FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380422322> ?p ?o ?g. }

• W4380422322 endingPage "e47862" @default.
• W4380422322 startingPage "e47862" @default.
• W4380422322 abstract "Background Observational biomedical studies facilitate a new strategy for large-scale electronic health record (EHR) utilization to support precision medicine. However, data label inaccessibility is an increasingly important issue in clinical prediction, despite the use of synthetic and semisupervised learning from data. Little research has aimed to uncover the underlying graphical structure of EHRs. Objective A network-based generative adversarial semisupervised method is proposed. The objective is to train clinical prediction models on label-deficient EHRs to achieve comparable learning performance to supervised methods. Methods Three public data sets and one colorectal cancer data set gathered from the Second Affiliated Hospital of Zhejiang University were selected as benchmarks. The proposed models were trained on 5% to 25% labeled data and evaluated on classification metrics against conventional semisupervised and supervised methods. The data quality, model security, and memory scalability were also evaluated. Results The proposed method for semisupervised classification outperforms related semisupervised methods under the same setup, with the average area under the receiver operating characteristics curve (AUC) reaching 0.945, 0.673, 0.611, and 0.588 for the four data sets, respectively, followed by graph-based semisupervised learning (0.450, 0.454, 0.425, and 0.5676, respectively) and label propagation (0.475,0.344, 0.440, and 0.477, respectively). The average classification AUCs with 10% labeled data were 0.929, 0.719, 0.652, and 0.650, respectively, comparable to that of the supervised learning methods logistic regression (0.601, 0.670, 0.731, and 0.710, respectively), support vector machines (0.733, 0.720, 0.720, and 0.721, respectively), and random forests (0.982, 0.750, 0.758, and 0.740, respectively). The concerns regarding the secondary use of data and data security are alleviated by realistic data synthesis and robust privacy preservation. Conclusions Training clinical prediction models on label-deficient EHRs is indispensable in data-driven research. The proposed method has great potential to exploit the intrinsic structure of EHRs and achieve comparable learning performance to supervised methods." @default.
• W4380422322 created "2023-06-14" @default.
• W4380422322 creator A5000413762 @default.
• W4380422322 creator A5008949219 @default.
• W4380422322 creator A5040651662 @default.
• W4380422322 creator A5049442940 @default.
• W4380422322 creator A5057311321 @default.
• W4380422322 creator A5069371874 @default.
• W4380422322 creator A5081262769 @default.
• W4380422322 date "2023-06-13" @default.
• W4380422322 modified "2023-09-26" @default.
• W4380422322 title "Improving an Electronic Health Record–Based Clinical Prediction Model Under Label Deficiency: Network-Based Generative Adversarial Semisupervised Approach" @default.
• W4380422322 cites W1126991912 @default.
• W4380422322 cites W1839682376 @default.
• W4380422322 cites W1974589509 @default.
• W4380422322 cites W2023248478 @default.
• W4380422322 cites W2027867013 @default.
• W4380422322 cites W2105289139 @default.
• W4380422322 cites W2164124780 @default.
• W4380422322 cites W2559898506 @default.
• W4380422322 cites W2751687090 @default.
• W4380422322 cites W2794511224 @default.
• W4380422322 cites W2797082239 @default.
• W4380422322 cites W2803290558 @default.
• W4380422322 cites W2805089815 @default.
• W4380422322 cites W2806048670 @default.
• W4380422322 cites W2904931021 @default.
• W4380422322 cites W2949688312 @default.
• W4380422322 cites W2950562763 @default.
• W4380422322 cites W2963034797 @default.
• W4380422322 cites W2963169753 @default.
• W4380422322 cites W2997445929 @default.
• W4380422322 cites W3096831136 @default.
• W4380422322 cites W3104038788 @default.
• W4380422322 cites W3105705953 @default.
• W4380422322 cites W4207024994 @default.
• W4380422322 cites W4210734798 @default.
• W4380422322 cites W4294558607 @default.
• W4380422322 cites W4297951436 @default.
• W4380422322 cites W4320013936 @default.
• W4380422322 doi "https://doi.org/10.2196/47862" @default.
• W4380422322 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37310778" @default.
• W4380422322 hasPublicationYear "2023" @default.
• W4380422322 type Work @default.
• W4380422322 citedByCount "0" @default.
• W4380422322 crossrefType "journal-article" @default.
• W4380422322 hasAuthorship W4380422322A5000413762 @default.
• W4380422322 hasAuthorship W4380422322A5008949219 @default.
• W4380422322 hasAuthorship W4380422322A5040651662 @default.
• W4380422322 hasAuthorship W4380422322A5049442940 @default.
• W4380422322 hasAuthorship W4380422322A5057311321 @default.
• W4380422322 hasAuthorship W4380422322A5069371874 @default.
• W4380422322 hasAuthorship W4380422322A5081262769 @default.
• W4380422322 hasBestOaLocation W43804223221 @default.
• W4380422322 hasConcept C119857082 @default.
• W4380422322 hasConcept C12267149 @default.
• W4380422322 hasConcept C124101348 @default.
• W4380422322 hasConcept C136389625 @default.
• W4380422322 hasConcept C151956035 @default.
• W4380422322 hasConcept C154945302 @default.
• W4380422322 hasConcept C41008148 @default.
• W4380422322 hasConcept C48044578 @default.
• W4380422322 hasConcept C50644808 @default.
• W4380422322 hasConcept C58471807 @default.
• W4380422322 hasConcept C58489278 @default.
• W4380422322 hasConcept C77088390 @default.
• W4380422322 hasConceptScore W4380422322C119857082 @default.
• W4380422322 hasConceptScore W4380422322C12267149 @default.
• W4380422322 hasConceptScore W4380422322C124101348 @default.
• W4380422322 hasConceptScore W4380422322C136389625 @default.
• W4380422322 hasConceptScore W4380422322C151956035 @default.
• W4380422322 hasConceptScore W4380422322C154945302 @default.
• W4380422322 hasConceptScore W4380422322C41008148 @default.
• W4380422322 hasConceptScore W4380422322C48044578 @default.
• W4380422322 hasConceptScore W4380422322C50644808 @default.
• W4380422322 hasConceptScore W4380422322C58471807 @default.
• W4380422322 hasConceptScore W4380422322C58489278 @default.
• W4380422322 hasConceptScore W4380422322C77088390 @default.
• W4380422322 hasLocation W43804223221 @default.
• W4380422322 hasLocation W43804223222 @default.
• W4380422322 hasLocation W43804223223 @default.
• W4380422322 hasOpenAccess W4380422322 @default.
• W4380422322 hasPrimaryLocation W43804223221 @default.
• W4380422322 hasRelatedWork W1996541855 @default.
• W4380422322 hasRelatedWork W2361747435 @default.
• W4380422322 hasRelatedWork W2554948173 @default.
• W4380422322 hasRelatedWork W3047552631 @default.
• W4380422322 hasRelatedWork W3099386970 @default.
• W4380422322 hasRelatedWork W3195168932 @default.
• W4380422322 hasRelatedWork W4285325926 @default.
• W4380422322 hasRelatedWork W4321636153 @default.
• W4380422322 hasRelatedWork W4383535405 @default.
• W4380422322 hasRelatedWork W4384828018 @default.
• W4380422322 hasVolume "11" @default.
• W4380422322 isParatext "false" @default.
• W4380422322 isRetracted "false" @default.
• W4380422322 workType "article" @default.