FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366389418> ?p ?o ?g. }

• W4366389418 abstract "<sec> <title>BACKGROUND</title> Identification and referral of at-risk patients from primary care practitioners (PCPs) to eye care professionals remains problematic. Approximately 1.9 million Americans suffer from vision loss as a result of undiagnosed or untreated ophthalmic conditions. Artificial intelligence modeling of 1,486,078 patients identifies individuals at higher risk for glaucoma, age-related macular degeneration, diabetic retinopathy, visually significant cataracts, and ocular surface disease. </sec> <sec> <title>OBJECTIVE</title> To build and compare artificial intelligence (AI) strategies, applicable to Electronic Health Records of primary care physicians (PCPs), capable of triaging patients for referral to eyecare specialists. </sec> <sec> <title>METHODS</title> From the Optum® de-identified Electronic Health Record dataset, 743,039 patients with age-related macular degeneration (AMD), visually significant cataract, diabetic retinopathy, glaucoma, or ocular surface disease (OSD) were exact matched on age and gender to 743,039 controls without eye conditions. Between 142-182 non-ophthalmic parameters per patient were inputted into five AI models: Generalized Linear Model (GLM), L1-regularized logistic regression, random forest, XGBoost, and J-48 decision trees. Model performance was compared for each pathology to select the most predictive algorithm. Area under the curve (AUC) was assessed for all algorithms for each outcome. </sec> <sec> <title>RESULTS</title> XGBoost demonstrated the best performance, showing, respectively, prediction accuracy and AUC of 78.6% and 0.878 for visually significant cataract, 77.4% and 0.858 for exudative AMD, 79.2% and 0.879 for non-exudative AMD, 72.2% and 0.803 for OSD requiring medication, 70.8% and 0.785 for glaucoma, 85.0% and 0.924 for type 1 nonproliferative diabetic retinopathy (NPDR), 82.2% and 0.911 for type 1 proliferative diabetic retinopathy (PDR), 81.3% and 0.891 for type 2 NPDR, and 82.1% and 0.900 for type 2 PDR. </sec> <sec> <title>CONCLUSIONS</title> The five AI strategies deployed were able to successfully identify patients with elevated odds ratios (ORs [95% CI]), thus capable of patient triage, for ocular pathology ranging from 2.4 [2.4-2.5] (glaucoma) to 5.7 [5.0-6.4] (type 1 NPDR), with an average OR of 3.9. The application of these models could enable PCPs to better identify and triage patients at risk for ophthalmic pathology. </sec> <sec> <title>CLINICALTRIAL</title> N/A </sec>" @default.
• W4366389418 created "2023-04-21" @default.
• W4366389418 creator A5004287177 @default.
• W4366389418 creator A5011574502 @default.
• W4366389418 creator A5027194846 @default.
• W4366389418 creator A5039287643 @default.
• W4366389418 creator A5066293424 @default.
• W4366389418 creator A5071216452 @default.
• W4366389418 date "2023-04-18" @default.
• W4366389418 modified "2023-09-30" @default.
• W4366389418 title "Artificial intelligence deployed on Electronic Health Record data: Strategies for identification and referral of at-risk patients from primary care physicians to eyecare specialists. (Preprint)" @default.
• W4366389418 cites W1548949849 @default.
• W4366389418 cites W1973499965 @default.
• W4366389418 cites W1983810077 @default.
• W4366389418 cites W2048082482 @default.
• W4366389418 cites W2048332545 @default.
• W4366389418 cites W2059974661 @default.
• W4366389418 cites W2083562884 @default.
• W4366389418 cites W2120711134 @default.
• W4366389418 cites W2140695747 @default.
• W4366389418 cites W2144717989 @default.
• W4366389418 cites W2145669020 @default.
• W4366389418 cites W2147322584 @default.
• W4366389418 cites W2165719451 @default.
• W4366389418 cites W2308032647 @default.
• W4366389418 cites W2402693112 @default.
• W4366389418 cites W2402719683 @default.
• W4366389418 cites W2557738935 @default.
• W4366389418 cites W2560103205 @default.
• W4366389418 cites W2567842442 @default.
