Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385698239> ?p ?o ?g. }
- W4385698239 abstract "“Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate the performance of a biopsy-decision support algorithmic model, the intelligent-augmented breast cancer risk calculator (iBRISK), on a multicenter patient dataset. Materials and Methods iBRISK was previously developed by applying deep learning to clinical risk factors and mammographic descriptors from 9,700 patient records at the primary institution and validated using another 1,078 patients. All patients were seen from March 2006-December 2016. In this multicenter study, iBRISK was further assessed on an independent, retrospective dataset (January 2015-June 2019) from three major health care institutions in Texas, USA with Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions. Data were dichotomized and trichotomized to measure precision in risk stratification and probability of malignancy (POM) estimation. iBRISK score was also evaluated as a continuous predictor of malignancy and cost saving analysis was performed. Results The iBRISK model’s accuracy was 89.5%, area under the receiver operating characteristic curve (AUROC) 0.93 (95% CI: 0.92–0.95), sensitivity 100%, and specificity 81%. A total of 4,209 women (56 [IQR: 45–65] years) were included in the multicenter dataset. Only two of 1,228 patients (0.16%) in the “low” POM group had malignant lesions while in the “high” POM, malignancy rate was 85.9%. iBRISK score as a continuous predictor of malignancy yielded an AUROC of 0.97 (95% CI: 0.97–0.98). Estimated potential cost savings were over $420 million. Conclusion iBRISK demonstrated high sensitivity in malignancy prediction of BI-RADS 4 lesions. iBRISK may safely obviate biopsies in up to 50% of patients in low or moderate POM-groups and reduce biopsy-associated costs. Published under a CC BY 4.0 license" @default.
- W4385698239 created "2023-08-10" @default.
- W4385698239 creator A5004526331 @default.
- W4385698239 creator A5007271191 @default.
- W4385698239 creator A5010561584 @default.
- W4385698239 creator A5015077092 @default.
- W4385698239 creator A5025409813 @default.
- W4385698239 creator A5029624096 @default.
- W4385698239 creator A5031598363 @default.
- W4385698239 creator A5033477318 @default.
- W4385698239 creator A5035940082 @default.
- W4385698239 creator A5038376885 @default.
- W4385698239 creator A5047918797 @default.
- W4385698239 creator A5057671045 @default.
- W4385698239 creator A5057702565 @default.
- W4385698239 creator A5059999814 @default.
- W4385698239 creator A5060561574 @default.
- W4385698239 creator A5061446821 @default.
- W4385698239 creator A5070774369 @default.
- W4385698239 creator A5071831846 @default.
- W4385698239 creator A5086830094 @default.
- W4385698239 creator A5090879728 @default.
- W4385698239 date "2023-08-09" @default.
- W4385698239 modified "2023-09-23" @default.
- W4385698239 title "A Deep Learning Decision Support Tool to Improve Risk Stratification and Reduce Unnecessary Biopsies in BI-RADS 4 Mammograms" @default.
- W4385698239 doi "https://doi.org/10.1148/ryai.220259" @default.
- W4385698239 hasPublicationYear "2023" @default.
- W4385698239 type Work @default.
- W4385698239 citedByCount "0" @default.
- W4385698239 crossrefType "journal-article" @default.
- W4385698239 hasAuthorship W4385698239A5004526331 @default.
- W4385698239 hasAuthorship W4385698239A5007271191 @default.
- W4385698239 hasAuthorship W4385698239A5010561584 @default.
- W4385698239 hasAuthorship W4385698239A5015077092 @default.
- W4385698239 hasAuthorship W4385698239A5025409813 @default.
- W4385698239 hasAuthorship W4385698239A5029624096 @default.
- W4385698239 hasAuthorship W4385698239A5031598363 @default.
- W4385698239 hasAuthorship W4385698239A5033477318 @default.
- W4385698239 hasAuthorship W4385698239A5035940082 @default.
