FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385145683> ?p ?o ?g. }

• W4385145683 abstract "Abstract Background Machine learning (ML) methods to build prediction models starting from electrocardiogram (ECG) signals are an emerging research field. The aim of the present study is to investigate the performances of two ML approaches based on ECGs for the prediction of new-onset atrial fibrillation (AF), in terms of discrimination, calibration and sample size dependence. Methods We trained two models to predict new-onset AF: a convolutional neural network (CNN), that takes as input the raw ECG signals, and an eXtreme Gradient Boosting model (XGB), that uses the signal’s extracted features. A penalized logistic regression model (LR) was used as a benchmark. Discrimination was evaluated with the area under the ROC curve, while calibration with the integrated calibration index. We investigated the dependence of models’ performances on the sample size and on class imbalance corrections introduced with random under-sampling. Results CNN's discrimination was the most affected by the sample size, outperforming XGB and LR only around n = 10.000 observations. Calibration showed only a small dependence on the sample size for all the models considered. Balancing the training set with random undersampling did not improve discrimination in any of the models. Instead, the main effect of imbalance corrections was to worsen the models’ calibration (for CNN, integrated calibration index from 0.014 [0.01, 0.018] to 0.17 [0.16, 0.19]). The sample size emerged as a fundamental point for developing the CNN model, especially in terms of discrimination (AUC = 0.75 [0.73, 0.77] when n = 10.000, AUC = 0.80 [0.79, 0.81] when n = 150.000). The effect of the sample size on the other two models was weaker. Imbalance corrections led to poorly calibrated models, for all the approaches considered, reducing the clinical utility of the models. Conclusions Our results suggest that the choice of approach in the analysis of ECG should be based on the amount of data available, preferring more standard models for small datasets. Moreover, imbalance correction methods should be avoided when developing clinical prediction models, where calibration is crucial." @default.
• W4385145683 created "2023-07-23" @default.
• W4385145683 creator A5014966655 @default.
• W4385145683 creator A5018004237 @default.
• W4385145683 creator A5038962020 @default.
• W4385145683 creator A5039739616 @default.
• W4385145683 creator A5041626379 @default.
• W4385145683 creator A5060744592 @default.
• W4385145683 creator A5070439792 @default.
• W4385145683 date "2023-07-22" @default.
• W4385145683 modified "2023-10-06" @default.
• W4385145683 title "Comparison of discrimination and calibration performance of ECG-based machine learning models for prediction of new-onset atrial fibrillation" @default.
• W4385145683 cites W2060374620 @default.
• W4385145683 cites W2097173178 @default.
• W4385145683 cites W2148143831 @default.
• W4385145683 cites W2609696371 @default.
• W4385145683 cites W2887355428 @default.
• W4385145683 cites W2902644322 @default.
• W4385145683 cites W2902730614 @default.
• W4385145683 cites W2943118732 @default.
• W4385145683 cites W2947446138 @default.
• W4385145683 cites W2954707123 @default.
• W4385145683 cites W2965520043 @default.
• W4385145683 cites W2968959539 @default.
• W4385145683 cites W2971393043 @default.
• W4385145683 cites W2991183299 @default.
• W4385145683 cites W2996480032 @default.
• W4385145683 cites W3007453563 @default.
• W4385145683 cites W3039775522 @default.
• W4385145683 cites W3102476541 @default.
• W4385145683 cites W3127657277 @default.
• W4385145683 cites W3129167842 @default.
• W4385145683 cites W3133470659 @default.
• W4385145683 cites W3153276113 @default.
• W4385145683 cites W3156215970 @default.
• W4385145683 cites W3186054243 @default.
• W4385145683 cites W3192248047 @default.
• W4385145683 cites W3212883348 @default.
• W4385145683 cites W4225754783 @default.
• W4385145683 cites W4243367342 @default.
• W4385145683 cites W4281717669 @default.
• W4385145683 cites W4309652961 @default.
• W4385145683 doi "https://doi.org/10.1186/s12874-023-01989-3" @default.
• W4385145683 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37481514" @default.
• W4385145683 hasPublicationYear "2023" @default.
• W4385145683 type Work @default.
• W4385145683 citedByCount "0" @default.
• W4385145683 crossrefType "journal-article" @default.
• W4385145683 hasAuthorship W4385145683A5014966655 @default.
• W4385145683 hasAuthorship W4385145683A5018004237 @default.
• W4385145683 hasAuthorship W4385145683A5038962020 @default.
• W4385145683 hasAuthorship W4385145683A5039739616 @default.
• W4385145683 hasAuthorship W4385145683A5041626379 @default.
• W4385145683 hasAuthorship W4385145683A5060744592 @default.
• W4385145683 hasAuthorship W4385145683A5070439792 @default.
• W4385145683 hasBestOaLocation W43851456831 @default.
• W4385145683 hasConcept C105795698 @default.
• W4385145683 hasConcept C119857082 @default.
• W4385145683 hasConcept C126322002 @default.
• W4385145683 hasConcept C129848803 @default.
• W4385145683 hasConcept C13280743 @default.
• W4385145683 hasConcept C136536468 @default.
• W4385145683 hasConcept C151956035 @default.
• W4385145683 hasConcept C153180895 @default.
• W4385145683 hasConcept C154945302 @default.
• W4385145683 hasConcept C165838908 @default.
• W4385145683 hasConcept C169258074 @default.
• W4385145683 hasConcept C185798385 @default.
• W4385145683 hasConcept C205649164 @default.
• W4385145683 hasConcept C2779161974 @default.
• W4385145683 hasConcept C33923547 @default.
• W4385145683 hasConcept C41008148 @default.
• W4385145683 hasConcept C71924100 @default.
• W4385145683 hasConcept C81363708 @default.
• W4385145683 hasConceptScore W4385145683C105795698 @default.
• W4385145683 hasConceptScore W4385145683C119857082 @default.
• W4385145683 hasConceptScore W4385145683C126322002 @default.
• W4385145683 hasConceptScore W4385145683C129848803 @default.
• W4385145683 hasConceptScore W4385145683C13280743 @default.
• W4385145683 hasConceptScore W4385145683C136536468 @default.
• W4385145683 hasConceptScore W4385145683C151956035 @default.
• W4385145683 hasConceptScore W4385145683C153180895 @default.
• W4385145683 hasConceptScore W4385145683C154945302 @default.
• W4385145683 hasConceptScore W4385145683C165838908 @default.
• W4385145683 hasConceptScore W4385145683C169258074 @default.
• W4385145683 hasConceptScore W4385145683C185798385 @default.
• W4385145683 hasConceptScore W4385145683C205649164 @default.
• W4385145683 hasConceptScore W4385145683C2779161974 @default.
• W4385145683 hasConceptScore W4385145683C33923547 @default.
• W4385145683 hasConceptScore W4385145683C41008148 @default.
• W4385145683 hasConceptScore W4385145683C71924100 @default.
• W4385145683 hasConceptScore W4385145683C81363708 @default.
• W4385145683 hasIssue "1" @default.
• W4385145683 hasLocation W43851456831 @default.
• W4385145683 hasLocation W43851456832 @default.
• W4385145683 hasLocation W43851456833 @default.
• W4385145683 hasOpenAccess W4385145683 @default.
• W4385145683 hasPrimaryLocation W43851456831 @default.
• W4385145683 hasRelatedWork W2994586973 @default.
• W4385145683 hasRelatedWork W3176807344 @default.

• next