Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383751243> ?p ?o ?g. }
- W4383751243 abstract "Spinal osteoporotic compression fractures (OCFs) can be an early biomarker for osteoporosis but are often subtle, incidental, and underreported. To ensure early diagnosis and treatment of osteoporosis, we aimed to build a deep learning vertebral body classifier for OCFs as a critical component of our future automated opportunistic screening tool.We retrospectively assembled a local dataset, including 1790 subjects and 15,050 vertebral bodies (thoracic and lumbar). Each vertebral body was annotated using an adaption of the modified-2 algorithm-based qualitative criteria. The Osteoporotic Fractures in Men (MrOS) Study dataset provided thoracic and lumbar spine radiographs of 5994 men from six clinical centers. Using both datasets, five deep learning algorithms were trained to classify each individual vertebral body of the spine radiographs. Classification performance was compared for these models using multiple metrics, including the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and positive predictive value (PPV).Our best model, built with ensemble averaging, achieved an AUC-ROC of 0.948 and 0.936 on the local dataset's test set and the MrOS dataset's test set, respectively. After setting the cutoff threshold to prioritize PPV, this model achieved a sensitivity of 54.5% and 47.8%, a specificity of 99.7% and 99.6%, and a PPV of 89.8% and 94.8%.Our model achieved an AUC-ROC>0.90 on both datasets. This testing shows some generalizability to real-world clinical datasets and a suitable performance for a future opportunistic osteoporosis screening tool." @default.
- W4383751243 created "2023-07-11" @default.
- W4383751243 creator A5000023033 @default.
- W4383751243 creator A5006366010 @default.
- W4383751243 creator A5008749627 @default.
- W4383751243 creator A5012414075 @default.
- W4383751243 creator A5013313674 @default.
- W4383751243 creator A5027997740 @default.
- W4383751243 creator A5044755649 @default.
- W4383751243 creator A5048894863 @default.
- W4383751243 creator A5051835976 @default.
- W4383751243 creator A5061809927 @default.
- W4383751243 creator A5066319123 @default.
- W4383751243 creator A5080086968 @default.
- W4383751243 creator A5083551874 @default.
- W4383751243 creator A5084866341 @default.
- W4383751243 creator A5092438344 @default.
- W4383751243 date "2023-07-01" @default.
- W4383751243 modified "2023-10-01" @default.
- W4383751243 title "Generalizability of Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs Using an Adaptation of the Modified-2 Algorithm-Based Qualitative Criteria" @default.
- W4383751243 cites W1964746339 @default.
- W4383751243 cites W1966507238 @default.
- W4383751243 cites W2027387089 @default.
- W4383751243 cites W2044178924 @default.
- W4383751243 cites W2061672958 @default.
- W4383751243 cites W2076731988 @default.
- W4383751243 cites W2080582155 @default.
- W4383751243 cites W2082229075 @default.
- W4383751243 cites W2112965041 @default.
- W4383751243 cites W2127003583 @default.
- W4383751243 cites W2165967346 @default.
- W4383751243 cites W2170424332 @default.
- W4383751243 cites W2231524159 @default.
- W4383751243 cites W2282007373 @default.
- W4383751243 cites W2328112189 @default.
- W4383751243 cites W2571578109 @default.
- W4383751243 cites W2592719727 @default.
- W4383751243 cites W2736858909 @default.
- W4383751243 cites W2800043213 @default.
- W4383751243 cites W2825122700 @default.
- W4383751243 cites W2905420468 @default.
- W4383751243 cites W2955713411 @default.
- W4383751243 cites W2990294637 @default.
- W4383751243 cites W3006539134 @default.
- W4383751243 cites W3043740578 @default.
- W4383751243 cites W3045126142 @default.
- W4383751243 cites W3090504844 @default.
- W4383751243 cites W3096754190 @default.
- W4383751243 cites W3102883434 @default.
- W4383751243 cites W3121936649 @default.
- W4383751243 cites W3123412464 @default.
- W4383751243 cites W3134978958 @default.
- W4383751243 cites W3208994043 @default.
- W4383751243 cites W4205129288 @default.
- W4383751243 cites W4221071228 @default.
- W4383751243 cites W4285554252 @default.
- W4383751243 doi "https://doi.org/10.1016/j.acra.2023.04.023" @default.
- W4383751243 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37438161" @default.
- W4383751243 hasPublicationYear "2023" @default.
- W4383751243 type Work @default.
- W4383751243 citedByCount "1" @default.
- W4383751243 countsByYear W43837512432023 @default.
- W4383751243 crossrefType "journal-article" @default.
- W4383751243 hasAuthorship W4383751243A5000023033 @default.
- W4383751243 hasAuthorship W4383751243A5006366010 @default.
- W4383751243 hasAuthorship W4383751243A5008749627 @default.
- W4383751243 hasAuthorship W4383751243A5012414075 @default.
- W4383751243 hasAuthorship W4383751243A5013313674 @default.
- W4383751243 hasAuthorship W4383751243A5027997740 @default.
- W4383751243 hasAuthorship W4383751243A5044755649 @default.
- W4383751243 hasAuthorship W4383751243A5048894863 @default.
- W4383751243 hasAuthorship W4383751243A5051835976 @default.
- W4383751243 hasAuthorship W4383751243A5061809927 @default.
- W4383751243 hasAuthorship W4383751243A5066319123 @default.
- W4383751243 hasAuthorship W4383751243A5080086968 @default.
- W4383751243 hasAuthorship W4383751243A5083551874 @default.
- W4383751243 hasAuthorship W4383751243A5084866341 @default.
- W4383751243 hasAuthorship W4383751243A5092438344 @default.
- W4383751243 hasConcept C105795698 @default.
- W4383751243 hasConcept C108583219 @default.
- W4383751243 hasConcept C11413529 @default.
- W4383751243 hasConcept C119857082 @default.
- W4383751243 hasConcept C121332964 @default.
- W4383751243 hasConcept C126322002 @default.
- W4383751243 hasConcept C126838900 @default.
- W4383751243 hasConcept C154945302 @default.
- W4383751243 hasConcept C163864269 @default.
- W4383751243 hasConcept C169903167 @default.
- W4383751243 hasConcept C27158222 @default.
- W4383751243 hasConcept C2776541429 @default.
- W4383751243 hasConcept C2778217198 @default.
- W4383751243 hasConcept C33923547 @default.
- W4383751243 hasConcept C36454342 @default.
- W4383751243 hasConcept C41008148 @default.
- W4383751243 hasConcept C44575665 @default.
- W4383751243 hasConcept C58471807 @default.
- W4383751243 hasConcept C62520636 @default.
- W4383751243 hasConcept C71924100 @default.
- W4383751243 hasConceptScore W4383751243C105795698 @default.
- W4383751243 hasConceptScore W4383751243C108583219 @default.