Skip to main content

Table 2 Pooled results of per-patient and per-node diagnosis from deep learning, radiomics and radiologists

From: Artificial intelligence for pre-operative lymph node staging in colorectal cancer: a systematic review and meta-analysis

Variable

Studies analysed

Type of malignancy

No. of studies

Pooled results (95% CI)

Heterogeneity (I2, %)

Heterogeneity P Value

Deep learning

 AUROC per-patient

[11, 12]

Rectal

2

0.917 (0.882–0.952)

0.00

0.829

Radiomics

 Sensitivity per-patient

[22, 24, 26]

Rectal

3

0.776 (0.685–0.851)

0.00

0.368

 Sensitivity per-node

[27, 33]

Rectal

2

0.896 (0.834–0.941)

0.00

0.393

 Specificity per-patient

[22, 24, 26]

Rectal

3

0.676 (0.608–0.739)

75.4

0.017

 Specificity per-node

[27, 33]

Rectal

2

0.743 (0.665–0.811)

87.8

0.004

 AUROC per patient

[21, 31]

Colorectal

2

0.727 (0.633–0.821)

94.1

< 0.0001

 AUROC per patient

[22,23,24, 26, 30]

Rectal

5

0.808 (0.739–0.876)

63.3

0.028

 AUROC per node

[27, 33]

Rectal

2

0.846 (0.803–0.890)

0.00

0.433

Radiologist

 Sensitivity per-patient

[21, 31]

Colorectal

2

0.641 (0.577–0.702)

70.9

0.064

 Specificity per-patient

[21, 31]

Colorectal

2

0.657 (0.597–0.713)

11.1

0.289

 Sensitivity per-patient

[22,23,24, 26]

Rectal

4

0.678 (0.628–0.726)

57.5

0.070

 Specificity per-patient

[22,23,24, 26]

Rectal

4

0.701 (0.667–0.733)

97.8

< 0.0001

 AUROC per-patient

[21, 31]

Colorectal

2

0.676 (0.627–0.725)

58.4

0.121

 AUROC per-patient

[22,23,24, 26, 30]

Rectal

5

0.688 (0.603 to 0.772)

93.4

< 0.0001

  1. AUROC, area under the receiver operating characteristic; CI, confidence interval