- W4385698239 hasAuthorship W4385698239A5038376885 @default.
- W4385698239 hasAuthorship W4385698239A5047918797 @default.
- W4385698239 hasAuthorship W4385698239A5057671045 @default.
- W4385698239 hasAuthorship W4385698239A5057702565 @default.
- W4385698239 hasAuthorship W4385698239A5059999814 @default.
- W4385698239 hasAuthorship W4385698239A5060561574 @default.
- W4385698239 hasAuthorship W4385698239A5061446821 @default.
- W4385698239 hasAuthorship W4385698239A5070774369 @default.
- W4385698239 hasAuthorship W4385698239A5071831846 @default.
- W4385698239 hasAuthorship W4385698239A5086830094 @default.
- W4385698239 hasAuthorship W4385698239A5090879728 @default.
- W4385698239 hasConcept C119857082 @default.
- W4385698239 hasConcept C121608353 @default.
- W4385698239 hasConcept C12174686 @default.
- W4385698239 hasConcept C126322002 @default.
- W4385698239 hasConcept C126838900 @default.
- W4385698239 hasConcept C141071460 @default.
- W4385698239 hasConcept C154945302 @default.
- W4385698239 hasConcept C167135981 @default.
- W4385698239 hasConcept C19527891 @default.
- W4385698239 hasConcept C2777432617 @default.
- W4385698239 hasConcept C2779098232 @default.
- W4385698239 hasConcept C2779399171 @default.
- W4385698239 hasConcept C2780472235 @default.
- W4385698239 hasConcept C3020404979 @default.
- W4385698239 hasConcept C38652104 @default.
- W4385698239 hasConcept C41008148 @default.
- W4385698239 hasConcept C530470458 @default.
- W4385698239 hasConcept C58471807 @default.
- W4385698239 hasConcept C71924100 @default.
- W4385698239 hasConceptScore W4385698239C119857082 @default.
- W4385698239 hasConceptScore W4385698239C121608353 @default.
- W4385698239 hasConceptScore W4385698239C12174686 @default.
- W4385698239 hasConceptScore W4385698239C126322002 @default.
- W4385698239 hasConceptScore W4385698239C126838900 @default.
- W4385698239 hasConceptScore W4385698239C141071460 @default.
- W4385698239 hasConceptScore W4385698239C154945302 @default.
- W4385698239 hasConceptScore W4385698239C167135981 @default.
- W4385698239 hasConceptScore W4385698239C19527891 @default.
- W4385698239 hasConceptScore W4385698239C2777432617 @default.
- W4385698239 hasConceptScore W4385698239C2779098232 @default.
- W4385698239 hasConceptScore W4385698239C2779399171 @default.
- W4385698239 hasConceptScore W4385698239C2780472235 @default.
- W4385698239 hasConceptScore W4385698239C3020404979 @default.
- W4385698239 hasConceptScore W4385698239C38652104 @default.
- W4385698239 hasConceptScore W4385698239C41008148 @default.
- W4385698239 hasConceptScore W4385698239C530470458 @default.
- W4385698239 hasConceptScore W4385698239C58471807 @default.
- W4385698239 hasConceptScore W4385698239C71924100 @default.
- W4385698239 hasLocation W43856982391 @default.
- W4385698239 hasOpenAccess W4385698239 @default.
- W4385698239 hasPrimaryLocation W43856982391 @default.
- W4385698239 hasRelatedWork W1842414821 @default.
- W4385698239 hasRelatedWork W2093929361 @default.
- W4385698239 hasRelatedWork W2155053728 @default.
- W4385698239 hasRelatedWork W2172773372 @default.
- W4385698239 hasRelatedWork W2411894266 @default.
- W4385698239 hasRelatedWork W2801970517 @default.
- W4385698239 hasRelatedWork W2992511872 @default.
- W4385698239 hasRelatedWork W3118638086 @default.
- W4385698239 hasRelatedWork W3204371950 @default.