Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148416954> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3148416954 endingPage "49" @default.
- W3148416954 startingPage "49" @default.
- W3148416954 abstract "ABSTRACT IMPACT: A machine learning approach using electronic health records can combine descriptive, population-level factors of pressure injury outcomes. OBJECTIVES/GOALS: Pressure injuries cause 60,000 deaths and cost $26 billion annually in the US, but prevention is laborious. We used clinical data to develop a machine learning algorithm for predicting pressure injury risk and prescribe the timing of intervention to help clinicians balance competing priorities. METHODS/STUDY POPULATION: We obtained 94,745 electronic health records with 7,000 predictors to calibrate a predictive algorithm of pressure injury risk. Machine learning was used to mine features predicting changes in pressure injury risk; random forests outperformed neural networks, boosting and bagging in feature selection. These features were fit to multilevel ordered logistic regression to create an algorithm that generated empirical Bayes estimates informing a decision-rule for follow-up based on individual risk trajectories over time. We used cross-validation to verify predictive validity, and constrained optimization to select a best-fit algorithm that reduced the time required to trigger patient follow-up. RESULTS/ANTICIPATED RESULTS: The algorithm significantly improved prediction of pressure injury risk (p<0.001) with an area under the ROC curve of 0.60 compared to the Braden Scale, a traditional clinician instrument of pressure injury risk. At a specificity of 0.50, the model achieved a sensitivity of 0.63 within 2.5 patient-days. Machine learning identified categorical increases in risk when patients were prescribed vasopressors (OR=16.4, p<0.001), beta-blockers (OR=4.8, p<0.001), erythropoietin stimulating agents (OR=3.0, p<0.001), or were ordered a urinalysis screen (OR=9.1, p<0.001), lipid panel (OR=5.7, p<0.001) or pre-albumin panel (OR=2.0, p<0.001). DISCUSSION/SIGNIFICANCE OF FINDINGS: This algorithm could help hospitals conserve resources within a critical period of patient vulnerability for pressure injury not reimbursed by Medicare. Savings generated by this approach could justify investment in machine learning to develop electronic warning systems for many iatrogenic injuries." @default.
- W3148416954 created "2021-04-13" @default.
- W3148416954 creator A5034035627 @default.
- W3148416954 creator A5082725876 @default.
- W3148416954 creator A5084745426 @default.
- W3148416954 date "2021-03-01" @default.
- W3148416954 modified "2023-09-27" @default.
- W3148416954 title "41250 Machine Learning to Identify Predictors of Iatrogenic Injury Using Empirical Bayes Estimates: A Cohort Study of Pressure Injury Prevention" @default.
- W3148416954 doi "https://doi.org/10.1017/cts.2021.530" @default.
- W3148416954 hasPublicationYear "2021" @default.
- W3148416954 type Work @default.
- W3148416954 sameAs 3148416954 @default.
- W3148416954 citedByCount "0" @default.
- W3148416954 crossrefType "journal-article" @default.
- W3148416954 hasAuthorship W3148416954A5034035627 @default.
- W3148416954 hasAuthorship W3148416954A5082725876 @default.
- W3148416954 hasAuthorship W3148416954A5084745426 @default.
- W3148416954 hasBestOaLocation W31484169541 @default.
- W3148416954 hasConcept C107327155 @default.
- W3148416954 hasConcept C107673813 @default.
- W3148416954 hasConcept C119857082 @default.
- W3148416954 hasConcept C12174686 @default.
- W3148416954 hasConcept C12267149 @default.
- W3148416954 hasConcept C148483581 @default.
- W3148416954 hasConcept C151956035 @default.
- W3148416954 hasConcept C154945302 @default.
- W3148416954 hasConcept C169258074 @default.
- W3148416954 hasConcept C194828623 @default.
- W3148416954 hasConcept C207201462 @default.
- W3148416954 hasConcept C2908647359 @default.
- W3148416954 hasConcept C38652104 @default.
- W3148416954 hasConcept C41008148 @default.
- W3148416954 hasConcept C52001869 @default.
- W3148416954 hasConcept C5274069 @default.
- W3148416954 hasConcept C58471807 @default.
- W3148416954 hasConcept C63527458 @default.
- W3148416954 hasConcept C71924100 @default.
- W3148416954 hasConcept C99454951 @default.
- W3148416954 hasConceptScore W3148416954C107327155 @default.
- W3148416954 hasConceptScore W3148416954C107673813 @default.
- W3148416954 hasConceptScore W3148416954C119857082 @default.
- W3148416954 hasConceptScore W3148416954C12174686 @default.
- W3148416954 hasConceptScore W3148416954C12267149 @default.
- W3148416954 hasConceptScore W3148416954C148483581 @default.
- W3148416954 hasConceptScore W3148416954C151956035 @default.
- W3148416954 hasConceptScore W3148416954C154945302 @default.
- W3148416954 hasConceptScore W3148416954C169258074 @default.
- W3148416954 hasConceptScore W3148416954C194828623 @default.
- W3148416954 hasConceptScore W3148416954C207201462 @default.
- W3148416954 hasConceptScore W3148416954C2908647359 @default.
- W3148416954 hasConceptScore W3148416954C38652104 @default.
- W3148416954 hasConceptScore W3148416954C41008148 @default.
- W3148416954 hasConceptScore W3148416954C52001869 @default.
- W3148416954 hasConceptScore W3148416954C5274069 @default.
- W3148416954 hasConceptScore W3148416954C58471807 @default.
- W3148416954 hasConceptScore W3148416954C63527458 @default.
- W3148416954 hasConceptScore W3148416954C71924100 @default.
- W3148416954 hasConceptScore W3148416954C99454951 @default.
- W3148416954 hasIssue "s1" @default.
- W3148416954 hasLocation W31484169541 @default.
- W3148416954 hasLocation W31484169542 @default.
- W3148416954 hasOpenAccess W3148416954 @default.
- W3148416954 hasPrimaryLocation W31484169541 @default.
- W3148416954 hasRelatedWork W3045445851 @default.
- W3148416954 hasRelatedWork W3146612261 @default.
- W3148416954 hasRelatedWork W3174196512 @default.
- W3148416954 hasRelatedWork W3210877509 @default.
- W3148416954 hasRelatedWork W4205415703 @default.
- W3148416954 hasRelatedWork W4212852473 @default.
- W3148416954 hasRelatedWork W4225312515 @default.
- W3148416954 hasRelatedWork W4225984265 @default.
- W3148416954 hasRelatedWork W4226324856 @default.
- W3148416954 hasRelatedWork W4293525103 @default.
- W3148416954 hasVolume "5" @default.
- W3148416954 isParatext "false" @default.
- W3148416954 isRetracted "false" @default.
- W3148416954 magId "3148416954" @default.
- W3148416954 workType "article" @default.