FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890520766> ?p ?o ?g. }

• W2890520766 endingPage "S6" @default.
• W2890520766 startingPage "S5" @default.
• W2890520766 abstract "Patients who leave without being seen (LWBS) remain a persistent challenge for emergency departments (ED). It results not only in sub-optimal patient care and medicolegal risk but LWBS is also publicly reported and has revenue implications both in terms of lost encounters and as a CMS quality measure (OP-22). Patients who leave without being seen (LWBS) are a persistent problem in the emergency department. Patients who leave the emergency department without being seen by a health care provider contribute to delays and ED cost but neither benefit from health care nor provide reimbursement for the encounter. Many different strategies have been proposed to reduce LWBS including having greeters meet patient on ED arrival, physician triage/rounding in the waiting room, presenting patients with estimates of waiting time, and providing reassurances to patients as they wait. One of the greatest challenges is identifying the particular patients at highest risk for LWBS. We retrospectively analyzed a cohort of patients seen in a large urban academic medical center emergency department. We used electronic health record (EHR) data that would be available at the time of patient triage in the ED including chief complaint, vital signs, prior diagnoses and comorbidities, medications, prior labs, and history/pattern of previous health care utilization. Additional features included demographics, time of day, and date. We utilized gradient boosting (xgBoost), an ensemble machine learning approach, in which a large number of weak learners are iteratively combined together into a single strong learner. 10x cross validation was used for testing. A dashboard for EHR integration was developed to facilitate display of real-time predictions at time of ED presentation. The machine learning models were trained on 3 years of data from 1/1/2015 to 1/10/2018 spanning 217,150 encounters for 113,400 patients. The overall LWBS rate was 4.42%. After 7 iterations of development, the xgBoost model achieved an AUC of 0.92 (Figure A) with good calibration (Figure B) an 79% accuracy, 89% sensitivity, and 79% specificity. The most important features (Figure C) included time of day, acuity, insurance type/status, chief complaint, utilization history, and medications. This represents the best model published to date to predict patient level risk of LWBS. We demonstrate the feasibility of using machine learning to accurately identify patients at risk for LWBS using only data available at time of triage. We also described a method for surfacing that information into the ED work stream. Prospective validation will be necessary to determine how effectively this prediction can be combined with intervention strategies to reduce LWBS and improve patient experience." @default.
• W2890520766 created "2018-09-27" @default.
• W2890520766 creator A5008266977 @default.
• W2890520766 creator A5012505929 @default.
• W2890520766 creator A5021241037 @default.
• W2890520766 creator A5026969327 @default.
• W2890520766 creator A5031994087 @default.
• W2890520766 creator A5051196831 @default.
• W2890520766 creator A5073722314 @default.
• W2890520766 date "2018-10-01" @default.
• W2890520766 modified "2023-09-27" @default.
• W2890520766 title "12 Predicting Patients at Risk for Leaving Without Being Seen Using Machine Learning" @default.
• W2890520766 doi "https://doi.org/10.1016/j.annemergmed.2018.08.017" @default.
• W2890520766 hasPublicationYear "2018" @default.
• W2890520766 type Work @default.
• W2890520766 sameAs 2890520766 @default.
• W2890520766 citedByCount "2" @default.
• W2890520766 countsByYear W28905207662020 @default.
• W2890520766 countsByYear W28905207662023 @default.
• W2890520766 crossrefType "journal-article" @default.
• W2890520766 hasAuthorship W2890520766A5008266977 @default.
• W2890520766 hasAuthorship W2890520766A5012505929 @default.
• W2890520766 hasAuthorship W2890520766A5021241037 @default.
• W2890520766 hasAuthorship W2890520766A5026969327 @default.
• W2890520766 hasAuthorship W2890520766A5031994087 @default.
• W2890520766 hasAuthorship W2890520766A5051196831 @default.
• W2890520766 hasAuthorship W2890520766A5073722314 @default.
• W2890520766 hasConcept C126322002 @default.
• W2890520766 hasConcept C141071460 @default.
• W2890520766 hasConcept C142724271 @default.
• W2890520766 hasConcept C159110408 @default.
• W2890520766 hasConcept C160735492 @default.
• W2890520766 hasConcept C162324750 @default.
• W2890520766 hasConcept C194828623 @default.
• W2890520766 hasConcept C195910791 @default.
• W2890520766 hasConcept C2777120189 @default.
• W2890520766 hasConcept C2778872837 @default.
• W2890520766 hasConcept C2779703844 @default.
• W2890520766 hasConcept C2780724011 @default.
• W2890520766 hasConcept C50522688 @default.
• W2890520766 hasConcept C534262118 @default.
• W2890520766 hasConcept C545542383 @default.
• W2890520766 hasConcept C71924100 @default.
• W2890520766 hasConcept C72563966 @default.
• W2890520766 hasConceptScore W2890520766C126322002 @default.
• W2890520766 hasConceptScore W2890520766C141071460 @default.
• W2890520766 hasConceptScore W2890520766C142724271 @default.
• W2890520766 hasConceptScore W2890520766C159110408 @default.
• W2890520766 hasConceptScore W2890520766C160735492 @default.
• W2890520766 hasConceptScore W2890520766C162324750 @default.
• W2890520766 hasConceptScore W2890520766C194828623 @default.
• W2890520766 hasConceptScore W2890520766C195910791 @default.
• W2890520766 hasConceptScore W2890520766C2777120189 @default.
• W2890520766 hasConceptScore W2890520766C2778872837 @default.
• W2890520766 hasConceptScore W2890520766C2779703844 @default.
• W2890520766 hasConceptScore W2890520766C2780724011 @default.
• W2890520766 hasConceptScore W2890520766C50522688 @default.
• W2890520766 hasConceptScore W2890520766C534262118 @default.
• W2890520766 hasConceptScore W2890520766C545542383 @default.
• W2890520766 hasConceptScore W2890520766C71924100 @default.
• W2890520766 hasConceptScore W2890520766C72563966 @default.
• W2890520766 hasIssue "4" @default.
• W2890520766 hasLocation W28905207661 @default.
• W2890520766 hasOpenAccess W2890520766 @default.
• W2890520766 hasPrimaryLocation W28905207661 @default.
• W2890520766 hasRelatedWork W1983575798 @default.
• W2890520766 hasRelatedWork W2012255001 @default.
• W2890520766 hasRelatedWork W2387797353 @default.
• W2890520766 hasRelatedWork W2904814977 @default.
• W2890520766 hasRelatedWork W3003580243 @default.
• W2890520766 hasRelatedWork W3022998877 @default.
• W2890520766 hasRelatedWork W4283720121 @default.
• W2890520766 hasRelatedWork W4300064785 @default.
• W2890520766 hasRelatedWork W45337665 @default.
• W2890520766 hasRelatedWork W3108001224 @default.
• W2890520766 hasVolume "72" @default.
• W2890520766 isParatext "false" @default.
• W2890520766 isRetracted "false" @default.
• W2890520766 magId "2890520766" @default.
• W2890520766 workType "article" @default.