Table 3 ROC analysis of standardized integral area algorithm for measuring scoliosis.

From: Application of machine learning standardized integral area algorithm in measuring the scoliosis

Variables

Standardized integral area cutoff value

AUC

Sensitivity

Specificity

Accuracy

PPV

NPV

Moderate scoliosis

0.20

0.865*

0.907

0.635

0.779

0.737

0.859

Severe scoliosis

0.40

0.873*

0.188

1.00

0.936

1.00

0.935

  1. Significant values are in underline.
  2. ROC receiver operating characteristics, AUC area under the ROC curve, PPV positive predictive value, NPV negative predictive value.
  3. *P < 0.05.
Back to article page