• W4366389418 cites W2605704142 @default.
• W4366389418 cites W2617110182 @default.
• W4366389418 cites W2752885356 @default.
• W4366389418 cites W2789604249 @default.
• W4366389418 cites W2804215653 @default.
• W4366389418 cites W2883079384 @default.
• W4366389418 cites W2884753852 @default.
• W4366389418 cites W2944954104 @default.
• W4366389418 cites W2949358505 @default.
• W4366389418 cites W2961780467 @default.
• W4366389418 cites W2971563774 @default.
• W4366389418 cites W2981344511 @default.
• W4366389418 cites W3003821248 @default.
• W4366389418 cites W3011701318 @default.
• W4366389418 cites W3018236424 @default.
• W4366389418 cites W3018911758 @default.
• W4366389418 cites W3040994663 @default.
• W4366389418 cites W3041921482 @default.
• W4366389418 cites W3102476541 @default.
• W4366389418 cites W68862571 @default.
• W4366389418 doi "https://doi.org/10.2196/preprints.48295" @default.
• W4366389418 hasPublicationYear "2023" @default.
• W4366389418 type Work @default.
• W4366389418 citedByCount "0" @default.
• W4366389418 crossrefType "posted-content" @default.
• W4366389418 hasAuthorship W4366389418A5004287177 @default.
• W4366389418 hasAuthorship W4366389418A5011574502 @default.
• W4366389418 hasAuthorship W4366389418A5027194846 @default.
• W4366389418 hasAuthorship W4366389418A5039287643 @default.
• W4366389418 hasAuthorship W4366389418A5066293424 @default.
• W4366389418 hasAuthorship W4366389418A5071216452 @default.
• W4366389418 hasConcept C118487528 @default.
• W4366389418 hasConcept C119767625 @default.
• W4366389418 hasConcept C126322002 @default.
• W4366389418 hasConcept C134018914 @default.
• W4366389418 hasConcept C151956035 @default.
• W4366389418 hasConcept C195910791 @default.
• W4366389418 hasConcept C2776135927 @default.
• W4366389418 hasConcept C2776403814 @default.
• W4366389418 hasConcept C2777155141 @default.
• W4366389418 hasConcept C2778257484 @default.
• W4366389418 hasConcept C2778527774 @default.
• W4366389418 hasConcept C2779134260 @default.
• W4366389418 hasConcept C2779829184 @default.
• W4366389418 hasConcept C2984752397 @default.
• W4366389418 hasConcept C512399662 @default.
• W4366389418 hasConcept C555293320 @default.
• W4366389418 hasConcept C58471807 @default.
• W4366389418 hasConcept C71924100 @default.
• W4366389418 hasConceptScore W4366389418C118487528 @default.
• W4366389418 hasConceptScore W4366389418C119767625 @default.
• W4366389418 hasConceptScore W4366389418C126322002 @default.
• W4366389418 hasConceptScore W4366389418C134018914 @default.
• W4366389418 hasConceptScore W4366389418C151956035 @default.
• W4366389418 hasConceptScore W4366389418C195910791 @default.
• W4366389418 hasConceptScore W4366389418C2776135927 @default.
• W4366389418 hasConceptScore W4366389418C2776403814 @default.
• W4366389418 hasConceptScore W4366389418C2777155141 @default.
• W4366389418 hasConceptScore W4366389418C2778257484 @default.
• W4366389418 hasConceptScore W4366389418C2778527774 @default.
• W4366389418 hasConceptScore W4366389418C2779134260 @default.
• W4366389418 hasConceptScore W4366389418C2779829184 @default.
• W4366389418 hasConceptScore W4366389418C2984752397 @default.
• W4366389418 hasConceptScore W4366389418C512399662 @default.
• W4366389418 hasConceptScore W4366389418C555293320 @default.
• W4366389418 hasConceptScore W4366389418C58471807 @default.
• W4366389418 hasConceptScore W4366389418C71924100 @default.
• W4366389418 hasLocation W43663894181 @default.
• W4366389418 hasOpenAccess W4366389418 @default.
• W4366389418 hasPrimaryLocation W43663894181 @default.

• next