medical-imaging/yolov8m-chest-xray-classification

Visibility: PUBLIC

Group by

Chest X-ray findings (NIH ChestX-ray14) medical-imaging/chest-xray-findings-classification

Metric

Value

95% CI

Rank

Best in catalogue

Source

Overlap

Mean ROC-AUC, 5 findings (logistic probe) ↑ higher is better · probe

By finding: 5 levels

levels share items; n is per level

0.645

[0.613, 0.675]

1013

3 / 5

0.689

reproduced

none declared

Mean average precision, 5 findings (logistic probe) ↑ higher is better · probe · secondary

By finding: 5 levels

levels share items; n is per level

0.145

[0.126, 0.181]

1013

—

0.203

reproduced

none declared

Metric	Value	95% CI	n	Rank	Best in catalogue	Source	Overlap	Board
ROC-AUC (logistic probe) ↑ higher is better · probe	0.992 best	[0.985, 0.998]	624	1 / 5	0.992	reproduced	overlap Train/test overlap declared by the evaluator: medical-imaging/chest-xray-pneumonia	Board
Accuracy (logistic probe) ↑ higher is better · probe · secondary	0.962 best	[0.946, 0.976]	624	—	0.962	reproduced	overlap Train/test overlap declared by the evaluator: medical-imaging/chest-xray-pneumonia	Board
Sensitivity, pneumonia (logistic probe) ↑ higher is better · probe · secondary	0.997 best	[0.992, 1.000]	624	—	0.997	reproduced	overlap Train/test overlap declared by the evaluator: medical-imaging/chest-xray-pneumonia	Board
Specificity, pneumonia (logistic probe) ↑ higher is better · probe · secondary	0.902 best	[0.859, 0.940]	624	—	0.902	reproduced	overlap Train/test overlap declared by the evaluator: medical-imaging/chest-xray-pneumonia	Board
Average precision (logistic probe) ↑ higher is better · probe · secondary	0.994 best	[0.989, 0.998]	624	—	0.994	reproduced	overlap Train/test overlap declared by the evaluator: medical-imaging/chest-xray-pneumonia	Board