FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208231772> ?p ?o ?g. }

• W3208231772 abstract "Abstract Background Stroke is the leading cause of death in China, and the stroke burden is especially high in rural areas. Risk prediction is essential for primary prevention of stroke. However, uncertainty remains about the optimal methodology for analyzing stroke risk. In this study, we aim to determine the most effective stroke prediction method in a targeted population and establish a general framework and pipeline for future analysis. Purpose 1) to determine the most effective stroke prediction method in a targeted population and 2) to establish a general framework and pipeline for future analysis. Methods Data were obtained from the China Stroke Primary Prevention Trial (CSPPT), a randomized, double-blind, multi-center clinical trial. 20,702 hypertensive patients without prior history of stroke were included in the study. The primary outcome was new nonfatal and fatal stroke (ischemic or hemorrhagic) occurring between baseline and follow-up (a median of 4.2 years). All suspected stroke cases were collected and further validated by the event adjudication committee. We compared two regression models (logistic regression and step wise logistic regression) and two machine learning methods (extreme gradient boosting and random forest). All models were trained using questionnaire data with and without laboratory data, then analyzed and compared. The primary outcome was defined as first stroke. Accuracy, sensitivity, specificity and AUCs (area under receiver operating characteristic curve) were used to assess each model. AUCs were used to evaluate the performance of each analysis method. Results In our data set with 20,702 samples and 127 variables, the highest AUCs (0.775 (0.725–0.826)) were observed with RUS (random under sampling) applied to RF (random forest). Before applying data balancing techniques, all analysis methods showed very low sensitivity (around 0.01), very high accuracy (around 0.97), and very high specificity (around 1.00). The mean AUCs were 0.741 (0.678–0.803). After data balancing techniques were applied, we observed an increase in sensitivity and decreases in accuracy and specificity. Different data balancing techniques had different effects on analysis methods. No significant effect on AUCs was observed; the range of increase and decrease was around 0.01. Similar overall patterns were observed when training with laboratory test data added. The mean AUCs were 0.739 (0.679–0.799) and 0.734 (0.674–9.795) for all models using data with and without laboratory test respectively. The 10 most important variables as determined by the model were selected as stroke risk predictors for all analysis models. Conclusion The most effective stroke prediction method in this Chinese rural hypertensive population is RUS applied to RF. The optimal analysis method and variable selection depends on data-specific features. FUNDunding Acknowledgement Type of funding sources: Public Institution(s). Main funding source(s): Key R&D Projects, Jiangxi [20203BBGL73173] National Key Research and Development Program [2016YFE0205400]" @default.
• W3208231772 created "2021-11-08" @default.
• W3208231772 creator A5001290903 @default.
• W3208231772 creator A5017096513 @default.
• W3208231772 creator A5029855304 @default.
• W3208231772 creator A5045772918 @default.
• W3208231772 creator A5049859611 @default.
• W3208231772 creator A5053467018 @default.
• W3208231772 creator A5054555433 @default.
• W3208231772 creator A5055547380 @default.
• W3208231772 creator A5087045654 @default.
• W3208231772 date "2021-10-01" @default.
• W3208231772 modified "2023-09-25" @default.
• W3208231772 title "Predicting stroke risk in Chinese hypertensive population using machine learning" @default.
• W3208231772 doi "https://doi.org/10.1093/eurheartj/ehab724.2489" @default.
• W3208231772 hasPublicationYear "2021" @default.
• W3208231772 type Work @default.
• W3208231772 sameAs 3208231772 @default.
• W3208231772 citedByCount "0" @default.
• W3208231772 crossrefType "journal-article" @default.
• W3208231772 hasAuthorship W3208231772A5001290903 @default.
• W3208231772 hasAuthorship W3208231772A5017096513 @default.
• W3208231772 hasAuthorship W3208231772A5029855304 @default.
• W3208231772 hasAuthorship W3208231772A5045772918 @default.
• W3208231772 hasAuthorship W3208231772A5049859611 @default.
• W3208231772 hasAuthorship W3208231772A5053467018 @default.
• W3208231772 hasAuthorship W3208231772A5054555433 @default.
• W3208231772 hasAuthorship W3208231772A5055547380 @default.
• W3208231772 hasAuthorship W3208231772A5087045654 @default.
• W3208231772 hasBestOaLocation W32082317721 @default.
• W3208231772 hasConcept C119857082 @default.
• W3208231772 hasConcept C126322002 @default.
• W3208231772 hasConcept C127413603 @default.
• W3208231772 hasConcept C151956035 @default.
• W3208231772 hasConcept C169258074 @default.
• W3208231772 hasConcept C2780645631 @default.
• W3208231772 hasConcept C2908647359 @default.
• W3208231772 hasConcept C41008148 @default.
• W3208231772 hasConcept C58471807 @default.
• W3208231772 hasConcept C71924100 @default.
• W3208231772 hasConcept C78519656 @default.
• W3208231772 hasConcept C99454951 @default.
• W3208231772 hasConceptScore W3208231772C119857082 @default.
• W3208231772 hasConceptScore W3208231772C126322002 @default.
• W3208231772 hasConceptScore W3208231772C127413603 @default.
• W3208231772 hasConceptScore W3208231772C151956035 @default.
• W3208231772 hasConceptScore W3208231772C169258074 @default.
• W3208231772 hasConceptScore W3208231772C2780645631 @default.
• W3208231772 hasConceptScore W3208231772C2908647359 @default.
• W3208231772 hasConceptScore W3208231772C41008148 @default.
• W3208231772 hasConceptScore W3208231772C58471807 @default.
• W3208231772 hasConceptScore W3208231772C71924100 @default.
• W3208231772 hasConceptScore W3208231772C78519656 @default.
• W3208231772 hasConceptScore W3208231772C99454951 @default.
• W3208231772 hasIssue "Supplement_1" @default.
• W3208231772 hasLocation W32082317721 @default.
• W3208231772 hasOpenAccess W3208231772 @default.
• W3208231772 hasPrimaryLocation W32082317721 @default.
• W3208231772 hasRelatedWork W2799952019 @default.
• W3208231772 hasRelatedWork W2899909823 @default.
• W3208231772 hasRelatedWork W3099386970 @default.
• W3208231772 hasRelatedWork W3194190302 @default.
• W3208231772 hasRelatedWork W4205415703 @default.
• W3208231772 hasRelatedWork W4206443144 @default.
• W3208231772 hasRelatedWork W4225984265 @default.
• W3208231772 hasRelatedWork W4239706975 @default.
• W3208231772 hasRelatedWork W4308993660 @default.
• W3208231772 hasRelatedWork W4367596031 @default.
• W3208231772 hasVolume "42" @default.
• W3208231772 isParatext "false" @default.
• W3208231772 isRetracted "false" @default.
• W3208231772 magId "3208231772" @default.
• W3208231772 workType "article" @default.