# Covid/non-covid classification on RSNA and RICORD CXR (test) Source: [Covid/non-covid classification on RSNA and RICORD CXR (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:56.226Z Evaluation of binary classification performance (COVID vs non-COVID) on the test split combining RSNA and RICORD Chest X-ray datasets, reporting Accuracy and True Positive Rate. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Covid/non-covid classification | | Dataset (including any stated split) | RSNA and RICORD CXR (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [True Positive Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SS-CXR | 98.25 | Not recorded | 68fa6f701e209131cea45921 | | DenseNet-169 | 98.15 | Not recorded | 68fa6f701e209131cea45921 | | EfficientNet-B2 | 97.6 | Not recorded | 68fa6f701e209131cea45921 | | InceptionResnet-V2 | 97.55 | Not recorded | 68fa6f701e209131cea45921 | | Inception-V3 | 97.5 | Not recorded | 68fa6f701e209131cea45921 | | VGG-16 | 97.5 | Not recorded | 68fa6f701e209131cea45921 | | DenseNet-121 | 96.5 | Not recorded | 68fa6f701e209131cea45921 | | ResNet50-V2 | 96.5 | Not recorded | 68fa6f701e209131cea45921 | | Covid-Net | 96.3 | Not recorded | 68fa6f701e209131cea45921 | | VGG-19 | 96.25 | Not recorded | 68fa6f701e209131cea45921 | | ViT-S | 89.25 | Not recorded | 68fa6f701e209131cea45921 | | Thoracic Radiologist | 64.373 | Not recorded | 68fa6f701e209131cea45921 | ### SS-CXR Accuracy: 98.25. Result ID: 6990d0e13a6c31484903837a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"SSL"}. This record does not assert independent reproduction. ### DenseNet-169 Accuracy: 98.15. Result ID: 6990d0e13a6c31484903837c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training":"None"}. This record does not assert independent reproduction. ### EfficientNet-B2 Accuracy: 97.6. Result ID: 6990d0e13a6c31484903837d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training":"None"}. This record does not assert independent reproduction. ### InceptionResnet-V2 Accuracy: 97.55. Result ID: 6990d0e13a6c31484903837e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training":"None"}. This record does not assert independent reproduction. ### Inception-V3 Accuracy: 97.5. Result ID: 6990d0e13a6c31484903837f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training":"None"}. This record does not assert independent reproduction. ### VGG-16 Accuracy: 97.5. Result ID: 6990d0e13a6c314849038380. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training":"None"}. This record does not assert independent reproduction. ### DenseNet-121 Accuracy: 96.5. Result ID: 6990d0e13a6c314849038381. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training Dataset":"CXR"}. This record does not assert independent reproduction. ### ResNet50-V2 Accuracy: 96.5. Result ID: 6990d0e13a6c314849038382. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training Dataset":"BiT-M"}. This record does not assert independent reproduction. ### Covid-Net Accuracy: 96.3. Result ID: 6990d0e13a6c314849038383. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training Dataset":"CXR-2"}. This record does not assert independent reproduction. ### VGG-19 Accuracy: 96.25. Result ID: 6990d0e13a6c314849038384. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Pre-training Dataset":"ImageNet"}. This record does not assert independent reproduction. ### ViT-S Accuracy: 89.25. Result ID: 6990d0e13a6c31484903837b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Learning Paradigm":"SSL"}. This record does not assert independent reproduction. ### Thoracic Radiologist Accuracy: 64.373. Result ID: 6990d0e13a6c314849038379. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Human Baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.