You are viewing the site in preview mode

Skip to main content

TableĀ 1 Summary of diagnosis in the training, validation, and test cohorts n = 1074

From: A deep learning model combining circulating tumor cells and radiological features in the multi-classification of mediastinal lesions in comparison with thoracic surgeons: a large-scale retrospective study

Characteristics

Training cohort n = 434

Validation cohort

n = 288

Test cohort

n = 352

Patient demographics

ā€ƒAge, years (mean ± SD)

53.81 ± 12.42

52.41 ± 13.63

53.76 ± 12.88

Sex (n, %)

ā€ƒMale

197(45.39%)

127(44.10%)

162(46.02%)

ā€ƒFemale

237(54.61%)

161(55.90%)

190(53.98%)

Lesion localization

ā€ƒAnterior

297(68.43%)

211(73.26%)

275(78.13%)

ā€ƒMiddle

94(21.66%)

50(17.36%)

54(15.34%)

ā€ƒPosterior

43(9.91%)

27(9.38%)

23(6.53%)

ā€ƒCTCs level (pg/ml)

12.48 ± 5.23

11.02 ± 4.62

15.19 ± 6.58

  1. CTCs Circulating tumor cells