Table 2.

Comparison of performance between machine learning and logistic regression in sex-specific obesity prediction.

	Gradient boosting, mean (95% CI)		Logistic regression, mean (95% CI)
Metrics	Male participants	Female participants	Male participants	Female participants
Accuracya	0.71 (0.69-0.73)	0.74 (0.72-0.75)	0.70 (0.68-0.72)	0.73 (0.71-0.74)
Sensitivitya	0.75 (0.73-0.78)	0.61 (0.58-0.63)	0.72 (0.69-0.75)	0.60 (0.57-0.63)
Specificitya	0.66 (0.63-0.69)	0.81 (0.80-0.83)	0.68 (0.65-0.71)	0.80 (0.78-0.81)
Area under the curveb	0.78 (0.76-0.80)	0.81 (0.79-0.82)	0.76 (0.74-0.78)	0.79 (0.77-0.80)

^aIn these rows, 95% CIs were calculated assuming Gaussian distribution of the proportions.

^bIn this row, 95% CIs were derived through resampling with the bootstrap percentile method with 2000 repetitions.