Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000386310> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3000386310 endingPage "19" @default.
- W3000386310 startingPage "15" @default.
- W3000386310 abstract "Purpose To validate a machine learning model trained on an open source dataset and subsequently optimize it to chest X-rays with large pneumothoraces from our institution. Methods The study was retrospective in nature. The open-source chest X-ray (CXR8) dataset was dichotomized to cases with pneumothorax (PTX) and all other cases (non-PTX), resulting in 41,946 non-PTX and 4696 PTX cases for the training set and 11,120 non-PTX and 541 PTX cases for the validation set. A limited supervision machine learning model was constructed to incorporate both localized and unlocalized pathology. Cases were then queried from our health system from 2013 to 2017. A total of 159 pneumothorax and 682 non-pneumothorax cases were available for the training set. For the validation set, 48 pneumothorax and 1287 non-pneumothorax cases were available. The model was trained, a receiver operator curve (ROC) was created, and output metrics, including area under the curve (AUC), sensitivity and specificity were calculated. Results Initial training of the model using the CXR8 dataset resulted in an AUC of 0.90 for pneumothorax detection. Naively inferring our own validation dataset on the CXR8 trained model output an AUC of 0.59. After re-training the model with our own training dataset, the validation dataset inference output an AUC of 0.90. Conclusion Our study showed that even though you may get great results on open-source datasets, those models may not translate well to real world data without an intervening retraining process." @default.
- W3000386310 created "2020-01-23" @default.
- W3000386310 creator A5061506587 @default.
- W3000386310 creator A5079423115 @default.
- W3000386310 date "2020-05-01" @default.
- W3000386310 modified "2023-10-02" @default.
- W3000386310 title "Retraining an open-source pneumothorax detecting machine learning algorithm for improved performance to medical images" @default.
- W3000386310 cites W2015159529 @default.
- W3000386310 cites W2044656011 @default.
- W3000386310 cites W2608231518 @default.
- W3000386310 cites W2733840449 @default.
- W3000386310 cites W2735045133 @default.
- W3000386310 cites W2767142522 @default.
- W3000386310 cites W2953130175 @default.
- W3000386310 doi "https://doi.org/10.1016/j.clinimag.2020.01.008" @default.
- W3000386310 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7085967" @default.
- W3000386310 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31954346" @default.
- W3000386310 hasPublicationYear "2020" @default.
- W3000386310 type Work @default.
- W3000386310 sameAs 3000386310 @default.
- W3000386310 citedByCount "21" @default.
- W3000386310 countsByYear W30003863102021 @default.
- W3000386310 countsByYear W30003863102022 @default.
- W3000386310 countsByYear W30003863102023 @default.
- W3000386310 crossrefType "journal-article" @default.
- W3000386310 hasAuthorship W3000386310A5061506587 @default.
- W3000386310 hasAuthorship W3000386310A5079423115 @default.
- W3000386310 hasBestOaLocation W30003863102 @default.
- W3000386310 hasConcept C11413529 @default.
- W3000386310 hasConcept C119857082 @default.
- W3000386310 hasConcept C126322002 @default.
- W3000386310 hasConcept C126838900 @default.
- W3000386310 hasConcept C144133560 @default.
- W3000386310 hasConcept C154945302 @default.
- W3000386310 hasConcept C155202549 @default.
- W3000386310 hasConcept C2778329176 @default.
- W3000386310 hasConcept C2778712577 @default.
- W3000386310 hasConcept C41008148 @default.
- W3000386310 hasConcept C51632099 @default.
- W3000386310 hasConcept C58471807 @default.
- W3000386310 hasConcept C58489278 @default.
- W3000386310 hasConcept C71924100 @default.
- W3000386310 hasConcept C76318530 @default.
- W3000386310 hasConceptScore W3000386310C11413529 @default.
- W3000386310 hasConceptScore W3000386310C119857082 @default.
- W3000386310 hasConceptScore W3000386310C126322002 @default.
- W3000386310 hasConceptScore W3000386310C126838900 @default.
- W3000386310 hasConceptScore W3000386310C144133560 @default.
- W3000386310 hasConceptScore W3000386310C154945302 @default.
- W3000386310 hasConceptScore W3000386310C155202549 @default.
- W3000386310 hasConceptScore W3000386310C2778329176 @default.
- W3000386310 hasConceptScore W3000386310C2778712577 @default.
- W3000386310 hasConceptScore W3000386310C41008148 @default.
- W3000386310 hasConceptScore W3000386310C51632099 @default.
- W3000386310 hasConceptScore W3000386310C58471807 @default.
- W3000386310 hasConceptScore W3000386310C58489278 @default.
- W3000386310 hasConceptScore W3000386310C71924100 @default.
- W3000386310 hasConceptScore W3000386310C76318530 @default.
- W3000386310 hasFunder F4320332161 @default.
- W3000386310 hasLocation W30003863101 @default.
- W3000386310 hasLocation W30003863102 @default.
- W3000386310 hasOpenAccess W3000386310 @default.
- W3000386310 hasPrimaryLocation W30003863101 @default.
- W3000386310 hasRelatedWork W2267592157 @default.
- W3000386310 hasRelatedWork W2945087682 @default.
- W3000386310 hasRelatedWork W3000386310 @default.
- W3000386310 hasRelatedWork W3018465876 @default.
- W3000386310 hasRelatedWork W3023559662 @default.
- W3000386310 hasRelatedWork W3035617937 @default.
- W3000386310 hasRelatedWork W3080910144 @default.
- W3000386310 hasRelatedWork W3153714520 @default.
- W3000386310 hasRelatedWork W4200115653 @default.
- W3000386310 hasRelatedWork W4225259767 @default.
- W3000386310 hasVolume "61" @default.
- W3000386310 isParatext "false" @default.
- W3000386310 isRetracted "false" @default.
- W3000386310 magId "3000386310" @default.
- W3000386310 workType "article" @default.