Table 4 Prognostic performance using summation of histologic components in combination with baseline clinical and pathologic features.

From: Deep learning models for histologic grading of breast cancer and association with disease prognosis

Model features

c-index

p-value (likelihood ratio test) for adding features to baseline

Baseline Features Only

0.74 [0.67, 0.81]

N/A (reference)

Baseline + AI-NGS

0.76 [0.69, 0.81]

0.036

Baseline + Single Pathologist

0.75 [0.69, 0.81]

0.064

Baseline + Majority Pathologist

0.76 [0.70, 0.82]

0.023

  1. Cox models were fitted and evaluated directly on the test set and p-values are for likelihood ratio test of baseline versus baseline plus grading scores. Baseline features include age (continuous), TNM (categorical), and ER status (binary). Number of cases represents all cases with baseline characteristics available (n = 762 cases; 82 events). Majority pathologist refers to the majority voted scores of three pathologists. Confidence intervals computed via bootstrap with 1000 iterations.
Back to article page