FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045346211> ?p ?o ?g. }

• W3045346211 endingPage "e0236378" @default.
• W3045346211 startingPage "e0236378" @default.
• W3045346211 abstract "Background To date, the missed diagnosis rate of pulmonary hypertension (PH) was high, and there has been limited development of a rapid, simple, and effective way to screen the disease. The purpose of this study is to develop a deep learning approach to achieve rapid detection of possible abnormalities in chest radiographs suggesting PH for screening patients suspected of PH. Methods We retrospectively collected frontal chest radiographs and the pulmonary artery systolic pressure (PASP) value measured by Doppler transthoracic echocardiography from 762 patients (357 healthy controls and 405 with PH) from three institutes in China from January 2013 to May 2019. The wohle sample comprised 762 images (641 for training, 80 for internal test, and 41 for external test). We firstly performed a 8-fold cross-validation on the 641 images selected for training (561 for pre-training, 80 for validation), then decided to tune learning rate to 0.0008 according to the best score on validation data. Finally, we used all the pre-training and validation data (561+80 = 641) to train our models (Resnet50, Xception, and Inception V3), evaluated them on internal and external test dataset to classify the images as having manifestations of PH or healthy according to the area under the receiver operating characteristic curve (AUC/ROC). After that, the three deep learning models were further used for prediction of PASP using regression algorithm. Moreover, we invited an experienced chest radiologist to classify the images in the test dataset as having PH or not, and compared the prediction accuracy performed by deep learing models with that of manual classification. Results The AUC performed by the best model (Inception V3) achieved 0.970 in the internal test, and slightly declined in the external test (0.967) when using deep learning algorithms to classify PH from normal based on chest X-rays. The mean absolute error (MAE) of the best model for prediction of PASP value was smaller in the internal test (7.45) compared to 9.95 in the external test. Manual classification of PH based on chest X-rays showed much lower AUCs compared to that performed by deep learning models both in the internal and external test. Conclusions The present study used deep learning algorithms to classify abnormalities suggesting PH in chest radiographs with high accuracy and good generalizability. Once tested prospectively in clinical settings, the technology could provide a non-invasive and easy-to-use method to screen patients suspected of having PH." @default.
• W3045346211 created "2020-07-29" @default.
• W3045346211 creator A5003105390 @default.
• W3045346211 creator A5004371868 @default.
• W3045346211 creator A5016483311 @default.
• W3045346211 creator A5017188235 @default.
• W3045346211 creator A5020538700 @default.
• W3045346211 creator A5025063777 @default.
• W3045346211 creator A5047256458 @default.
• W3045346211 creator A5053551341 @default.
• W3045346211 creator A5061672505 @default.
• W3045346211 creator A5086189626 @default.
• W3045346211 creator A5087509057 @default.
• W3045346211 creator A5089676379 @default.
• W3045346211 date "2020-07-24" @default.
• W3045346211 modified "2023-09-26" @default.
• W3045346211 title "A promising approach for screening pulmonary hypertension based on frontal chest radiographs using deep learning: A retrospective study" @default.
• W3045346211 cites W1832115302 @default.
• W3045346211 cites W1849277567 @default.
• W3045346211 cites W1971114335 @default.
• W3045346211 cites W1989584416 @default.
• W3045346211 cites W2003399513 @default.
• W3045346211 cites W2026939372 @default.
• W3045346211 cites W2033380643 @default.
• W3045346211 cites W2057143098 @default.
• W3045346211 cites W2074688428 @default.
• W3045346211 cites W2082526668 @default.
• W3045346211 cites W2095912225 @default.
• W3045346211 cites W2135473502 @default.
• W3045346211 cites W2141619730 @default.
• W3045346211 cites W2141905152 @default.
• W3045346211 cites W2154286581 @default.
• W3045346211 cites W2161370807 @default.
• W3045346211 cites W2183644045 @default.
• W3045346211 cites W2187630416 @default.
• W3045346211 cites W2253429366 @default.
• W3045346211 cites W2440599146 @default.
• W3045346211 cites W2474991055 @default.
• W3045346211 cites W2533800772 @default.
• W3045346211 cites W2559794190 @default.
• W3045346211 cites W2582602949 @default.
• W3045346211 cites W2605975631 @default.
• W3045346211 cites W2608231518 @default.
• W3045346211 cites W2618530766 @default.
• W3045346211 cites W2731899572 @default.
• W3045346211 cites W2760946358 @default.
• W3045346211 cites W2788633781 @default.
• W3045346211 cites W2811374795 @default.
• W3045346211 cites W2885326465 @default.
• W3045346211 cites W2895598278 @default.
• W3045346211 cites W2901794879 @default.
• W3045346211 cites W2901954625 @default.
• W3045346211 cites W2919115771 @default.
• W3045346211 cites W2948930564 @default.
• W3045346211 cites W2966884791 @default.
• W3045346211 doi "https://doi.org/10.1371/journal.pone.0236378" @default.
• W3045346211 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7380616" @default.
• W3045346211 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32706807" @default.
• W3045346211 hasPublicationYear "2020" @default.
• W3045346211 type Work @default.
• W3045346211 sameAs 3045346211 @default.
• W3045346211 citedByCount "16" @default.
• W3045346211 countsByYear W30453462112021 @default.
• W3045346211 countsByYear W30453462112022 @default.
• W3045346211 countsByYear W30453462112023 @default.
• W3045346211 crossrefType "journal-article" @default.
• W3045346211 hasAuthorship W3045346211A5003105390 @default.
• W3045346211 hasAuthorship W3045346211A5004371868 @default.
• W3045346211 hasAuthorship W3045346211A5016483311 @default.
• W3045346211 hasAuthorship W3045346211A5017188235 @default.
• W3045346211 hasAuthorship W3045346211A5020538700 @default.
• W3045346211 hasAuthorship W3045346211A5025063777 @default.
• W3045346211 hasAuthorship W3045346211A5047256458 @default.
• W3045346211 hasAuthorship W3045346211A5053551341 @default.
• W3045346211 hasAuthorship W3045346211A5061672505 @default.
• W3045346211 hasAuthorship W3045346211A5086189626 @default.
• W3045346211 hasAuthorship W3045346211A5087509057 @default.
• W3045346211 hasAuthorship W3045346211A5089676379 @default.
• W3045346211 hasBestOaLocation W30453462111 @default.
• W3045346211 hasConcept C108583219 @default.
• W3045346211 hasConcept C126322002 @default.
• W3045346211 hasConcept C126838900 @default.
• W3045346211 hasConcept C154945302 @default.
• W3045346211 hasConcept C167135981 @default.
• W3045346211 hasConcept C2780930700 @default.
• W3045346211 hasConcept C2780940725 @default.
• W3045346211 hasConcept C36454342 @default.
• W3045346211 hasConcept C41008148 @default.
• W3045346211 hasConcept C58471807 @default.
• W3045346211 hasConcept C71924100 @default.
• W3045346211 hasConceptScore W3045346211C108583219 @default.
• W3045346211 hasConceptScore W3045346211C126322002 @default.
• W3045346211 hasConceptScore W3045346211C126838900 @default.
• W3045346211 hasConceptScore W3045346211C154945302 @default.
• W3045346211 hasConceptScore W3045346211C167135981 @default.
• W3045346211 hasConceptScore W3045346211C2780930700 @default.
• W3045346211 hasConceptScore W3045346211C2780940725 @default.
• W3045346211 hasConceptScore W3045346211C36454342 @default.

• next