FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385989160> ?p ?o ?g. }

• W4385989160 endingPage "100385" @default.
• W4385989160 startingPage "100385" @default.
• W4385989160 abstract "PurposeTo develop machine learning (ML) models to predict, at baseline, treatment outcomes at month 9 in patients with neovascular age-related macular degeneration (nAMD) receiving faricimab.DesignRetrospective proof-of-concept study.SubjectsPatients enrolled in the phase 2 AVENUE trial (NCT02484690) of faricimab in nAMD.MethodsBaseline characteristics and spectral domain optical coherence tomography (SD-OCT) image data from 185 faricimab-treated eyes were split into 80% training and 20% test sets at the patient level. Input variables were baseline age, sex, best-corrected visual acuity (BCVA), central subfield thickness (CST), low luminance deficit, treatment arm, and SD-OCT images. A regression problem (BCVA) and a binary classification problem (reduction of CST by 35%)were considered. Overall, 10 models were developed and tested for each problem. Benchmark classical ML models (linear, random forest [RF], extreme gradient boosting [XGBoost]) were trained on baseline characteristics; benchmark deep neural networks (DNNs) were trained on baseline SD-OCT B-scans. Baseline characteristics and SD-OCT data were merged using 2 approaches: model stacking (using DNN prediction as an input feature for classical ML models) and model averaging (which averaged predictions from the DNN using SD-OCT volume and from classical ML models using baseline characteristics).Main Outcome MeasuresTreatment outcomes were defined by 2 target variables: functional (BCVA letter score) and anatomical (percent decrease in CST from baseline) outcomes at month 9.ResultsThe best-performing BCVA regression model with respect to the test coefficient of determination (R2) was the linear model in the model-stacking approach with R2 of 0.31. The best-performing CST classification model with respect to test area under receiver operating characteristics (AUROC) was the benchmark linear model with AUROC of 0.87. A post-hoc analysis showed the baseline BCVA and the baseline CST had the most effect in the all-model prediction for BCVA regression and CST classification, respectively.ConclusionsPromising signals for predicting treatment outcomes from baseline characteristics were detected; however, the predictive benefit of baseline images was unclear in this proof-of-concept study. Further testing and validation with larger, independent data sets is required to fully explore the predictive capacity of ML models using baseline imaging data. To develop machine learning (ML) models to predict, at baseline, treatment outcomes at month 9 in patients with neovascular age-related macular degeneration (nAMD) receiving faricimab. Retrospective proof-of-concept study. Patients enrolled in the phase 2 AVENUE trial (NCT02484690) of faricimab in nAMD. Baseline characteristics and spectral domain optical coherence tomography (SD-OCT) image data from 185 faricimab-treated eyes were split into 80% training and 20% test sets at the patient level. Input variables were baseline age, sex, best-corrected visual acuity (BCVA), central subfield thickness (CST), low luminance deficit, treatment arm, and SD-OCT images. A regression problem (BCVA) and a binary classification problem (reduction of CST by 35%)were considered. Overall, 10 models were developed and tested for each problem. Benchmark classical ML models (linear, random forest [RF], extreme gradient boosting [XGBoost]) were trained on baseline characteristics; benchmark deep neural networks (DNNs) were trained on baseline SD-OCT B-scans. Baseline characteristics and SD-OCT data were merged using 2 approaches: model stacking (using DNN prediction as an input feature for classical ML models) and model averaging (which averaged predictions from the DNN using SD-OCT volume and from classical ML models using baseline characteristics). Treatment outcomes were defined by 2 target variables: functional (BCVA letter score) and anatomical (percent decrease in CST from baseline) outcomes at month 9. The best-performing BCVA regression model with respect to the test coefficient of determination (R2) was the linear model in the model-stacking approach with R2 of 0.31. The best-performing CST classification model with respect to test area under receiver operating characteristics (AUROC) was the benchmark linear model with AUROC of 0.87. A post-hoc analysis showed the baseline BCVA and the baseline CST had the most effect in the all-model prediction for BCVA regression and CST classification, respectively. Promising signals for predicting treatment outcomes from baseline characteristics were detected; however, the predictive benefit of baseline images was unclear in this proof-of-concept study. Further testing and validation with larger, independent data sets is required to fully explore the predictive capacity of ML models using baseline imaging data." @default.
• W4385989160 created "2023-08-19" @default.
• W4385989160 creator A5028983146 @default.
• W4385989160 creator A5030619198 @default.
• W4385989160 creator A5044217019 @default.
