Skip to main content
. 2024 Feb 6;16(4):469. doi: 10.3390/nu16040469

Table 2.

Classification of ChatGPT responses in comparison to guideline recommendations.

Topic Appropriate Not Fully Matched General Advice Not Supported Inappropriate Missing
Hypercholesterolemia
Hypertriglyceridemia
15 (71.4%) 2 (9.5%) 4 (19.0%) 0 0 2
Arterial hypertension 8 (66.7%) 1 (8.3%) 3 (25.0%) 0 0 1
Obesity 7 (70.0%) 0 2 (20.0%) 0 1 (10.0%) 2
Type 2 diabetes mellitus 10 (71.4%) 1 (7.1%) 2 (14.3%) 1 (7.1%) 0 3
NAFLD 11 (73.3%) 1 (6.7%) 2 (13.3%) 0 1 (6.7%) 2
Chronic kidney disease 7 (70.0%) 1 (10.0%) 2 (20.0%) 0 0 2
Sarcopenia 5 (55.6%) 0 4 (44.4%) 0 0 0