FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379798163> ?p ?o ?g. }

• W4379798163 endingPage "1151" @default.
• W4379798163 startingPage "1140" @default.
• W4379798163 abstract "Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing and deploying personalized medicine and targeted clinical trials. Recent advances in ML have enabled the integration of wider ranges of data including both medical records and imaging (radiomics). However, the development of prognostic models is complex as no modeling strategy is universally superior to others and validation of developed models requires large and diverse datasets to demonstrate that prognostic models developed (regardless of method) from one dataset are applicable to other datasets both internally and externally. Using a retrospective dataset of 2,552 patients from a single institution and a strict evaluation framework that included external validation on three external patient cohorts (873 patients), we crowdsourced the development of ML models to predict overall survival in head and neck cancer (HNC) using electronic medical records (EMR) and pretreatment radiological images. To assess the relative contributions of radiomics in predicting HNC prognosis, we compared 12 different models using imaging and/or EMR data. The model with the highest accuracy used multitask learning on clinical data and tumor volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction, outperforming models relying on clinical data only, engineered radiomics, or complex deep neural network architecture. However, when we attempted to extend the best performing models from this large training dataset to other institutions, we observed significant reductions in the performance of the model in those datasets, highlighting the importance of detailed population-based reporting for AI/ML model utility and stronger validation frameworks. We have developed highly prognostic models for overall survival in HNC using EMRs and pretreatment radiological images based on a large, retrospective dataset of 2,552 patients from our institution.Diverse ML approaches were used by independent investigators. The model with the highest accuracy used multitask learning on clinical data and tumor volume.External validation of the top three performing models on three datasets (873 patients) with significant differences in the distributions of clinical and demographic variables demonstrated significant decreases in model performance. Significance: ML combined with simple prognostic factors outperformed multiple advanced CT radiomics and deep learning methods. ML models provided diverse solutions for prognosis of patients with HNC but their prognostic value is affected by differences in patient populations and require extensive validation." @default.
• W4379798163 created "2023-06-09" @default.
• W4379798163 creator A5000041878 @default.
• W4379798163 creator A5001452511 @default.
• W4379798163 creator A5008075505 @default.
• W4379798163 creator A5010067099 @default.
• W4379798163 creator A5010487226 @default.
• W4379798163 creator A5018154366 @default.
• W4379798163 creator A5018962553 @default.
• W4379798163 creator A5024123838 @default.
• W4379798163 creator A5034105554 @default.
• W4379798163 creator A5039985523 @default.
• W4379798163 creator A5043371954 @default.
• W4379798163 creator A5044425152 @default.
• W4379798163 creator A5050418994 @default.
• W4379798163 creator A5057938768 @default.
• W4379798163 creator A5063842271 @default.
• W4379798163 creator A5064900626 @default.
• W4379798163 creator A5081114674 @default.
• W4379798163 creator A5082888506 @default.
• W4379798163 creator A5091831506 @default.
• W4379798163 date "2023-06-29" @default.
• W4379798163 modified "2023-09-30" @default.
• W4379798163 title "Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics" @default.
• W4379798163 cites W1496107432 @default.
• W4379798163 cites W1966716734 @default.
• W4379798163 cites W1990956554 @default.
• W4379798163 cites W2015712245 @default.
• W4379798163 cites W2031095044 @default.
• W4379798163 cites W2082704080 @default.
• W4379798163 cites W2083927153 @default.
• W4379798163 cites W2103004421 @default.
• W4379798163 cites W2118366842 @default.
• W4379798163 cites W2119872305 @default.
• W4379798163 cites W2124891284 @default.
• W4379798163 cites W2126994971 @default.
• W4379798163 cites W2129925362 @default.
• W4379798163 cites W2151554678 @default.
• W4379798163 cites W2154053567 @default.
• W4379798163 cites W2158485828 @default.
• W4379798163 cites W2158698691 @default.
• W4379798163 cites W2159755394 @default.
• W4379798163 cites W2166948894 @default.
• W4379798163 cites W2174661749 @default.
• W4379798163 cites W2409456704 @default.
• W4379798163 cites W2484065175 @default.
• W4379798163 cites W2513587258 @default.
• W4379798163 cites W2592785849 @default.
• W4379798163 cites W2600642189 @default.
• W4379798163 cites W2737453412 @default.
• W4379798163 cites W2767128594 @default.
• W4379798163 cites W2787225861 @default.
• W4379798163 cites W2804779932 @default.
• W4379798163 cites W28412257 @default.
• W4379798163 cites W2886281300 @default.
• W4379798163 cites W2889506086 @default.
• W4379798163 cites W2890236360 @default.
• W4379798163 cites W2899847761 @default.
• W4379798163 cites W2912914218 @default.
• W4379798163 cites W2917986559 @default.
• W4379798163 cites W2919115771 @default.
• W4379798163 cites W2923027365 @default.
• W4379798163 cites W2946185430 @default.
• W4379798163 cites W2954041497 @default.
• W4379798163 cites W2954499361 @default.
• W4379798163 cites W2965469956 @default.
• W4379798163 cites W2970269748 @default.
• W4379798163 cites W2974710849 @default.
• W4379798163 cites W2992715741 @default.
• W4379798163 cites W2997449172 @default.
• W4379798163 cites W2998789541 @default.
• W4379798163 cites W3008058947 @default.
• W4379798163 cites W3008840315 @default.
• W4379798163 cites W3024513077 @default.
• W4379798163 cites W3025872843 @default.
• W4379798163 cites W3080627676 @default.
• W4379798163 cites W3091673453 @default.
• W4379798163 cites W3093025058 @default.
• W4379798163 cites W3097217077 @default.
• W4379798163 cites W3142450577 @default.
• W4379798163 cites W4205530749 @default.
• W4379798163 cites W4245824586 @default.
• W4379798163 doi "https://doi.org/10.1158/2767-9764.crc-22-0152" @default.
• W4379798163 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37397861" @default.
• W4379798163 hasPublicationYear "2023" @default.
• W4379798163 type Work @default.
• W4379798163 citedByCount "5" @default.
• W4379798163 countsByYear W43797981632023 @default.
• W4379798163 crossrefType "journal-article" @default.
• W4379798163 hasAuthorship W4379798163A5000041878 @default.
• W4379798163 hasAuthorship W4379798163A5001452511 @default.
• W4379798163 hasAuthorship W4379798163A5008075505 @default.
• W4379798163 hasAuthorship W4379798163A5010067099 @default.
• W4379798163 hasAuthorship W4379798163A5010487226 @default.
• W4379798163 hasAuthorship W4379798163A5018154366 @default.
• W4379798163 hasAuthorship W4379798163A5018962553 @default.
• W4379798163 hasAuthorship W4379798163A5024123838 @default.
• W4379798163 hasAuthorship W4379798163A5034105554 @default.

• next