• W4385989160 creator A5047542789 @default.
• W4385989160 creator A5051983200 @default.
• W4385989160 creator A5059541679 @default.
• W4385989160 creator A5087351938 @default.
• W4385989160 date "2024-03-01" @default.
• W4385989160 modified "2023-10-18" @default.
• W4385989160 title "Machine Learning to Predict Faricimab Treatment Outcome in Neovascular Age-Related Macular Degeneration" @default.
• W4385989160 cites W2107688758 @default.
• W4385989160 cites W2134161293 @default.
• W4385989160 cites W2175768232 @default.
• W4385989160 cites W2531065411 @default.
• W4385989160 cites W2618325173 @default.
• W4385989160 cites W2761604622 @default.
• W4385989160 cites W28412257 @default.
• W4385989160 cites W2976112560 @default.
• W4385989160 cites W2988969159 @default.
• W4385989160 cites W2990343807 @default.
• W4385989160 cites W3035426851 @default.
• W4385989160 cites W3046457241 @default.
• W4385989160 cites W3046726202 @default.
• W4385989160 cites W3084069549 @default.
• W4385989160 cites W3157651190 @default.
• W4385989160 cites W3180759626 @default.
• W4385989160 cites W3190709038 @default.
• W4385989160 cites W3215971225 @default.
• W4385989160 cites W4221012768 @default.
• W4385989160 doi "https://doi.org/10.1016/j.xops.2023.100385" @default.
• W4385989160 hasPublicationYear "2024" @default.
• W4385989160 type Work @default.
• W4385989160 citedByCount "0" @default.
• W4385989160 crossrefType "journal-article" @default.
• W4385989160 hasAuthorship W4385989160A5028983146 @default.
• W4385989160 hasAuthorship W4385989160A5030619198 @default.
• W4385989160 hasAuthorship W4385989160A5044217019 @default.
• W4385989160 hasAuthorship W4385989160A5047542789 @default.
• W4385989160 hasAuthorship W4385989160A5051983200 @default.
• W4385989160 hasAuthorship W4385989160A5059541679 @default.
• W4385989160 hasAuthorship W4385989160A5087351938 @default.
• W4385989160 hasBestOaLocation W43859891601 @default.
• W4385989160 hasConcept C118487528 @default.
• W4385989160 hasConcept C119857082 @default.
• W4385989160 hasConcept C154945302 @default.
• W4385989160 hasConcept C169258074 @default.
• W4385989160 hasConcept C2776403814 @default.
• W4385989160 hasConcept C2778818243 @default.
• W4385989160 hasConcept C41008148 @default.
• W4385989160 hasConcept C48921125 @default.
• W4385989160 hasConcept C70153297 @default.
• W4385989160 hasConcept C71924100 @default.
• W4385989160 hasConceptScore W4385989160C118487528 @default.
• W4385989160 hasConceptScore W4385989160C119857082 @default.
• W4385989160 hasConceptScore W4385989160C154945302 @default.
• W4385989160 hasConceptScore W4385989160C169258074 @default.
• W4385989160 hasConceptScore W4385989160C2776403814 @default.
• W4385989160 hasConceptScore W4385989160C2778818243 @default.
• W4385989160 hasConceptScore W4385989160C41008148 @default.
• W4385989160 hasConceptScore W4385989160C48921125 @default.
• W4385989160 hasConceptScore W4385989160C70153297 @default.
• W4385989160 hasConceptScore W4385989160C71924100 @default.
• W4385989160 hasIssue "2" @default.
• W4385989160 hasLocation W43859891601 @default.
• W4385989160 hasOpenAccess W4385989160 @default.
• W4385989160 hasPrimaryLocation W43859891601 @default.
• W4385989160 hasRelatedWork W2049145612 @default.
• W4385989160 hasRelatedWork W2994531931 @default.
• W4385989160 hasRelatedWork W3201348321 @default.
• W4385989160 hasRelatedWork W3208169454 @default.
• W4385989160 hasRelatedWork W4294691859 @default.
• W4385989160 hasRelatedWork W4315777889 @default.
• W4385989160 hasRelatedWork W4322710485 @default.
• W4385989160 hasRelatedWork W4360991425 @default.
• W4385989160 hasRelatedWork W4379617137 @default.
• W4385989160 hasRelatedWork W4386690025 @default.
• W4385989160 hasVolume "4" @default.
• W4385989160 isParatext "false" @default.
• W4385989160 isRetracted "false" @default.
• W4385989160 workType "article" @default.