Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280491884> ?p ?o ?g. }
- W4280491884 abstract "To construct and validate prediction models for the risk of diabetic retinopathy (DR) in patients with type 2 diabetes mellitus.Patients with type 2 diabetes mellitus hospitalized over the period between January 2010 and September 2018 were retrospectively collected. Eighteen baseline demographic and clinical characteristics were used as predictors to train five machine-learning models. The model that showed favorable predictive efficacy was evaluated at annual follow-ups. Multi-point data of the patients in the test set were utilized to further evaluate the model's performance. We also assessed the relative prognostic importance of the selected risk factors for DR outcomes.Of 7943 collected patients, 1692 (21.30%) developed DR during follow-up. Among the five models, the XGBoost model achieved the highest predictive performance with an AUC, accuracy, sensitivity, and specificity of 0.803, 88.9%, 74.0%, and 81.1%, respectively. The XGBoost model's AUCs in the different follow-up periods were 0.834 to 0.966. In addition to the classical risk factors of DR, serum uric acid (SUA), low-density lipoprotein cholesterol (LDL-C), total cholesterol (TC), estimated glomerular filtration rate (eGFR), and triglyceride (TG) were also identified to be important and strong predictors for the disease. Compared with the clinical diagnosis method of DR, the XGBoost model achieved an average of 2.895 years prior to the first diagnosis.The proposed model achieved high performance in predicting the risk of DR among patients with type 2 diabetes mellitus at each time point. This study established the potential of the XGBoost model to facilitate clinicians in identifying high-risk patients and making type 2 diabetes management-related decisions." @default.
- W4280491884 created "2022-05-22" @default.
- W4280491884 creator A5000119580 @default.
- W4280491884 creator A5003331350 @default.
- W4280491884 creator A5005606057 @default.
- W4280491884 creator A5037255059 @default.
- W4280491884 creator A5042802004 @default.
- W4280491884 creator A5047179600 @default.
- W4280491884 creator A5053165442 @default.
- W4280491884 creator A5055207211 @default.
- W4280491884 creator A5070918242 @default.
- W4280491884 creator A5073113793 @default.
- W4280491884 creator A5090988194 @default.
- W4280491884 date "2022-05-17" @default.
- W4280491884 modified "2023-10-03" @default.
- W4280491884 title "Using Machine Learning Techniques to Develop Risk Prediction Models for the Risk of Incident Diabetic Retinopathy Among Patients With Type 2 Diabetes Mellitus: A Cohort Study" @default.
- W4280491884 cites W1966206262 @default.
- W4280491884 cites W1985282719 @default.
- W4280491884 cites W2027114368 @default.
- W4280491884 cites W2033428406 @default.
- W4280491884 cites W2058428120 @default.
- W4280491884 cites W2066417811 @default.
- W4280491884 cites W2087907943 @default.
- W4280491884 cites W2090883327 @default.
- W4280491884 cites W2122111042 @default.
- W4280491884 cites W2124521298 @default.
- W4280491884 cites W2130157840 @default.
- W4280491884 cites W2134293572 @default.
- W4280491884 cites W2141864382 @default.
- W4280491884 cites W2155965977 @default.
- W4280491884 cites W2234307896 @default.
- W4280491884 cites W2337454357 @default.
- W4280491884 cites W2598992821 @default.
- W4280491884 cites W2612292012 @default.
- W4280491884 cites W2808905409 @default.
- W4280491884 cites W2885568874 @default.
- W4280491884 cites W2888589263 @default.
- W4280491884 cites W2910210501 @default.
- W4280491884 cites W2911964244 @default.
- W4280491884 cites W2940010972 @default.
- W4280491884 cites W2958369942 @default.
- W4280491884 cites W2976376778 @default.
- W4280491884 cites W2978502824 @default.
- W4280491884 cites W3016330753 @default.
- W4280491884 cites W3033553585 @default.
- W4280491884 cites W3102476541 @default.
- W4280491884 cites W3106367574 @default.
- W4280491884 cites W3108717672 @default.
- W4280491884 cites W3111698685 @default.
- W4280491884 cites W4239510810 @default.
- W4280491884 cites W4243892209 @default.
- W4280491884 doi "https://doi.org/10.3389/fendo.2022.876559" @default.
- W4280491884 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35655800" @default.
- W4280491884 hasPublicationYear "2022" @default.
- W4280491884 type Work @default.
- W4280491884 citedByCount "6" @default.
- W4280491884 countsByYear W42804918842022 @default.
- W4280491884 countsByYear W42804918842023 @default.
- W4280491884 crossrefType "journal-article" @default.
- W4280491884 hasAuthorship W4280491884A5000119580 @default.
- W4280491884 hasAuthorship W4280491884A5003331350 @default.
- W4280491884 hasAuthorship W4280491884A5005606057 @default.
- W4280491884 hasAuthorship W4280491884A5037255059 @default.
- W4280491884 hasAuthorship W4280491884A5042802004 @default.
- W4280491884 hasAuthorship W4280491884A5047179600 @default.
- W4280491884 hasAuthorship W4280491884A5053165442 @default.
- W4280491884 hasAuthorship W4280491884A5055207211 @default.
- W4280491884 hasAuthorship W4280491884A5070918242 @default.
- W4280491884 hasAuthorship W4280491884A5073113793 @default.
- W4280491884 hasAuthorship W4280491884A5090988194 @default.
- W4280491884 hasBestOaLocation W42804918841 @default.
- W4280491884 hasConcept C126322002 @default.
- W4280491884 hasConcept C134018914 @default.
- W4280491884 hasConcept C2777180221 @default.
- W4280491884 hasConcept C2779829184 @default.
- W4280491884 hasConcept C2910068830 @default.
- W4280491884 hasConcept C555293320 @default.
- W4280491884 hasConcept C58471807 @default.
- W4280491884 hasConcept C71924100 @default.
- W4280491884 hasConceptScore W4280491884C126322002 @default.
- W4280491884 hasConceptScore W4280491884C134018914 @default.
- W4280491884 hasConceptScore W4280491884C2777180221 @default.
- W4280491884 hasConceptScore W4280491884C2779829184 @default.
- W4280491884 hasConceptScore W4280491884C2910068830 @default.
- W4280491884 hasConceptScore W4280491884C555293320 @default.
- W4280491884 hasConceptScore W4280491884C58471807 @default.
- W4280491884 hasConceptScore W4280491884C71924100 @default.
- W4280491884 hasLocation W42804918841 @default.
- W4280491884 hasLocation W42804918842 @default.
- W4280491884 hasLocation W42804918843 @default.
- W4280491884 hasOpenAccess W4280491884 @default.
- W4280491884 hasPrimaryLocation W42804918841 @default.
- W4280491884 hasRelatedWork W1563850031 @default.
- W4280491884 hasRelatedWork W2367206690 @default.
- W4280491884 hasRelatedWork W2386926331 @default.
- W4280491884 hasRelatedWork W2401570230 @default.
- W4280491884 hasRelatedWork W2415759662 @default.
- W4280491884 hasRelatedWork W2907238362 @default.
- W4280491884 hasRelatedWork W2947297366 @default.
- W4280491884 hasRelatedWork W3036934084 @default.