default.
• W4248448265 creator A5088202717 @default.
• W4248448265 date "2020-08-12" @default.
• W4248448265 modified "2023-09-26" @default.
• W4248448265 title "Assessing the International Transferability of a Machine Learning Model for Detecting Medication Error in the General Internal Medicine Clinic: Multicenter Preliminary Validation Study (Preprint)" @default.
• W4248448265 cites W1967042569 @default.
• W4248448265 cites W1972978214 @default.
• W4248448265 cites W2006849636 @default.
• W4248448265 cites W2022909531 @default.
• W4248448265 cites W2042265219 @default.
• W4248448265 cites W2045345984 @default.
• W4248448265 cites W2101098820 @default.
• W4248448265 cites W2110922423 @default.
• W4248448265 cites W2116836111 @default.
• W4248448265 cites W2121055261 @default.
• W4248448265 cites W2131402221 @default.
• W4248448265 cites W2159101763 @default.
• W4248448265 cites W2161488224 @default.
• W4248448265 cites W2166858912 @default.
• W4248448265 cites W2409124292 @default.
• W4248448265 cites W2493980083 @default.
• W4248448265 cites W2513917195 @default.
• W4248448265 cites W2575766973 @default.
• W4248448265 cites W2577663806 @default.
• W4248448265 cites W2607596737 @default.
• W4248448265 cites W2617544848 @default.
• W4248448265 cites W2748245851 @default.
• W4248448265 cites W2751520945 @default.
• W4248448265 cites W2787225861 @default.
• W4248448265 cites W2789882727 @default.
• W4248448265 cites W2789922031 @default.
• W4248448265 cites W2795594780 @default.
• W4248448265 cites W2799962345 @default.
• W4248448265 cites W2886522935 @default.
• W4248448265 cites W2890473359 @default.
• W4248448265 cites W2899682645 @default.
• W4248448265 cites W2905810301 @default.
• W4248448265 cites W2907200675 @default.
• W4248448265 cites W2915257975 @default.
• W4248448265 cites W2915569858 @default.
• W4248448265 cites W2943491685 @default.
• W4248448265 cites W2946814533 @default.
• W4248448265 cites W2955881972 @default.
• W4248448265 cites W2969444923 @default.
• W4248448265 cites W2973888100 @default.
• W4248448265 cites W2991582385 @default.
• W4248448265 cites W3000003130 @default.
• W4248448265 cites W3010405236 @default.
• W4248448265 cites W3019268698 @default.
• W4248448265 cites W4229956755 @default.
• W4248448265 cites W2098702751 @default.
• W4248448265 doi "https://doi.org/10.2196/preprints.23454" @default.
• W4248448265 hasPublicationYear "2020" @default.
• W4248448265 type Work @default.
• W4248448265 citedByCount "0" @default.
• W4248448265 crossrefType "posted-content" @default.
• W4248448265 hasAuthorship W4248448265A5008438843 @default.
• W4248448265 hasAuthorship W4248448265A5017869910 @default.
• W4248448265 hasAuthorship W4248448265A5021013376 @default.
• W4248448265 hasAuthorship W4248448265A5028915930 @default.
• W4248448265 hasAuthorship W4248448265A5036110536 @default.
• W4248448265 hasAuthorship W4248448265A5042749926 @default.
• W4248448265 hasAuthorship W4248448265A5045320870 @default.
• W4248448265 hasAuthorship W4248448265A5049955839 @default.
• W4248448265 hasAuthorship W4248448265A5051372750 @default.
• W4248448265 hasAuthorship W4248448265A5051376406 @default.
• W4248448265 hasAuthorship W4248448265A5088202717 @default.
• W4248448265 hasBestOaLocation W42484482652 @default.
• W4248448265 hasConcept C119857082 @default.
• W4248448265 hasConcept C140331021 @default.
• W4248448265 hasConcept C154945302 @default.
• W4248448265 hasConcept C159110408 @default.
• W4248448265 hasConcept C177264268 @default.
• W4248448265 hasConcept C199360897 @default.
• W4248448265 hasConcept C2426938 @default.
• W4248448265 hasConcept C41008148 @default.
• W4248448265 hasConcept C512399662 @default.
• W4248448265 hasConcept C61272859 @default.
• W4248448265 hasConcept C71924100 @default.
• W4248448265 hasConceptScore W4248448265C119857082 @default.
• W4248448265 hasConceptScore W4248448265C140331021 @default.
• W4248448265 hasConceptScore W4248448265C154945302 @default.
• W4248448265 hasConceptScore W4248448265C159110408 @default.
• W4248448265 hasConceptScore W4248448265C177264268 @default.
• W4248448265 hasConceptScore W4248448265C199360897 @default.
• W4248448265 hasConceptScore W4248448265C2426938 @default.
• W4248448265 hasConceptScore W4248448265C41008148 @default.
• W4248448265 hasConceptScore W4248448265C512399662 @default.
• W4248448265 hasConceptScore W4248448265C61272859 @default.

• next