Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content

Table 3 The performance of clinical and radiomic models for PFS prediction

From: Early prediction of progression-free survival of patients with locally advanced nasopharyngeal carcinoma using multi-parametric MRI radiomics

Models

C-index (95%CI)

Training dataset

P-value

Validation dataset

P-value

Clinical model

0.722 (0.698–0.746)

< 0.001*

0.544 (0.487–0.601)

< 0.001*

DWI-based radiomic model

0.786 (0.759–0.813)

< 0.001*

0.739 (0.712–0.766)

0.013*

T1WI-based radiomic model

0.875 (0.861–0.889)

< 0.001*

0.734 (0.709–0.759)

0.004*

cT1WI-based radiomic model

0.924 (0.910–0.938)

0.752

0.722 (0.697–0.747)

< 0.001*

T2WI-based radiomic model

0.611 (0.587–0.635)

< 0.001*

0.598 (0.541–0.655)

< 0.001*

T1WI- plus cT1WI-based radiomic model

0.927 (0.900-0.954)

0.692

0.747 (0.720–0.774)

0.038

Fusion radiomic model

0.921 (0.907–0.935)

Ref.

0.788 (0.763–0.813)

Ref.

Combined model

0.945 (0.931–0.959)

0.012*

0.788 (0.763–0.813)

1

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us