Table 1 Summary of ALK/ROS1 classifier results.

From: Direct identification of ALK and ROS1 fusions in non-small cell lung cancer from hematoxylin and eosin-stained slides using deep learning algorithms

  

Conventional methods

AI-based model

 

N

# Positive

# Negative

TP

TN

FP

FN

Sensitivity

Specificity

Concordance

ALK

72

6

66

6

66

0

0

100%

100%

100%

ROS1

68

2

66

2

65

1

0

100%

98.48%

98.53%

  1. TP true positive, TN true negative, FP false positive, FN false negative.
Back to article page