Table 4 Score distribution of ChatGPT-4 responses according to the mDISCERN scale and quality classification.

From: Evaluation of the reliability and readability of ChatGPT-4 responses regarding hypothyroidism during pregnancy

 

n = 19

mDISCERN criteria

 Poor (< 40% score [ < 16])

0 (0%)

 Fair (40–79% score [16–31])

15 (78.9%)

 Good (≥ 80% score [32])

4 (21.1%)

Quality classification

 Low quality

1 (5.3%)

 Moderate quality

2 (10.5%)

 High quality

16 (84.2%)

  1. mDISCERN Modified DISCERN, GQS Global quality score. Categorical variables are presented as n (%) in the table.
Back to article page